diff options
Diffstat (limited to 'fs')
417 files changed, 11373 insertions, 7432 deletions
diff --git a/fs/9p/fid.c b/fs/9p/fid.c index baf2b152229e..23cf9b2fbfe4 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -28,14 +28,18 @@ static inline void __add_fid(struct dentry *dentry, struct p9_fid *fid) /** * v9fs_fid_add - add a fid to a dentry * @dentry: dentry that the fid is being added to - * @fid: fid to add + * @pfid: fid to add, NULLed out * */ -void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid) +void v9fs_fid_add(struct dentry *dentry, struct p9_fid **pfid) { + struct p9_fid *fid = *pfid; + spin_lock(&dentry->d_lock); __add_fid(dentry, fid); spin_unlock(&dentry->d_lock); + + *pfid = NULL; } /** @@ -56,7 +60,7 @@ static struct p9_fid *v9fs_fid_find_inode(struct inode *inode, kuid_t uid) h = (struct hlist_head *)&inode->i_private; hlist_for_each_entry(fid, h, ilist) { if (uid_eq(fid->uid, uid)) { - refcount_inc(&fid->count); + p9_fid_get(fid); ret = fid; break; } @@ -68,15 +72,19 @@ static struct p9_fid *v9fs_fid_find_inode(struct inode *inode, kuid_t uid) /** * v9fs_open_fid_add - add an open fid to an inode * @inode: inode that the fid is being added to - * @fid: fid to add + * @pfid: fid to add, NULLed out * */ -void v9fs_open_fid_add(struct inode *inode, struct p9_fid *fid) +void v9fs_open_fid_add(struct inode *inode, struct p9_fid **pfid) { + struct p9_fid *fid = *pfid; + spin_lock(&inode->i_lock); hlist_add_head(&fid->ilist, (struct hlist_head *)&inode->i_private); spin_unlock(&inode->i_lock); + + *pfid = NULL; } @@ -104,7 +112,7 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any) hlist_for_each_entry(fid, h, dlist) { if (any || uid_eq(fid->uid, uid)) { ret = fid; - refcount_inc(&ret->count); + p9_fid_get(ret); break; } } @@ -150,9 +158,9 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry, { struct dentry *ds; const unsigned char **wnames, *uname; - int i, n, l, clone, access; + int i, n, l, access; struct v9fs_session_info *v9ses; - struct p9_fid *fid, *old_fid; + struct p9_fid *fid, *root_fid, *old_fid; v9ses = v9fs_dentry2v9ses(dentry); access = v9ses->flags & V9FS_ACCESS_MASK; @@ -169,17 +177,17 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry, fid = v9fs_fid_find(ds, uid, any); if (fid) { /* Found the parent fid do a lookup with that */ - struct p9_fid *ofid = fid; + old_fid = fid; - fid = p9_client_walk(ofid, 1, &dentry->d_name.name, 1); - p9_client_clunk(ofid); + fid = p9_client_walk(old_fid, 1, &dentry->d_name.name, 1); + p9_fid_put(old_fid); goto fid_out; } up_read(&v9ses->rename_sem); /* start from the root and try to do a lookup */ - fid = v9fs_fid_find(dentry->d_sb->s_root, uid, any); - if (!fid) { + root_fid = v9fs_fid_find(dentry->d_sb->s_root, uid, any); + if (!root_fid) { /* the user is not attached to the fs yet */ if (access == V9FS_ACCESS_SINGLE) return ERR_PTR(-EPERM); @@ -194,12 +202,13 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry, if (IS_ERR(fid)) return fid; - refcount_inc(&fid->count); - v9fs_fid_add(dentry->d_sb->s_root, fid); + root_fid = p9_fid_get(fid); + v9fs_fid_add(dentry->d_sb->s_root, &fid); } /* If we are root ourself just return that */ if (dentry->d_sb->s_root == dentry) - return fid; + return root_fid; + /* * Do a multipath walk with attached root. * When walking parent we need to make sure we @@ -211,19 +220,20 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry, fid = ERR_PTR(n); goto err_out; } - old_fid = fid; - clone = 1; + fid = root_fid; + old_fid = root_fid; i = 0; while (i < n) { l = min(n - i, P9_MAXWELEM); /* * We need to hold rename lock when doing a multipath - * walk to ensure none of the patch component change + * walk to ensure none of the path components change */ - fid = p9_client_walk(fid, l, &wnames[i], clone); + fid = p9_client_walk(old_fid, l, &wnames[i], + old_fid == root_fid /* clone */); /* non-cloning walk will return the same fid */ if (fid != old_fid) { - p9_client_clunk(old_fid); + p9_fid_put(old_fid); old_fid = fid; } if (IS_ERR(fid)) { @@ -231,7 +241,6 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry, goto err_out; } i += l; - clone = 0; } kfree(wnames); fid_out: @@ -239,11 +248,11 @@ fid_out: spin_lock(&dentry->d_lock); if (d_unhashed(dentry)) { spin_unlock(&dentry->d_lock); - p9_client_clunk(fid); + p9_fid_put(fid); fid = ERR_PTR(-ENOENT); } else { __add_fid(dentry, fid); - refcount_inc(&fid->count); + p9_fid_get(fid); spin_unlock(&dentry->d_lock); } } @@ -300,7 +309,7 @@ struct p9_fid *v9fs_writeback_fid(struct dentry *dentry) fid = clone_fid(ofid); if (IS_ERR(fid)) goto error_out; - p9_client_clunk(ofid); + p9_fid_put(ofid); /* * writeback fid will only be used to write back the * dirty pages. We always request for the open fid in read-write @@ -309,7 +318,7 @@ struct p9_fid *v9fs_writeback_fid(struct dentry *dentry) */ err = p9_client_open(fid, O_RDWR); if (err < 0) { - p9_client_clunk(fid); + p9_fid_put(fid); fid = ERR_PTR(err); goto error_out; } diff --git a/fs/9p/fid.h b/fs/9p/fid.h index f7f33509e169..8a4e8cd12ca2 100644 --- a/fs/9p/fid.h +++ b/fs/9p/fid.h @@ -13,9 +13,9 @@ static inline struct p9_fid *v9fs_parent_fid(struct dentry *dentry) { return v9fs_fid_lookup(dentry->d_parent); } -void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid); +void v9fs_fid_add(struct dentry *dentry, struct p9_fid **fid); struct p9_fid *v9fs_writeback_fid(struct dentry *dentry); -void v9fs_open_fid_add(struct inode *inode, struct p9_fid *fid); +void v9fs_open_fid_add(struct inode *inode, struct p9_fid **fid); static inline struct p9_fid *clone_fid(struct p9_fid *fid) { return IS_ERR(fid) ? fid : p9_client_walk(fid, 0, NULL, 1); @@ -29,7 +29,7 @@ static inline struct p9_fid *v9fs_fid_clone(struct dentry *dentry) return fid; nfid = clone_fid(fid); - p9_client_clunk(fid); + p9_fid_put(fid); return nfid; } #endif diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index d0833fa69faf..47b9a1122f34 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -73,7 +73,7 @@ static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file) BUG_ON(!fid); } - refcount_inc(&fid->count); + p9_fid_get(fid); rreq->netfs_priv = fid; return 0; } @@ -86,7 +86,7 @@ static void v9fs_free_request(struct netfs_io_request *rreq) { struct p9_fid *fid = rreq->netfs_priv; - p9_client_clunk(fid); + p9_fid_put(fid); } /** diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index 1c609e99d280..f89f01734587 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -54,7 +54,7 @@ static void v9fs_dentry_release(struct dentry *dentry) p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n", dentry, dentry); hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata) - p9_client_clunk(hlist_entry(p, struct p9_fid, dlist)); + p9_fid_put(hlist_entry(p, struct p9_fid, dlist)); dentry->d_fsdata = NULL; } @@ -85,7 +85,7 @@ static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) retval = v9fs_refresh_inode_dotl(fid, inode); else retval = v9fs_refresh_inode(fid, inode); - p9_client_clunk(fid); + p9_fid_put(fid); if (retval == -ENOENT) return 0; diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 958680f7f23e..000fbaae9b18 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -218,7 +218,7 @@ int v9fs_dir_release(struct inode *inode, struct file *filp) spin_lock(&inode->i_lock); hlist_del(&fid->ilist); spin_unlock(&inode->i_lock); - p9_client_clunk(fid); + p9_fid_put(fid); } if ((filp->f_mode & FMODE_WRITE)) { diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 2573c08f335c..aec43ba83799 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -63,15 +63,16 @@ int v9fs_file_open(struct inode *inode, struct file *file) err = p9_client_open(fid, omode); if (err < 0) { - p9_client_clunk(fid); + p9_fid_put(fid); return err; } if ((file->f_flags & O_APPEND) && (!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses))) generic_file_llseek(file, 0, SEEK_END); + + file->private_data = fid; } - file->private_data = fid; mutex_lock(&v9inode->v_mutex); if ((v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) && !v9inode->writeback_fid && @@ -95,10 +96,10 @@ int v9fs_file_open(struct inode *inode, struct file *file) if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) fscache_use_cookie(v9fs_inode_cookie(v9inode), file->f_mode & FMODE_WRITE); - v9fs_open_fid_add(inode, fid); + v9fs_open_fid_add(inode, &fid); return 0; out_error: - p9_client_clunk(file->private_data); + p9_fid_put(file->private_data); file->private_data = NULL; return err; } diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 3d8297714772..4d1a4a8d9277 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -399,10 +399,8 @@ void v9fs_evict_inode(struct inode *inode) fscache_relinquish_cookie(v9fs_inode_cookie(v9inode), false); /* clunk the fid stashed in writeback_fid */ - if (v9inode->writeback_fid) { - p9_client_clunk(v9inode->writeback_fid); - v9inode->writeback_fid = NULL; - } + p9_fid_put(v9inode->writeback_fid); + v9inode->writeback_fid = NULL; } static int v9fs_test_inode(struct inode *inode, void *data) @@ -569,7 +567,7 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags) if (v9fs_proto_dotl(v9ses)) retval = p9_client_unlinkat(dfid, dentry->d_name.name, v9fs_at_to_dotl_flags(flags)); - p9_client_clunk(dfid); + p9_fid_put(dfid); if (retval == -EOPNOTSUPP) { /* Try the one based on path */ v9fid = v9fs_fid_clone(dentry); @@ -633,14 +631,12 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir, if (IS_ERR(ofid)) { err = PTR_ERR(ofid); p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); - p9_client_clunk(dfid); - return ERR_PTR(err); + goto error; } err = p9_client_fcreate(ofid, name, perm, mode, extension); if (err < 0) { p9_debug(P9_DEBUG_VFS, "p9_client_fcreate failed %d\n", err); - p9_client_clunk(dfid); goto error; } @@ -651,8 +647,6 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir, err = PTR_ERR(fid); p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); - fid = NULL; - p9_client_clunk(dfid); goto error; } /* @@ -663,21 +657,17 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir, err = PTR_ERR(inode); p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", err); - p9_client_clunk(dfid); goto error; } - v9fs_fid_add(dentry, fid); + v9fs_fid_add(dentry, &fid); d_instantiate(dentry, inode); } - p9_client_clunk(dfid); + p9_fid_put(dfid); return ofid; error: - if (ofid) - p9_client_clunk(ofid); - - if (fid) - p9_client_clunk(fid); - + p9_fid_put(dfid); + p9_fid_put(ofid); + p9_fid_put(fid); return ERR_PTR(err); } @@ -708,7 +698,7 @@ v9fs_vfs_create(struct user_namespace *mnt_userns, struct inode *dir, return PTR_ERR(fid); v9fs_invalidate_inode_attr(dir); - p9_client_clunk(fid); + p9_fid_put(fid); return 0; } @@ -744,7 +734,7 @@ static int v9fs_vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, } if (fid) - p9_client_clunk(fid); + p9_fid_put(fid); return err; } @@ -785,7 +775,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, */ name = dentry->d_name.name; fid = p9_client_walk(dfid, 1, &name, 1); - p9_client_clunk(dfid); + p9_fid_put(dfid); if (fid == ERR_PTR(-ENOENT)) inode = NULL; else if (IS_ERR(fid)) @@ -804,11 +794,11 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, res = d_splice_alias(inode, dentry); if (!IS_ERR(fid)) { if (!res) - v9fs_fid_add(dentry, fid); + v9fs_fid_add(dentry, &fid); else if (!IS_ERR(res)) - v9fs_fid_add(res, fid); + v9fs_fid_add(res, &fid); else - p9_client_clunk(fid); + p9_fid_put(fid); } return res; } @@ -847,7 +837,6 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, v9fs_proto_dotu(v9ses))); if (IS_ERR(fid)) { err = PTR_ERR(fid); - fid = NULL; goto error; } @@ -882,7 +871,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) fscache_use_cookie(v9fs_inode_cookie(v9inode), file->f_mode & FMODE_WRITE); - v9fs_open_fid_add(inode, fid); + v9fs_open_fid_add(inode, &fid); file->f_mode |= FMODE_CREATED; out: @@ -890,8 +879,7 @@ out: return err; error: - if (fid) - p9_client_clunk(fid); + p9_fid_put(fid); goto out; } @@ -939,9 +927,9 @@ v9fs_vfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, struct inode *old_inode; struct inode *new_inode; struct v9fs_session_info *v9ses; - struct p9_fid *oldfid, *dfid; - struct p9_fid *olddirfid; - struct p9_fid *newdirfid; + struct p9_fid *oldfid = NULL, *dfid = NULL; + struct p9_fid *olddirfid = NULL; + struct p9_fid *newdirfid = NULL; struct p9_wstat wstat; if (flags) @@ -958,21 +946,22 @@ v9fs_vfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, dfid = v9fs_parent_fid(old_dentry); olddirfid = clone_fid(dfid); - if (dfid && !IS_ERR(dfid)) - p9_client_clunk(dfid); + p9_fid_put(dfid); + dfid = NULL; if (IS_ERR(olddirfid)) { retval = PTR_ERR(olddirfid); - goto done; + goto error; } dfid = v9fs_parent_fid(new_dentry); newdirfid = clone_fid(dfid); - p9_client_clunk(dfid); + p9_fid_put(dfid); + dfid = NULL; if (IS_ERR(newdirfid)) { retval = PTR_ERR(newdirfid); - goto clunk_olddir; + goto error; } down_write(&v9ses->rename_sem); @@ -983,7 +972,7 @@ v9fs_vfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, retval = p9_client_rename(oldfid, newdirfid, new_dentry->d_name.name); if (retval != -EOPNOTSUPP) - goto clunk_newdir; + goto error_locked; } if (old_dentry->d_parent != new_dentry->d_parent) { /* @@ -992,14 +981,14 @@ v9fs_vfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, p9_debug(P9_DEBUG_ERROR, "old dir and new dir are different\n"); retval = -EXDEV; - goto clunk_newdir; + goto error_locked; } v9fs_blank_wstat(&wstat); wstat.muid = v9ses->uname; wstat.name = new_dentry->d_name.name; retval = p9_client_wstat(oldfid, &wstat); -clunk_newdir: +error_locked: if (!retval) { if (new_inode) { if (S_ISDIR(new_inode->i_mode)) @@ -1020,13 +1009,11 @@ clunk_newdir: d_move(old_dentry, new_dentry); } up_write(&v9ses->rename_sem); - p9_client_clunk(newdirfid); - -clunk_olddir: - p9_client_clunk(olddirfid); -done: - p9_client_clunk(oldfid); +error: + p9_fid_put(newdirfid); + p9_fid_put(olddirfid); + p9_fid_put(oldfid); return retval; } @@ -1060,7 +1047,7 @@ v9fs_vfs_getattr(struct user_namespace *mnt_userns, const struct path *path, return PTR_ERR(fid); st = p9_client_stat(fid); - p9_client_clunk(fid); + p9_fid_put(fid); if (IS_ERR(st)) return PTR_ERR(st); @@ -1136,7 +1123,7 @@ static int v9fs_vfs_setattr(struct user_namespace *mnt_userns, retval = p9_client_wstat(fid, &wstat); if (use_dentry) - p9_client_clunk(fid); + p9_fid_put(fid); if (retval < 0) return retval; @@ -1261,7 +1248,7 @@ static const char *v9fs_vfs_get_link(struct dentry *dentry, return ERR_CAST(fid); st = p9_client_stat(fid); - p9_client_clunk(fid); + p9_fid_put(fid); if (IS_ERR(st)) return ERR_CAST(st); @@ -1308,7 +1295,7 @@ static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry, return PTR_ERR(fid); v9fs_invalidate_inode_attr(dir); - p9_client_clunk(fid); + p9_fid_put(fid); return 0; } @@ -1364,7 +1351,7 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir, v9fs_refresh_inode(oldfid, d_inode(old_dentry)); v9fs_invalidate_inode_attr(dir); } - p9_client_clunk(oldfid); + p9_fid_put(oldfid); return retval; } diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index b6eb1160296c..5cfa4b4f070f 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -238,7 +238,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, struct inode *inode; struct p9_fid *fid = NULL; struct v9fs_inode *v9inode; - struct p9_fid *dfid, *ofid, *inode_fid; + struct p9_fid *dfid = NULL, *ofid = NULL, *inode_fid = NULL; struct v9fs_session_info *v9ses; struct posix_acl *pacl = NULL, *dacl = NULL; struct dentry *res = NULL; @@ -274,7 +274,6 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, if (IS_ERR(ofid)) { err = PTR_ERR(ofid); p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); - p9_client_clunk(dfid); goto out; } @@ -286,38 +285,34 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, if (err) { p9_debug(P9_DEBUG_VFS, "Failed to get acl values in creat %d\n", err); - p9_client_clunk(dfid); - goto error; + goto out; } err = p9_client_create_dotl(ofid, name, v9fs_open_to_dotl_flags(flags), mode, gid, &qid); if (err < 0) { p9_debug(P9_DEBUG_VFS, "p9_client_open_dotl failed in creat %d\n", err); - p9_client_clunk(dfid); - goto error; + goto out; } v9fs_invalidate_inode_attr(dir); /* instantiate inode and assign the unopened fid to the dentry */ fid = p9_client_walk(dfid, 1, &name, 1); - p9_client_clunk(dfid); if (IS_ERR(fid)) { err = PTR_ERR(fid); p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); - fid = NULL; - goto error; + goto out; } inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", err); - goto error; + goto out; } /* Now set the ACL based on the default value */ v9fs_set_create_acl(inode, fid, dacl, pacl); - v9fs_fid_add(dentry, fid); + v9fs_fid_add(dentry, &fid); d_instantiate(dentry, inode); v9inode = V9FS_I(inode); @@ -336,7 +331,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, if (IS_ERR(inode_fid)) { err = PTR_ERR(inode_fid); mutex_unlock(&v9inode->v_mutex); - goto err_clunk_old_fid; + goto out; } v9inode->writeback_fid = (void *) inode_fid; } @@ -344,25 +339,20 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, /* Since we are opening a file, assign the open fid to the file */ err = finish_open(file, dentry, generic_file_open); if (err) - goto err_clunk_old_fid; + goto out; file->private_data = ofid; if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) fscache_use_cookie(v9fs_inode_cookie(v9inode), file->f_mode & FMODE_WRITE); - v9fs_open_fid_add(inode, ofid); + v9fs_open_fid_add(inode, &ofid); file->f_mode |= FMODE_CREATED; out: + p9_fid_put(dfid); + p9_fid_put(ofid); + p9_fid_put(fid); v9fs_put_acl(dacl, pacl); dput(res); return err; - -error: - if (fid) - p9_client_clunk(fid); -err_clunk_old_fid: - if (ofid) - p9_client_clunk(ofid); - goto out; } /** @@ -400,7 +390,6 @@ static int v9fs_vfs_mkdir_dotl(struct user_namespace *mnt_userns, if (IS_ERR(dfid)) { err = PTR_ERR(dfid); p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err); - dfid = NULL; goto error; } @@ -422,7 +411,6 @@ static int v9fs_vfs_mkdir_dotl(struct user_namespace *mnt_userns, err = PTR_ERR(fid); p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); - fid = NULL; goto error; } @@ -435,10 +423,9 @@ static int v9fs_vfs_mkdir_dotl(struct user_namespace *mnt_userns, err); goto error; } - v9fs_fid_add(dentry, fid); + v9fs_fid_add(dentry, &fid); v9fs_set_create_acl(inode, fid, dacl, pacl); d_instantiate(dentry, inode); - fid = NULL; err = 0; } else { /* @@ -457,10 +444,9 @@ static int v9fs_vfs_mkdir_dotl(struct user_namespace *mnt_userns, inc_nlink(dir); v9fs_invalidate_inode_attr(dir); error: - if (fid) - p9_client_clunk(fid); + p9_fid_put(fid); v9fs_put_acl(dacl, pacl); - p9_client_clunk(dfid); + p9_fid_put(dfid); return err; } @@ -489,7 +475,7 @@ v9fs_vfs_getattr_dotl(struct user_namespace *mnt_userns, */ st = p9_client_getattr_dotl(fid, P9_STATS_ALL); - p9_client_clunk(fid); + p9_fid_put(fid); if (IS_ERR(st)) return PTR_ERR(st); @@ -603,7 +589,7 @@ int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns, retval = p9_client_setattr(fid, &p9attr); if (retval < 0) { if (use_dentry) - p9_client_clunk(fid); + p9_fid_put(fid); return retval; } @@ -619,12 +605,12 @@ int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns, retval = v9fs_acl_chmod(inode, fid); if (retval < 0) { if (use_dentry) - p9_client_clunk(fid); + p9_fid_put(fid); return retval; } } if (use_dentry) - p9_client_clunk(fid); + p9_fid_put(fid); return 0; } @@ -743,7 +729,6 @@ v9fs_vfs_symlink_dotl(struct user_namespace *mnt_userns, struct inode *dir, err = PTR_ERR(fid); p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); - fid = NULL; goto error; } @@ -755,9 +740,8 @@ v9fs_vfs_symlink_dotl(struct user_namespace *mnt_userns, struct inode *dir, err); goto error; } - v9fs_fid_add(dentry, fid); + v9fs_fid_add(dentry, &fid); d_instantiate(dentry, inode); - fid = NULL; err = 0; } else { /* Not in cached mode. No need to populate inode with stat */ @@ -770,10 +754,8 @@ v9fs_vfs_symlink_dotl(struct user_namespace *mnt_userns, struct inode *dir, } error: - if (fid) - p9_client_clunk(fid); - - p9_client_clunk(dfid); + p9_fid_put(fid); + p9_fid_put(dfid); return err; } @@ -803,14 +785,14 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, oldfid = v9fs_fid_lookup(old_dentry); if (IS_ERR(oldfid)) { - p9_client_clunk(dfid); + p9_fid_put(dfid); return PTR_ERR(oldfid); } err = p9_client_link(dfid, oldfid, dentry->d_name.name); - p9_client_clunk(dfid); - p9_client_clunk(oldfid); + p9_fid_put(dfid); + p9_fid_put(oldfid); if (err < 0) { p9_debug(P9_DEBUG_VFS, "p9_client_link failed %d\n", err); return err; @@ -826,7 +808,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, return PTR_ERR(fid); v9fs_refresh_inode_dotl(fid, d_inode(old_dentry)); - p9_client_clunk(fid); + p9_fid_put(fid); } ihold(d_inode(old_dentry)); d_instantiate(dentry, d_inode(old_dentry)); @@ -866,7 +848,6 @@ v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir, if (IS_ERR(dfid)) { err = PTR_ERR(dfid); p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err); - dfid = NULL; goto error; } @@ -891,7 +872,6 @@ v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir, err = PTR_ERR(fid); p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); - fid = NULL; goto error; } @@ -905,9 +885,8 @@ v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir, goto error; } v9fs_set_create_acl(inode, fid, dacl, pacl); - v9fs_fid_add(dentry, fid); + v9fs_fid_add(dentry, &fid); d_instantiate(dentry, inode); - fid = NULL; err = 0; } else { /* @@ -923,10 +902,9 @@ v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir, d_instantiate(dentry, inode); } error: - if (fid) - p9_client_clunk(fid); + p9_fid_put(fid); v9fs_put_acl(dacl, pacl); - p9_client_clunk(dfid); + p9_fid_put(dfid); return err; } @@ -956,7 +934,7 @@ v9fs_vfs_get_link_dotl(struct dentry *dentry, if (IS_ERR(fid)) return ERR_CAST(fid); retval = p9_client_readlink(fid, &target); - p9_client_clunk(fid); + p9_fid_put(fid); if (retval) return ERR_PTR(retval); set_delayed_call(done, kfree_link, target); diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 97e23b4e6982..2d9ee073d12c 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -184,13 +184,13 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, retval = v9fs_get_acl(inode, fid); if (retval) goto release_sb; - v9fs_fid_add(root, fid); + v9fs_fid_add(root, &fid); p9_debug(P9_DEBUG_VFS, " simple set mount, return 0\n"); return dget(sb->s_root); clunk_fid: - p9_client_clunk(fid); + p9_fid_put(fid); v9fs_session_close(v9ses); free_session: kfree(v9ses); @@ -203,7 +203,7 @@ release_sb: * attached the fid to dentry so it won't get clunked * automatically. */ - p9_client_clunk(fid); + p9_fid_put(fid); deactivate_locked_super(sb); return ERR_PTR(retval); } @@ -270,7 +270,7 @@ static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf) } res = simple_statfs(dentry, buf); done: - p9_client_clunk(fid); + p9_fid_put(fid); return res; } diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index a824441b95a2..1f9298a4bd42 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -44,7 +44,7 @@ ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, if (err) retval = err; } - p9_client_clunk(attr_fid); + p9_fid_put(attr_fid); return retval; } @@ -71,7 +71,7 @@ ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name, if (IS_ERR(fid)) return PTR_ERR(fid); ret = v9fs_fid_xattr_get(fid, name, buffer, buffer_size); - p9_client_clunk(fid); + p9_fid_put(fid); return ret; } @@ -98,7 +98,7 @@ int v9fs_xattr_set(struct dentry *dentry, const char *name, if (IS_ERR(fid)) return PTR_ERR(fid); ret = v9fs_fid_xattr_set(fid, name, value, value_len, flags); - p9_client_clunk(fid); + p9_fid_put(fid); return ret; } @@ -128,7 +128,7 @@ int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name, retval); else p9_client_write(fid, 0, &from, &retval); - err = p9_client_clunk(fid); + err = p9_fid_put(fid); if (!retval && err) retval = err; return retval; diff --git a/fs/Kconfig b/fs/Kconfig index 5976eb33535f..a547307c1ae8 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -247,8 +247,7 @@ config HUGETLB_PAGE # # Select this config option from the architecture Kconfig, if it is preferred -# to enable the feature of minimizing overhead of struct page associated with -# each HugeTLB page. +# to enable the feature of HugeTLB Vmemmap Optimization (HVO). # config ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP bool @@ -259,14 +258,13 @@ config HUGETLB_PAGE_OPTIMIZE_VMEMMAP depends on SPARSEMEM_VMEMMAP config HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON - bool "Default optimizing vmemmap pages of HugeTLB to on" + bool "HugeTLB Vmemmap Optimization (HVO) defaults to on" default n depends on HUGETLB_PAGE_OPTIMIZE_VMEMMAP help - When using HUGETLB_PAGE_OPTIMIZE_VMEMMAP, the optimizing unused vmemmap - pages associated with each HugeTLB page is default off. Say Y here - to enable optimizing vmemmap pages of HugeTLB by default. It can then - be disabled on the command line via hugetlb_free_vmemmap=off. + The HugeTLB VmemmapvOptimization (HVO) defaults to off. Say Y here to + enable HVO by default. It can be disabled via hugetlb_free_vmemmap=off + (boot command line) or hugetlb_optimize_vmemmap (sysctl). config MEMFD_CREATE def_bool TMPFS || HUGETLBFS diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 07ad744eef77..988c2ac7cece 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -158,7 +158,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, cell->name[i] = tolower(name[i]); cell->name[i] = 0; - atomic_set(&cell->ref, 1); + refcount_set(&cell->ref, 1); atomic_set(&cell->active, 0); INIT_WORK(&cell->manager, afs_manage_cell_work); cell->volumes = RB_ROOT; @@ -287,7 +287,7 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, cell = candidate; candidate = NULL; atomic_set(&cell->active, 2); - trace_afs_cell(cell->debug_id, atomic_read(&cell->ref), 2, afs_cell_trace_insert); + trace_afs_cell(cell->debug_id, refcount_read(&cell->ref), 2, afs_cell_trace_insert); rb_link_node_rcu(&cell->net_node, parent, pp); rb_insert_color(&cell->net_node, &net->cells); up_write(&net->cells_lock); @@ -295,7 +295,7 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, afs_queue_cell(cell, afs_cell_trace_get_queue_new); wait_for_cell: - trace_afs_cell(cell->debug_id, atomic_read(&cell->ref), atomic_read(&cell->active), + trace_afs_cell(cell->debug_id, refcount_read(&cell->ref), atomic_read(&cell->active), afs_cell_trace_wait); _debug("wait_for_cell"); wait_var_event(&cell->state, @@ -490,13 +490,13 @@ static void afs_cell_destroy(struct rcu_head *rcu) { struct afs_cell *cell = container_of(rcu, struct afs_cell, rcu); struct afs_net *net = cell->net; - int u; + int r; _enter("%p{%s}", cell, cell->name); - u = atomic_read(&cell->ref); - ASSERTCMP(u, ==, 0); - trace_afs_cell(cell->debug_id, u, atomic_read(&cell->active), afs_cell_trace_free); + r = refcount_read(&cell->ref); + ASSERTCMP(r, ==, 0); + trace_afs_cell(cell->debug_id, r, atomic_read(&cell->active), afs_cell_trace_free); afs_put_vlserverlist(net, rcu_access_pointer(cell->vl_servers)); afs_unuse_cell(net, cell->alias_of, afs_cell_trace_unuse_alias); @@ -539,13 +539,10 @@ void afs_cells_timer(struct timer_list *timer) */ struct afs_cell *afs_get_cell(struct afs_cell *cell, enum afs_cell_trace reason) { - int u; + int r; - if (atomic_read(&cell->ref) <= 0) - BUG(); - - u = atomic_inc_return(&cell->ref); - trace_afs_cell(cell->debug_id, u, atomic_read(&cell->active), reason); + __refcount_inc(&cell->ref, &r); + trace_afs_cell(cell->debug_id, r + 1, atomic_read(&cell->active), reason); return cell; } @@ -556,12 +553,14 @@ void afs_put_cell(struct afs_cell *cell, enum afs_cell_trace reason) { if (cell) { unsigned int debug_id = cell->debug_id; - unsigned int u, a; + unsigned int a; + bool zero; + int r; a = atomic_read(&cell->active); - u = atomic_dec_return(&cell->ref); - trace_afs_cell(debug_id, u, a, reason); - if (u == 0) { + zero = __refcount_dec_and_test(&cell->ref, &r); + trace_afs_cell(debug_id, r - 1, a, reason); + if (zero) { a = atomic_read(&cell->active); WARN(a != 0, "Cell active count %u > 0\n", a); call_rcu(&cell->rcu, afs_cell_destroy); @@ -574,14 +573,12 @@ void afs_put_cell(struct afs_cell *cell, enum afs_cell_trace reason) */ struct afs_cell *afs_use_cell(struct afs_cell *cell, enum afs_cell_trace reason) { - int u, a; - - if (atomic_read(&cell->ref) <= 0) - BUG(); + int r, a; - u = atomic_read(&cell->ref); + r = refcount_read(&cell->ref); + WARN_ON(r == 0); a = atomic_inc_return(&cell->active); - trace_afs_cell(cell->debug_id, u, a, reason); + trace_afs_cell(cell->debug_id, r, a, reason); return cell; } @@ -593,7 +590,7 @@ void afs_unuse_cell(struct afs_net *net, struct afs_cell *cell, enum afs_cell_tr { unsigned int debug_id; time64_t now, expire_delay; - int u, a; + int r, a; if (!cell) return; @@ -607,9 +604,9 @@ void afs_unuse_cell(struct afs_net *net, struct afs_cell *cell, enum afs_cell_tr expire_delay = afs_cell_gc_delay; debug_id = cell->debug_id; - u = atomic_read(&cell->ref); + r = refcount_read(&cell->ref); a = atomic_dec_return(&cell->active); - trace_afs_cell(debug_id, u, a, reason); + trace_afs_cell(debug_id, r, a, reason); WARN_ON(a == 0); if (a == 1) /* 'cell' may now be garbage collected. */ @@ -621,11 +618,11 @@ void afs_unuse_cell(struct afs_net *net, struct afs_cell *cell, enum afs_cell_tr */ void afs_see_cell(struct afs_cell *cell, enum afs_cell_trace reason) { - int u, a; + int r, a; - u = atomic_read(&cell->ref); + r = refcount_read(&cell->ref); a = atomic_read(&cell->active); - trace_afs_cell(cell->debug_id, u, a, reason); + trace_afs_cell(cell->debug_id, r, a, reason); } /* @@ -739,7 +736,7 @@ again: active = 1; if (atomic_try_cmpxchg_relaxed(&cell->active, &active, 0)) { rb_erase(&cell->net_node, &net->cells); - trace_afs_cell(cell->debug_id, atomic_read(&cell->ref), 0, + trace_afs_cell(cell->debug_id, refcount_read(&cell->ref), 0, afs_cell_trace_unuse_delete); smp_store_release(&cell->state, AFS_CELL_REMOVED); } @@ -866,7 +863,7 @@ void afs_manage_cells(struct work_struct *work) bool sched_cell = false; active = atomic_read(&cell->active); - trace_afs_cell(cell->debug_id, atomic_read(&cell->ref), + trace_afs_cell(cell->debug_id, refcount_read(&cell->ref), active, afs_cell_trace_manage); ASSERTCMP(active, >=, 1); @@ -874,7 +871,7 @@ void afs_manage_cells(struct work_struct *work) if (purging) { if (test_and_clear_bit(AFS_CELL_FL_NO_GC, &cell->flags)) { active = atomic_dec_return(&cell->active); - trace_afs_cell(cell->debug_id, atomic_read(&cell->ref), + trace_afs_cell(cell->debug_id, refcount_read(&cell->ref), active, afs_cell_trace_unuse_pin); } } diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index a3f5de28be79..0a090d614e76 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -212,8 +212,8 @@ static void SRXAFSCB_CallBack(struct work_struct *work) * to maintain cache coherency. */ if (call->server) { - trace_afs_server(call->server, - atomic_read(&call->server->ref), + trace_afs_server(call->server->debug_id, + refcount_read(&call->server->ref), atomic_read(&call->server->active), afs_server_trace_callback); afs_break_callbacks(call->server, call->count, call->request); diff --git a/fs/afs/flock.c b/fs/afs/flock.c index c4210a3964d8..bbcc5afd1576 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -76,7 +76,7 @@ void afs_lock_op_done(struct afs_call *call) if (call->error == 0) { spin_lock(&vnode->lock); trace_afs_flock_ev(vnode, NULL, afs_flock_timestamp, 0); - vnode->locked_at = call->reply_time; + vnode->locked_at = call->issue_time; afs_schedule_lock_extension(vnode); spin_unlock(&vnode->lock); } diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 4943413d9c5f..7d37f63ef0f0 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -131,7 +131,7 @@ bad: static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry) { - return ktime_divns(call->reply_time, NSEC_PER_SEC) + expiry; + return ktime_divns(call->issue_time, NSEC_PER_SEC) + expiry; } static void xdr_decode_AFSCallBack(const __be32 **_bp, diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 64dab70d4a4f..6d3a3dbe4928 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -104,12 +104,14 @@ static int afs_inode_init_from_status(struct afs_operation *op, inode->i_op = &afs_file_inode_operations; inode->i_fop = &afs_file_operations; inode->i_mapping->a_ops = &afs_file_aops; + mapping_set_large_folios(inode->i_mapping); break; case AFS_FTYPE_DIR: inode->i_mode = S_IFDIR | (status->mode & S_IALLUGO); inode->i_op = &afs_dir_inode_operations; inode->i_fop = &afs_dir_file_operations; inode->i_mapping->a_ops = &afs_dir_aops; + mapping_set_large_folios(inode->i_mapping); break; case AFS_FTYPE_SYMLINK: /* Symlinks with a mode of 0644 are actually mountpoints. */ diff --git a/fs/afs/internal.h b/fs/afs/internal.h index a6f25d9e75b5..723d162078a3 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -122,7 +122,7 @@ struct afs_call { }; struct afs_operation *op; unsigned int server_index; - atomic_t usage; + refcount_t ref; enum afs_call_state state; spinlock_t state_lock; int error; /* error code */ @@ -137,7 +137,6 @@ struct afs_call { bool need_attention; /* T if RxRPC poked us */ bool async; /* T if asynchronous */ bool upgrade; /* T to request service upgrade */ - bool have_reply_time; /* T if have got reply_time */ bool intr; /* T if interruptible */ bool unmarshalling_error; /* T if an unmarshalling error occurred */ u16 service_id; /* Actual service ID (after upgrade) */ @@ -151,7 +150,7 @@ struct afs_call { } __attribute__((packed)); __be64 tmp64; }; - ktime_t reply_time; /* Time of first reply packet */ + ktime_t issue_time; /* Time of issue of operation */ }; struct afs_call_type { @@ -365,7 +364,7 @@ struct afs_cell { struct hlist_node proc_link; /* /proc cell list link */ time64_t dns_expiry; /* Time AFSDB/SRV record expires */ time64_t last_inactive; /* Time of last drop of usage count */ - atomic_t ref; /* Struct refcount */ + refcount_t ref; /* Struct refcount */ atomic_t active; /* Active usage counter */ unsigned long flags; #define AFS_CELL_FL_NO_GC 0 /* The cell was added manually, don't auto-gc */ @@ -410,7 +409,7 @@ struct afs_vlserver { #define AFS_VLSERVER_FL_IS_YFS 2 /* Server is YFS not AFS */ #define AFS_VLSERVER_FL_RESPONDING 3 /* VL server is responding */ rwlock_t lock; /* Lock on addresses */ - atomic_t usage; + refcount_t ref; unsigned int rtt; /* Server's current RTT in uS */ /* Probe state */ @@ -446,7 +445,7 @@ struct afs_vlserver_entry { struct afs_vlserver_list { struct rcu_head rcu; - atomic_t usage; + refcount_t ref; u8 nr_servers; u8 index; /* Server currently in use */ u8 preferred; /* Preferred server */ @@ -517,7 +516,7 @@ struct afs_server { #define AFS_SERVER_FL_NO_IBULK 17 /* Fileserver doesn't support FS.InlineBulkStatus */ #define AFS_SERVER_FL_NO_RM2 18 /* Fileserver doesn't support YFS.RemoveFile2 */ #define AFS_SERVER_FL_HAS_FS64 19 /* Fileserver supports FS.{Fetch,Store}Data64 */ - atomic_t ref; /* Object refcount */ + refcount_t ref; /* Object refcount */ atomic_t active; /* Active user count */ u32 addr_version; /* Address list version */ unsigned int rtt; /* Server's current RTT in uS */ @@ -571,7 +570,7 @@ struct afs_volume { struct rcu_head rcu; afs_volid_t vid; /* volume ID */ }; - atomic_t usage; + refcount_t ref; time64_t update_at; /* Time at which to next update */ struct afs_cell *cell; /* Cell to which belongs (pins ref) */ struct rb_node cell_node; /* Link in cell->volumes */ @@ -1493,14 +1492,14 @@ extern int afs_end_vlserver_operation(struct afs_vl_cursor *); */ static inline struct afs_vlserver *afs_get_vlserver(struct afs_vlserver *vlserver) { - atomic_inc(&vlserver->usage); + refcount_inc(&vlserver->ref); return vlserver; } static inline struct afs_vlserver_list *afs_get_vlserverlist(struct afs_vlserver_list *vllist) { if (vllist) - atomic_inc(&vllist->usage); + refcount_inc(&vllist->ref); return vllist; } diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 933e67fcdab1..805328ca5428 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -69,6 +69,7 @@ int afs_abort_to_error(u32 abort_code) /* Unified AFS error table */ case UAEPERM: return -EPERM; case UAENOENT: return -ENOENT; + case UAEAGAIN: return -EAGAIN; case UAEACCES: return -EACCES; case UAEBUSY: return -EBUSY; case UAEEXIST: return -EEXIST; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index e1b863449296..2a0c83d71565 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -47,7 +47,7 @@ static int afs_proc_cells_show(struct seq_file *m, void *v) /* display one cell per line on subsequent lines */ seq_printf(m, "%3u %3u %6lld %2u %2u %s\n", - atomic_read(&cell->ref), + refcount_read(&cell->ref), atomic_read(&cell->active), cell->dns_expiry - ktime_get_real_seconds(), vllist ? vllist->nr_servers : 0, @@ -217,7 +217,7 @@ static int afs_proc_cell_volumes_show(struct seq_file *m, void *v) } seq_printf(m, "%3d %08llx %s %s\n", - atomic_read(&vol->usage), vol->vid, + refcount_read(&vol->ref), vol->vid, afs_vol_types[vol->type], vol->name); @@ -388,7 +388,7 @@ static int afs_proc_servers_show(struct seq_file *m, void *v) alist = rcu_dereference(server->addresses); seq_printf(m, "%pU %3d %3d\n", &server->uuid, - atomic_read(&server->ref), + refcount_read(&server->ref), atomic_read(&server->active)); seq_printf(m, " - info: fl=%lx rtt=%u brk=%x\n", server->flags, server->rtt, server->cb_s_break); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index a5434f3e57c6..eccc3cd0cb70 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -145,14 +145,14 @@ static struct afs_call *afs_alloc_call(struct afs_net *net, call->type = type; call->net = net; call->debug_id = atomic_inc_return(&rxrpc_debug_id); - atomic_set(&call->usage, 1); + refcount_set(&call->ref, 1); INIT_WORK(&call->async_work, afs_process_async_call); init_waitqueue_head(&call->waitq); spin_lock_init(&call->state_lock); call->iter = &call->def_iter; o = atomic_inc_return(&net->nr_outstanding_calls); - trace_afs_call(call, afs_call_trace_alloc, 1, o, + trace_afs_call(call->debug_id, afs_call_trace_alloc, 1, o, __builtin_return_address(0)); return call; } @@ -163,14 +163,16 @@ static struct afs_call *afs_alloc_call(struct afs_net *net, void afs_put_call(struct afs_call *call) { struct afs_net *net = call->net; - int n = atomic_dec_return(&call->usage); - int o = atomic_read(&net->nr_outstanding_calls); + unsigned int debug_id = call->debug_id; + bool zero; + int r, o; - trace_afs_call(call, afs_call_trace_put, n, o, + zero = __refcount_dec_and_test(&call->ref, &r); + o = atomic_read(&net->nr_outstanding_calls); + trace_afs_call(debug_id, afs_call_trace_put, r - 1, o, __builtin_return_address(0)); - ASSERTCMP(n, >=, 0); - if (n == 0) { + if (zero) { ASSERT(!work_pending(&call->async_work)); ASSERT(call->type->name != NULL); @@ -185,7 +187,7 @@ void afs_put_call(struct afs_call *call) afs_put_addrlist(call->alist); kfree(call->request); - trace_afs_call(call, afs_call_trace_free, 0, o, + trace_afs_call(call->debug_id, afs_call_trace_free, 0, o, __builtin_return_address(0)); kfree(call); @@ -198,9 +200,11 @@ void afs_put_call(struct afs_call *call) static struct afs_call *afs_get_call(struct afs_call *call, enum afs_call_trace why) { - int u = atomic_inc_return(&call->usage); + int r; - trace_afs_call(call, why, u, + __refcount_inc(&call->ref, &r); + + trace_afs_call(call->debug_id, why, r + 1, atomic_read(&call->net->nr_outstanding_calls), __builtin_return_address(0)); return call; @@ -347,6 +351,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) if (call->max_lifespan) rxrpc_kernel_set_max_life(call->net->socket, rxcall, call->max_lifespan); + call->issue_time = ktime_get_real(); /* send the request */ iov[0].iov_base = call->request; @@ -497,12 +502,6 @@ static void afs_deliver_to_call(struct afs_call *call) return; } - if (!call->have_reply_time && - rxrpc_kernel_get_reply_time(call->net->socket, - call->rxcall, - &call->reply_time)) - call->have_reply_time = true; - ret = call->type->deliver(call); state = READ_ONCE(call->state); if (ret == 0 && call->unmarshalling_error) @@ -668,14 +667,13 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall, unsigned long call_user_ID) { struct afs_call *call = (struct afs_call *)call_user_ID; - int u; + int r; trace_afs_notify_call(rxcall, call); call->need_attention = true; - u = atomic_fetch_add_unless(&call->usage, 1, 0); - if (u != 0) { - trace_afs_call(call, afs_call_trace_wake, u + 1, + if (__refcount_inc_not_zero(&call->ref, &r)) { + trace_afs_call(call->debug_id, afs_call_trace_wake, r + 1, atomic_read(&call->net->nr_outstanding_calls), __builtin_return_address(0)); diff --git a/fs/afs/server.c b/fs/afs/server.c index 6e5b9a19b234..4981baf97835 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -228,7 +228,7 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell, if (!server) goto enomem; - atomic_set(&server->ref, 1); + refcount_set(&server->ref, 1); atomic_set(&server->active, 1); server->debug_id = atomic_inc_return(&afs_server_debug_id); RCU_INIT_POINTER(server->addresses, alist); @@ -243,7 +243,7 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell, server->rtt = UINT_MAX; afs_inc_servers_outstanding(net); - trace_afs_server(server, 1, 1, afs_server_trace_alloc); + trace_afs_server(server->debug_id, 1, 1, afs_server_trace_alloc); _leave(" = %p", server); return server; @@ -352,9 +352,12 @@ void afs_servers_timer(struct timer_list *timer) struct afs_server *afs_get_server(struct afs_server *server, enum afs_server_trace reason) { - unsigned int u = atomic_inc_return(&server->ref); + unsigned int a; + int r; - trace_afs_server(server, u, atomic_read(&server->active), reason); + __refcount_inc(&server->ref, &r); + a = atomic_read(&server->active); + trace_afs_server(server->debug_id, r + 1, a, reason); return server; } @@ -364,14 +367,14 @@ struct afs_server *afs_get_server(struct afs_server *server, static struct afs_server *afs_maybe_use_server(struct afs_server *server, enum afs_server_trace reason) { - unsigned int r = atomic_fetch_add_unless(&server->ref, 1, 0); unsigned int a; + int r; - if (r == 0) + if (!__refcount_inc_not_zero(&server->ref, &r)) return NULL; a = atomic_inc_return(&server->active); - trace_afs_server(server, r, a, reason); + trace_afs_server(server->debug_id, r + 1, a, reason); return server; } @@ -380,10 +383,13 @@ static struct afs_server *afs_maybe_use_server(struct afs_server *server, */ struct afs_server *afs_use_server(struct afs_server *server, enum afs_server_trace reason) { - unsigned int r = atomic_inc_return(&server->ref); - unsigned int a = atomic_inc_return(&server->active); + unsigned int a; + int r; - trace_afs_server(server, r, a, reason); + __refcount_inc(&server->ref, &r); + a = atomic_inc_return(&server->active); + + trace_afs_server(server->debug_id, r + 1, a, reason); return server; } @@ -393,14 +399,17 @@ struct afs_server *afs_use_server(struct afs_server *server, enum afs_server_tra void afs_put_server(struct afs_net *net, struct afs_server *server, enum afs_server_trace reason) { - unsigned int usage; + unsigned int a, debug_id = server->debug_id; + bool zero; + int r; if (!server) return; - usage = atomic_dec_return(&server->ref); - trace_afs_server(server, usage, atomic_read(&server->active), reason); - if (unlikely(usage == 0)) + a = atomic_inc_return(&server->active); + zero = __refcount_dec_and_test(&server->ref, &r); + trace_afs_server(debug_id, r - 1, a, reason); + if (unlikely(zero)) __afs_put_server(net, server); } @@ -436,7 +445,7 @@ static void afs_server_rcu(struct rcu_head *rcu) { struct afs_server *server = container_of(rcu, struct afs_server, rcu); - trace_afs_server(server, atomic_read(&server->ref), + trace_afs_server(server->debug_id, refcount_read(&server->ref), atomic_read(&server->active), afs_server_trace_free); afs_put_addrlist(rcu_access_pointer(server->addresses)); kfree(server); @@ -487,7 +496,7 @@ static void afs_gc_servers(struct afs_net *net, struct afs_server *gc_list) active = atomic_read(&server->active); if (active == 0) { - trace_afs_server(server, atomic_read(&server->ref), + trace_afs_server(server->debug_id, refcount_read(&server->ref), active, afs_server_trace_gc); next = rcu_dereference_protected( server->uuid_next, lockdep_is_held(&net->fs_lock.lock)); @@ -553,7 +562,7 @@ void afs_manage_servers(struct work_struct *work) _debug("manage %pU %u", &server->uuid, active); if (purging) { - trace_afs_server(server, atomic_read(&server->ref), + trace_afs_server(server->debug_id, refcount_read(&server->ref), active, afs_server_trace_purging); if (active != 0) pr_notice("Can't purge s=%08x\n", server->debug_id); @@ -633,7 +642,8 @@ static noinline bool afs_update_server_record(struct afs_operation *op, _enter(""); - trace_afs_server(server, atomic_read(&server->ref), atomic_read(&server->active), + trace_afs_server(server->debug_id, refcount_read(&server->ref), + atomic_read(&server->active), afs_server_trace_update); alist = afs_vl_lookup_addrs(op->volume->cell, op->key, &server->uuid); diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c index 38b2ba1d9ec0..acc48216136a 100644 --- a/fs/afs/vl_list.c +++ b/fs/afs/vl_list.c @@ -17,7 +17,7 @@ struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len, vlserver = kzalloc(struct_size(vlserver, name, name_len + 1), GFP_KERNEL); if (vlserver) { - atomic_set(&vlserver->usage, 1); + refcount_set(&vlserver->ref, 1); rwlock_init(&vlserver->lock); init_waitqueue_head(&vlserver->probe_wq); spin_lock_init(&vlserver->probe_lock); @@ -39,13 +39,9 @@ static void afs_vlserver_rcu(struct rcu_head *rcu) void afs_put_vlserver(struct afs_net *net, struct afs_vlserver *vlserver) { - if (vlserver) { - unsigned int u = atomic_dec_return(&vlserver->usage); - //_debug("VL PUT %p{%u}", vlserver, u); - - if (u == 0) - call_rcu(&vlserver->rcu, afs_vlserver_rcu); - } + if (vlserver && + refcount_dec_and_test(&vlserver->ref)) + call_rcu(&vlserver->rcu, afs_vlserver_rcu); } struct afs_vlserver_list *afs_alloc_vlserver_list(unsigned int nr_servers) @@ -54,7 +50,7 @@ struct afs_vlserver_list *afs_alloc_vlserver_list(unsigned int nr_servers) vllist = kzalloc(struct_size(vllist, servers, nr_servers), GFP_KERNEL); if (vllist) { - atomic_set(&vllist->usage, 1); + refcount_set(&vllist->ref, 1); rwlock_init(&vllist->lock); } @@ -64,10 +60,7 @@ struct afs_vlserver_list *afs_alloc_vlserver_list(unsigned int nr_servers) void afs_put_vlserverlist(struct afs_net *net, struct afs_vlserver_list *vllist) { if (vllist) { - unsigned int u = atomic_dec_return(&vllist->usage); - - //_debug("VLLS PUT %p{%u}", vllist, u); - if (u == 0) { + if (refcount_dec_and_test(&vllist->ref)) { int i; for (i = 0; i < vllist->nr_servers; i++) { diff --git a/fs/afs/volume.c b/fs/afs/volume.c index cc665cef0abe..f4937029dcd7 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -52,7 +52,7 @@ static void afs_remove_volume_from_cell(struct afs_volume *volume) struct afs_cell *cell = volume->cell; if (!hlist_unhashed(&volume->proc_link)) { - trace_afs_volume(volume->vid, atomic_read(&volume->usage), + trace_afs_volume(volume->vid, refcount_read(&cell->ref), afs_volume_trace_remove); write_seqlock(&cell->volume_lock); hlist_del_rcu(&volume->proc_link); @@ -87,7 +87,7 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, volume->type_force = params->force; volume->name_len = vldb->name_len; - atomic_set(&volume->usage, 1); + refcount_set(&volume->ref, 1); INIT_HLIST_NODE(&volume->proc_link); rwlock_init(&volume->servers_lock); rwlock_init(&volume->cb_v_break_lock); @@ -228,7 +228,7 @@ static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume) afs_remove_volume_from_cell(volume); afs_put_serverlist(net, rcu_access_pointer(volume->servers)); afs_put_cell(volume->cell, afs_cell_trace_put_vol); - trace_afs_volume(volume->vid, atomic_read(&volume->usage), + trace_afs_volume(volume->vid, refcount_read(&volume->ref), afs_volume_trace_free); kfree_rcu(volume, rcu); @@ -242,8 +242,10 @@ struct afs_volume *afs_get_volume(struct afs_volume *volume, enum afs_volume_trace reason) { if (volume) { - int u = atomic_inc_return(&volume->usage); - trace_afs_volume(volume->vid, u, reason); + int r; + + __refcount_inc(&volume->ref, &r); + trace_afs_volume(volume->vid, r + 1, reason); } return volume; } @@ -257,9 +259,12 @@ void afs_put_volume(struct afs_net *net, struct afs_volume *volume, { if (volume) { afs_volid_t vid = volume->vid; - int u = atomic_dec_return(&volume->usage); - trace_afs_volume(vid, u, reason); - if (u == 0) + bool zero; + int r; + + zero = __refcount_dec_and_test(&volume->ref, &r); + trace_afs_volume(vid, r - 1, reason); + if (zero) afs_destroy_volume(net, volume); } } diff --git a/fs/afs/write.c b/fs/afs/write.c index 2c885b22de34..9ebdd36eaf2f 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -91,7 +91,7 @@ try_again: goto flush_conflicting_write; } - *_page = &folio->page; + *_page = folio_file_page(folio, pos / PAGE_SIZE); _leave(" = 0"); return 0; diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index fdc7d675b4b0..11571cca86c1 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -232,8 +232,7 @@ static void xdr_decode_YFSCallBack(const __be32 **_bp, struct afs_callback *cb = &scb->callback; ktime_t cb_expiry; - cb_expiry = call->reply_time; - cb_expiry = ktime_add(cb_expiry, xdr_to_u64(x->expiration_time) * 100); + cb_expiry = ktime_add(call->issue_time, xdr_to_u64(x->expiration_time) * 100); cb->expires_at = ktime_divns(cb_expiry, NSEC_PER_SEC); scb->have_cb = true; *_bp += xdr_size(x); diff --git a/fs/attr.c b/fs/attr.c index b5b8835ddf15..1552a5f23d6b 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -183,6 +183,8 @@ EXPORT_SYMBOL(setattr_prepare); */ int inode_newsize_ok(const struct inode *inode, loff_t offset) { + if (offset < 0) + return -EINVAL; if (inode->i_size < offset) { unsigned long limit; diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h index 918826eaceea..d5a44fa88acf 100644 --- a/fs/autofs/autofs_i.h +++ b/fs/autofs/autofs_i.h @@ -51,8 +51,6 @@ extern struct file_system_type autofs_fs_type; */ struct autofs_info { struct dentry *dentry; - struct inode *inode; - int flags; struct completion expire_complete; @@ -148,6 +146,11 @@ static inline int autofs_oz_mode(struct autofs_sb_info *sbi) task_pgrp(current) == sbi->oz_pgrp); } +static inline bool autofs_empty(struct autofs_info *ino) +{ + return ino->count < 2; +} + struct inode *autofs_get_inode(struct super_block *, umode_t); void autofs_free_ino(struct autofs_info *); diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index b3fefd6237c3..038b3d2d9f57 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -371,7 +371,7 @@ static struct dentry *should_expire(struct dentry *dentry, return NULL; } - if (simple_empty(dentry)) + if (autofs_empty(ino)) return NULL; /* Case 2: tree mount, expire iff entire tree is not busy */ diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index 9edf243713eb..affa70360b1f 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -20,6 +20,7 @@ struct autofs_info *autofs_new_ino(struct autofs_sb_info *sbi) INIT_LIST_HEAD(&ino->expiring); ino->last_used = jiffies; ino->sbi = sbi; + ino->count = 1; } return ino; } diff --git a/fs/autofs/root.c b/fs/autofs/root.c index 91fe4548c256..ca03c1cae2be 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -10,6 +10,7 @@ #include "autofs_i.h" +static int autofs_dir_permission(struct user_namespace *, struct inode *, int); static int autofs_dir_symlink(struct user_namespace *, struct inode *, struct dentry *, const char *); static int autofs_dir_unlink(struct inode *, struct dentry *); @@ -50,6 +51,7 @@ const struct file_operations autofs_dir_operations = { const struct inode_operations autofs_dir_inode_operations = { .lookup = autofs_lookup, + .permission = autofs_dir_permission, .unlink = autofs_dir_unlink, .symlink = autofs_dir_symlink, .mkdir = autofs_dir_mkdir, @@ -77,6 +79,7 @@ static int autofs_dir_open(struct inode *inode, struct file *file) { struct dentry *dentry = file->f_path.dentry; struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); + struct autofs_info *ino = autofs_dentry_ino(dentry); pr_debug("file=%p dentry=%p %pd\n", file, dentry, dentry); @@ -93,7 +96,7 @@ static int autofs_dir_open(struct inode *inode, struct file *file) * it. */ spin_lock(&sbi->lookup_lock); - if (!path_is_mountpoint(&file->f_path) && simple_empty(dentry)) { + if (!path_is_mountpoint(&file->f_path) && autofs_empty(ino)) { spin_unlock(&sbi->lookup_lock); return -ENOENT; } @@ -288,9 +291,26 @@ static struct dentry *autofs_mountpoint_changed(struct path *path) struct dentry *dentry = path->dentry; struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); - /* - * If this is an indirect mount the dentry could have gone away - * as a result of an expire and a new one created. + /* If this is an indirect mount the dentry could have gone away + * and a new one created. + * + * This is unusual and I can't remember the case for which it + * was originally added now. But an example of how this can + * happen is an autofs indirect mount that has the "browse" + * option set and also has the "symlink" option in the autofs + * map entry. In this case the daemon will remove the browse + * directory and create a symlink as the mount leaving the + * struct path stale. + * + * Another not so obvious case is when a mount in an autofs + * indirect mount that uses the "nobrowse" option is being + * expired at the same time as a path walk. If the mount has + * been umounted but the mount point directory seen before + * becoming unhashed (during a lockless path walk) when a stat + * family system call is made the mount won't be re-mounted as + * it should. In this case the mount point that's been removed + * (by the daemon) will be stale and the a new mount point + * dentry created. */ if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) { struct dentry *parent = dentry->d_parent; @@ -362,7 +382,7 @@ static struct vfsmount *autofs_d_automount(struct path *path) * the mount never trigger mounts themselves (they have an * autofs trigger mount mounted on them). But v4 pseudo direct * mounts do need the leaves to trigger mounts. In this case - * we have no choice but to use the list_empty() check and + * we have no choice but to use the autofs_empty() check and * require user space behave. */ if (sbi->version > 4) { @@ -371,7 +391,7 @@ static struct vfsmount *autofs_d_automount(struct path *path) goto done; } } else { - if (!simple_empty(dentry)) { + if (!autofs_empty(ino)) { spin_unlock(&sbi->fs_lock); goto done; } @@ -426,9 +446,8 @@ static int autofs_d_manage(const struct path *path, bool rcu_walk) if (rcu_walk) { /* We don't need fs_lock in rcu_walk mode, - * just testing 'AUTOFS_INFO_NO_RCU' is enough. - * simple_empty() takes a spinlock, so leave it - * to last. + * just testing 'AUTOFS_INF_WANT_EXPIRE' is enough. + * * We only return -EISDIR when certain this isn't * a mount-trap. */ @@ -441,9 +460,7 @@ static int autofs_d_manage(const struct path *path, bool rcu_walk) inode = d_inode_rcu(dentry); if (inode && S_ISLNK(inode->i_mode)) return -EISDIR; - if (list_empty(&dentry->d_subdirs)) - return 0; - if (!simple_empty(dentry)) + if (!autofs_empty(ino)) return -EISDIR; return 0; } @@ -463,7 +480,7 @@ static int autofs_d_manage(const struct path *path, bool rcu_walk) * we can avoid needless calls ->d_automount() and avoid * an incorrect ELOOP error return. */ - if ((!path_is_mountpoint(path) && !simple_empty(dentry)) || + if ((!path_is_mountpoint(path) && !autofs_empty(ino)) || (d_really_is_positive(dentry) && d_is_symlink(dentry))) status = -EISDIR; } @@ -526,11 +543,30 @@ static struct dentry *autofs_lookup(struct inode *dir, return NULL; } +static int autofs_dir_permission(struct user_namespace *mnt_userns, + struct inode *inode, int mask) +{ + if (mask & MAY_WRITE) { + struct autofs_sb_info *sbi = autofs_sbi(inode->i_sb); + + if (!autofs_oz_mode(sbi)) + return -EACCES; + + /* autofs_oz_mode() needs to allow path walks when the + * autofs mount is catatonic but the state of an autofs + * file system needs to be preserved over restarts. + */ + if (sbi->flags & AUTOFS_SBI_CATATONIC) + return -EACCES; + } + + return generic_permission(mnt_userns, inode, mask); +} + static int autofs_dir_symlink(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, const char *symname) { - struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); struct autofs_info *p_ino; struct inode *inode; @@ -539,16 +575,6 @@ static int autofs_dir_symlink(struct user_namespace *mnt_userns, pr_debug("%s <- %pd\n", symname, dentry); - if (!autofs_oz_mode(sbi)) - return -EACCES; - - /* autofs_oz_mode() needs to allow path walks when the - * autofs mount is catatonic but the state of an autofs - * file system needs to be preserved over restarts. - */ - if (sbi->flags & AUTOFS_SBI_CATATONIC) - return -EACCES; - BUG_ON(!ino); autofs_clean_ino(ino); @@ -571,7 +597,6 @@ static int autofs_dir_symlink(struct user_namespace *mnt_userns, d_add(dentry, inode); dget(dentry); - ino->count++; p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count++; @@ -601,17 +626,6 @@ static int autofs_dir_unlink(struct inode *dir, struct dentry *dentry) struct autofs_info *ino = autofs_dentry_ino(dentry); struct autofs_info *p_ino; - if (!autofs_oz_mode(sbi)) - return -EACCES; - - /* autofs_oz_mode() needs to allow path walks when the - * autofs mount is catatonic but the state of an autofs - * file system needs to be preserved over restarts. - */ - if (sbi->flags & AUTOFS_SBI_CATATONIC) - return -EACCES; - - ino->count--; p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count--; dput(ino->dentry); @@ -683,16 +697,6 @@ static int autofs_dir_rmdir(struct inode *dir, struct dentry *dentry) pr_debug("dentry %p, removing %pd\n", dentry, dentry); - if (!autofs_oz_mode(sbi)) - return -EACCES; - - /* autofs_oz_mode() needs to allow path walks when the - * autofs mount is catatonic but the state of an autofs - * file system needs to be preserved over restarts. - */ - if (sbi->flags & AUTOFS_SBI_CATATONIC) - return -EACCES; - if (ino->count != 1) return -ENOTEMPTY; @@ -704,7 +708,6 @@ static int autofs_dir_rmdir(struct inode *dir, struct dentry *dentry) if (sbi->version < 5) autofs_clear_leaf_automount_flags(dentry); - ino->count--; p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count--; dput(ino->dentry); @@ -726,16 +729,6 @@ static int autofs_dir_mkdir(struct user_namespace *mnt_userns, struct autofs_info *p_ino; struct inode *inode; - if (!autofs_oz_mode(sbi)) - return -EACCES; - - /* autofs_oz_mode() needs to allow path walks when the - * autofs mount is catatonic but the state of an autofs - * file system needs to be preserved over restarts. - */ - if (sbi->flags & AUTOFS_SBI_CATATONIC) - return -EACCES; - pr_debug("dentry %p, creating %pd\n", dentry, dentry); BUG_ON(!ino); @@ -753,7 +746,6 @@ static int autofs_dir_mkdir(struct user_namespace *mnt_userns, autofs_set_leaf_automount_flags(dentry); dget(dentry); - ino->count++; p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count++; inc_nlink(dir); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c3aecfb0a71d..e0375ba9d0fe 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -440,39 +440,26 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, btrfs_put_caching_control(caching_ctl); } -int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache) +static int btrfs_caching_ctl_wait_done(struct btrfs_block_group *cache, + struct btrfs_caching_control *caching_ctl) +{ + wait_event(caching_ctl->wait, btrfs_block_group_done(cache)); + return cache->cached == BTRFS_CACHE_ERROR ? -EIO : 0; +} + +static int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache) { struct btrfs_caching_control *caching_ctl; - int ret = 0; + int ret; caching_ctl = btrfs_get_caching_control(cache); if (!caching_ctl) return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0; - - wait_event(caching_ctl->wait, btrfs_block_group_done(cache)); - if (cache->cached == BTRFS_CACHE_ERROR) - ret = -EIO; + ret = btrfs_caching_ctl_wait_done(cache, caching_ctl); btrfs_put_caching_control(caching_ctl); return ret; } -static bool space_cache_v1_done(struct btrfs_block_group *cache) -{ - bool ret; - - spin_lock(&cache->lock); - ret = cache->cached != BTRFS_CACHE_FAST; - spin_unlock(&cache->lock); - - return ret; -} - -void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache, - struct btrfs_caching_control *caching_ctl) -{ - wait_event(caching_ctl->wait, space_cache_v1_done(cache)); -} - #ifdef CONFIG_BTRFS_DEBUG static void fragment_free_space(struct btrfs_block_group *block_group) { @@ -750,9 +737,8 @@ done: btrfs_put_block_group(block_group); } -int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only) +int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait) { - DEFINE_WAIT(wait); struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_caching_control *caching_ctl = NULL; int ret = 0; @@ -785,10 +771,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only } WARN_ON(cache->caching_ctl); cache->caching_ctl = caching_ctl; - if (btrfs_test_opt(fs_info, SPACE_CACHE)) - cache->cached = BTRFS_CACHE_FAST; - else - cache->cached = BTRFS_CACHE_STARTED; + cache->cached = BTRFS_CACHE_STARTED; cache->has_caching_ctl = 1; spin_unlock(&cache->lock); @@ -801,8 +784,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work); out: - if (load_cache_only && caching_ctl) - btrfs_wait_space_cache_v1_finished(cache, caching_ctl); + if (wait && caching_ctl) + ret = btrfs_caching_ctl_wait_done(cache, caching_ctl); if (caching_ctl) btrfs_put_caching_control(caching_ctl); @@ -1640,9 +1623,11 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) div64_u64(zone_unusable * 100, bg->length)); trace_btrfs_reclaim_block_group(bg); ret = btrfs_relocate_chunk(fs_info, bg->start); - if (ret) + if (ret) { + btrfs_dec_block_group_ro(bg); btrfs_err(fs_info, "error relocating chunk %llu", bg->start); + } next: btrfs_put_block_group(bg); @@ -3310,7 +3295,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, * space back to the block group, otherwise we will leak space. */ if (!alloc && !btrfs_block_group_done(cache)) - btrfs_cache_block_group(cache, 1); + btrfs_cache_block_group(cache, true); byte_in_group = bytenr - cache->start; WARN_ON(byte_in_group > cache->length); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 35e0e860cc0b..6b3cdc4cbc41 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -263,9 +263,7 @@ void btrfs_dec_nocow_writers(struct btrfs_block_group *bg); void btrfs_wait_nocow_writers(struct btrfs_block_group *bg); void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, u64 num_bytes); -int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache); -int btrfs_cache_block_group(struct btrfs_block_group *cache, - int load_cache_only); +int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait); void btrfs_put_caching_control(struct btrfs_caching_control *ctl); struct btrfs_caching_control *btrfs_get_caching_control( struct btrfs_block_group *cache); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 6e556031a8f3..ebfa35fe1c38 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2075,6 +2075,9 @@ cow_done: if (!p->skip_locking) { level = btrfs_header_level(b); + + btrfs_maybe_reset_lockdep_class(root, b); + if (level <= write_lock_level) { btrfs_tree_lock(b); p->locks[level] = BTRFS_WRITE_LOCK; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4db85b9dc7ed..df8c99c99df9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -505,7 +505,6 @@ struct btrfs_free_cluster { enum btrfs_caching_type { BTRFS_CACHE_NO, BTRFS_CACHE_STARTED, - BTRFS_CACHE_FAST, BTRFS_CACHE_FINISHED, BTRFS_CACHE_ERROR, }; @@ -1089,8 +1088,6 @@ struct btrfs_fs_info { spinlock_t zone_active_bgs_lock; struct list_head zone_active_bgs; - /* Waiters when BTRFS_FS_NEED_ZONE_FINISH is set */ - wait_queue_head_t zone_finish_wait; /* Updates are not protected by any lock */ struct btrfs_commit_stats commit_stats; @@ -1173,6 +1170,8 @@ enum { BTRFS_ROOT_ORPHAN_CLEANUP, /* This root has a drop operation that was started previously. */ BTRFS_ROOT_UNFINISHED_DROP, + /* This reloc root needs to have its buffers lockdep class reset. */ + BTRFS_ROOT_RESET_LOCKDEP_CLASS, }; static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index f43196a893ca..41cddd3ff059 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -165,7 +165,7 @@ no_valid_dev_replace_entry_found: */ if (btrfs_find_device(fs_info->fs_devices, &args)) { btrfs_err(fs_info, - "replace devid present without an active replace item"); +"replace without active item, run 'device scan --forget' on the target device"); ret = -EUCLEAN; } else { dev_replace->srcdev = NULL; @@ -1129,8 +1129,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info) up_write(&dev_replace->rwsem); /* Scrub for replace must not be running in suspended state */ - ret = btrfs_scrub_cancel(fs_info); - ASSERT(ret != -ENOTCONN); + btrfs_scrub_cancel(fs_info); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4c3166f3c725..1af28b066b42 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -87,88 +87,6 @@ struct async_submit_bio { }; /* - * Lockdep class keys for extent_buffer->lock's in this root. For a given - * eb, the lockdep key is determined by the btrfs_root it belongs to and - * the level the eb occupies in the tree. - * - * Different roots are used for different purposes and may nest inside each - * other and they require separate keysets. As lockdep keys should be - * static, assign keysets according to the purpose of the root as indicated - * by btrfs_root->root_key.objectid. This ensures that all special purpose - * roots have separate keysets. - * - * Lock-nesting across peer nodes is always done with the immediate parent - * node locked thus preventing deadlock. As lockdep doesn't know this, use - * subclass to avoid triggering lockdep warning in such cases. - * - * The key is set by the readpage_end_io_hook after the buffer has passed - * csum validation but before the pages are unlocked. It is also set by - * btrfs_init_new_buffer on freshly allocated blocks. - * - * We also add a check to make sure the highest level of the tree is the - * same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this code - * needs update as well. - */ -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# if BTRFS_MAX_LEVEL != 8 -# error -# endif - -#define DEFINE_LEVEL(stem, level) \ - .names[level] = "btrfs-" stem "-0" #level, - -#define DEFINE_NAME(stem) \ - DEFINE_LEVEL(stem, 0) \ - DEFINE_LEVEL(stem, 1) \ - DEFINE_LEVEL(stem, 2) \ - DEFINE_LEVEL(stem, 3) \ - DEFINE_LEVEL(stem, 4) \ - DEFINE_LEVEL(stem, 5) \ - DEFINE_LEVEL(stem, 6) \ - DEFINE_LEVEL(stem, 7) - -static struct btrfs_lockdep_keyset { - u64 id; /* root objectid */ - /* Longest entry: btrfs-free-space-00 */ - char names[BTRFS_MAX_LEVEL][20]; - struct lock_class_key keys[BTRFS_MAX_LEVEL]; -} btrfs_lockdep_keysets[] = { - { .id = BTRFS_ROOT_TREE_OBJECTID, DEFINE_NAME("root") }, - { .id = BTRFS_EXTENT_TREE_OBJECTID, DEFINE_NAME("extent") }, - { .id = BTRFS_CHUNK_TREE_OBJECTID, DEFINE_NAME("chunk") }, - { .id = BTRFS_DEV_TREE_OBJECTID, DEFINE_NAME("dev") }, - { .id = BTRFS_CSUM_TREE_OBJECTID, DEFINE_NAME("csum") }, - { .id = BTRFS_QUOTA_TREE_OBJECTID, DEFINE_NAME("quota") }, - { .id = BTRFS_TREE_LOG_OBJECTID, DEFINE_NAME("log") }, - { .id = BTRFS_TREE_RELOC_OBJECTID, DEFINE_NAME("treloc") }, - { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, DEFINE_NAME("dreloc") }, - { .id = BTRFS_UUID_TREE_OBJECTID, DEFINE_NAME("uuid") }, - { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, DEFINE_NAME("free-space") }, - { .id = 0, DEFINE_NAME("tree") }, -}; - -#undef DEFINE_LEVEL -#undef DEFINE_NAME - -void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, - int level) -{ - struct btrfs_lockdep_keyset *ks; - - BUG_ON(level >= ARRAY_SIZE(ks->keys)); - - /* find the matching keyset, id 0 is the default entry */ - for (ks = btrfs_lockdep_keysets; ks->id; ks++) - if (ks->id == objectid) - break; - - lockdep_set_class_and_name(&eb->lock, - &ks->keys[level], ks->names[level]); -} - -#endif - -/* * Compute the csum of a btree block and store the result to provided buffer. */ static void csum_tree_block(struct extent_buffer *buf, u8 *result) @@ -3150,7 +3068,6 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) init_waitqueue_head(&fs_info->transaction_blocked_wait); init_waitqueue_head(&fs_info->async_submit_wait); init_waitqueue_head(&fs_info->delayed_iputs_wait); - init_waitqueue_head(&fs_info->zone_finish_wait); /* Usable values until the real ones are cached from the superblock */ fs_info->nodesize = 4096; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 8993b428e09c..47ad8e0a2d33 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -137,14 +137,4 @@ int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags); int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid); int btrfs_init_root_free_objectid(struct btrfs_root *root); -#ifdef CONFIG_DEBUG_LOCK_ALLOC -void btrfs_set_buffer_lockdep_class(u64 objectid, - struct extent_buffer *eb, int level); -#else -static inline void btrfs_set_buffer_lockdep_class(u64 objectid, - struct extent_buffer *eb, int level) -{ -} -#endif - #endif diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index ea3ec1e761e8..6914cd8024ba 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2551,17 +2551,10 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, return -EINVAL; /* - * pull in the free space cache (if any) so that our pin - * removes the free space from the cache. We have load_only set - * to one because the slow code to read in the free extents does check - * the pinned extents. + * Fully cache the free space first so that our pin removes the free space + * from the cache. */ - btrfs_cache_block_group(cache, 1); - /* - * Make sure we wait until the cache is completely built in case it is - * missing or is invalid and therefore needs to be rebuilt. - */ - ret = btrfs_wait_block_group_cache_done(cache); + ret = btrfs_cache_block_group(cache, true); if (ret) goto out; @@ -2584,12 +2577,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info, if (!block_group) return -EINVAL; - btrfs_cache_block_group(block_group, 1); - /* - * Make sure we wait until the cache is completely built in case it is - * missing or is invalid and therefore needs to be rebuilt. - */ - ret = btrfs_wait_block_group_cache_done(block_group); + ret = btrfs_cache_block_group(block_group, true); if (ret) goto out; @@ -4399,7 +4387,7 @@ have_block_group: ffe_ctl->cached = btrfs_block_group_done(block_group); if (unlikely(!ffe_ctl->cached)) { ffe_ctl->have_caching_bg = true; - ret = btrfs_cache_block_group(block_group, 0); + ret = btrfs_cache_block_group(block_group, false); /* * If we get ENOMEM here or something else we want to @@ -4867,6 +4855,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *buf; + u64 lockdep_owner = owner; buf = btrfs_find_create_tree_block(fs_info, bytenr, owner, level); if (IS_ERR(buf)) @@ -4886,11 +4875,26 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, } /* + * The reloc trees are just snapshots, so we need them to appear to be + * just like any other fs tree WRT lockdep. + * + * The exception however is in replace_path() in relocation, where we + * hold the lock on the original fs root and then search for the reloc + * root. At that point we need to make sure any reloc root buffers are + * set to the BTRFS_TREE_RELOC_OBJECTID lockdep class in order to make + * lockdep happy. + */ + if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID && + !test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state)) + lockdep_owner = BTRFS_FS_TREE_OBJECTID; + + /* * This needs to stay, because we could allocate a freed block from an * old tree into a new tree, so we need to make sure this new block is * set to the appropriate level and owner. */ - btrfs_set_buffer_lockdep_class(owner, buf, level); + btrfs_set_buffer_lockdep_class(lockdep_owner, buf, level); + __btrfs_tree_lock(buf, nest); btrfs_clean_tree_block(buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); @@ -6153,13 +6157,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) if (end - start >= range->minlen) { if (!btrfs_block_group_done(cache)) { - ret = btrfs_cache_block_group(cache, 0); - if (ret) { - bg_failed++; - bg_ret = ret; - continue; - } - ret = btrfs_wait_block_group_cache_done(cache); + ret = btrfs_cache_block_group(cache, true); if (ret) { bg_failed++; bg_ret = ret; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index bfae67c593c5..cf4f19e80e2f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3233,7 +3233,7 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl, u32 bio_size = bio->bi_iter.bi_size; u32 real_size; const sector_t sector = disk_bytenr >> SECTOR_SHIFT; - bool contig; + bool contig = false; int ret; ASSERT(bio); @@ -3242,10 +3242,35 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl, if (bio_ctrl->compress_type != compress_type) return 0; - if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) + + if (bio->bi_iter.bi_size == 0) { + /* We can always add a page into an empty bio. */ + contig = true; + } else if (bio_ctrl->compress_type == BTRFS_COMPRESS_NONE) { + struct bio_vec *bvec = bio_last_bvec_all(bio); + + /* + * The contig check requires the following conditions to be met: + * 1) The pages are belonging to the same inode + * This is implied by the call chain. + * + * 2) The range has adjacent logical bytenr + * + * 3) The range has adjacent file offset + * This is required for the usage of btrfs_bio->file_offset. + */ + if (bio_end_sector(bio) == sector && + page_offset(bvec->bv_page) + bvec->bv_offset + + bvec->bv_len == page_offset(page) + pg_offset) + contig = true; + } else { + /* + * For compression, all IO should have its logical bytenr + * set to the starting bytenr of the compressed extent. + */ contig = bio->bi_iter.bi_sector == sector; - else - contig = bio_end_sector(bio) == sector; + } + if (!contig) return 0; @@ -6140,6 +6165,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, struct extent_buffer *exists = NULL; struct page *p; struct address_space *mapping = fs_info->btree_inode->i_mapping; + u64 lockdep_owner = owner_root; int uptodate = 1; int ret; @@ -6164,7 +6190,15 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, eb = __alloc_extent_buffer(fs_info, start, len); if (!eb) return ERR_PTR(-ENOMEM); - btrfs_set_buffer_lockdep_class(owner_root, eb, level); + + /* + * The reloc trees are just snapshots, so we need them to appear to be + * just like any other fs tree WRT lockdep. + */ + if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID) + lockdep_owner = BTRFS_FS_TREE_OBJECTID; + + btrfs_set_buffer_lockdep_class(lockdep_owner, eb, level); num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++, index++) { diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 66c822182ecc..5a3f6e0d9688 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2482,6 +2482,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); + btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_mark_buffer_dirty(leaf); goto out; } @@ -2498,6 +2499,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); + btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_mark_buffer_dirty(leaf); goto out; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f0c97d25b4a0..1372210869b1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1644,10 +1644,9 @@ static noinline int run_delalloc_zoned(struct btrfs_inode *inode, done_offset = end; if (done_offset == start) { - struct btrfs_fs_info *info = inode->root->fs_info; - - wait_var_event(&info->zone_finish_wait, - !test_bit(BTRFS_FS_NEED_ZONE_FINISH, &info->flags)); + wait_on_bit_io(&inode->root->fs_info->flags, + BTRFS_FS_NEED_ZONE_FINISH, + TASK_UNINTERRUPTIBLE); continue; } @@ -7694,6 +7693,20 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, bool unlock_extents = false; /* + * We could potentially fault if we have a buffer > PAGE_SIZE, and if + * we're NOWAIT we may submit a bio for a partial range and return + * EIOCBQUEUED, which would result in an errant short read. + * + * The best way to handle this would be to allow for partial completions + * of iocb's, so we could submit the partial bio, return and fault in + * the rest of the pages, and then submit the io for the rest of the + * range. However we don't have that currently, so simply return + * -EAGAIN at this point so that the normal path is used. + */ + if (!write && (flags & IOMAP_NOWAIT) && length > PAGE_SIZE) + return -EAGAIN; + + /* * Cap the size of reads to that usually seen in buffered I/O as we need * to allocate a contiguous array for the checksums. */ diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 33461b4f9c8b..9063072b399b 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -14,6 +14,93 @@ #include "locking.h" /* + * Lockdep class keys for extent_buffer->lock's in this root. For a given + * eb, the lockdep key is determined by the btrfs_root it belongs to and + * the level the eb occupies in the tree. + * + * Different roots are used for different purposes and may nest inside each + * other and they require separate keysets. As lockdep keys should be + * static, assign keysets according to the purpose of the root as indicated + * by btrfs_root->root_key.objectid. This ensures that all special purpose + * roots have separate keysets. + * + * Lock-nesting across peer nodes is always done with the immediate parent + * node locked thus preventing deadlock. As lockdep doesn't know this, use + * subclass to avoid triggering lockdep warning in such cases. + * + * The key is set by the readpage_end_io_hook after the buffer has passed + * csum validation but before the pages are unlocked. It is also set by + * btrfs_init_new_buffer on freshly allocated blocks. + * + * We also add a check to make sure the highest level of the tree is the + * same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this code + * needs update as well. + */ +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#if BTRFS_MAX_LEVEL != 8 +#error +#endif + +#define DEFINE_LEVEL(stem, level) \ + .names[level] = "btrfs-" stem "-0" #level, + +#define DEFINE_NAME(stem) \ + DEFINE_LEVEL(stem, 0) \ + DEFINE_LEVEL(stem, 1) \ + DEFINE_LEVEL(stem, 2) \ + DEFINE_LEVEL(stem, 3) \ + DEFINE_LEVEL(stem, 4) \ + DEFINE_LEVEL(stem, 5) \ + DEFINE_LEVEL(stem, 6) \ + DEFINE_LEVEL(stem, 7) + +static struct btrfs_lockdep_keyset { + u64 id; /* root objectid */ + /* Longest entry: btrfs-free-space-00 */ + char names[BTRFS_MAX_LEVEL][20]; + struct lock_class_key keys[BTRFS_MAX_LEVEL]; +} btrfs_lockdep_keysets[] = { + { .id = BTRFS_ROOT_TREE_OBJECTID, DEFINE_NAME("root") }, + { .id = BTRFS_EXTENT_TREE_OBJECTID, DEFINE_NAME("extent") }, + { .id = BTRFS_CHUNK_TREE_OBJECTID, DEFINE_NAME("chunk") }, + { .id = BTRFS_DEV_TREE_OBJECTID, DEFINE_NAME("dev") }, + { .id = BTRFS_CSUM_TREE_OBJECTID, DEFINE_NAME("csum") }, + { .id = BTRFS_QUOTA_TREE_OBJECTID, DEFINE_NAME("quota") }, + { .id = BTRFS_TREE_LOG_OBJECTID, DEFINE_NAME("log") }, + { .id = BTRFS_TREE_RELOC_OBJECTID, DEFINE_NAME("treloc") }, + { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, DEFINE_NAME("dreloc") }, + { .id = BTRFS_UUID_TREE_OBJECTID, DEFINE_NAME("uuid") }, + { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, DEFINE_NAME("free-space") }, + { .id = 0, DEFINE_NAME("tree") }, +}; + +#undef DEFINE_LEVEL +#undef DEFINE_NAME + +void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level) +{ + struct btrfs_lockdep_keyset *ks; + + BUG_ON(level >= ARRAY_SIZE(ks->keys)); + + /* Find the matching keyset, id 0 is the default entry */ + for (ks = btrfs_lockdep_keysets; ks->id; ks++) + if (ks->id == objectid) + break; + + lockdep_set_class_and_name(&eb->lock, &ks->keys[level], ks->names[level]); +} + +void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb) +{ + if (test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state)) + btrfs_set_buffer_lockdep_class(root->root_key.objectid, + eb, btrfs_header_level(eb)); +} + +#endif + +/* * Extent buffer locking * ===================== * @@ -164,6 +251,8 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root) while (1) { eb = btrfs_root_node(root); + + btrfs_maybe_reset_lockdep_class(root, eb); btrfs_tree_lock(eb); if (eb == root->node) break; @@ -185,6 +274,8 @@ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root) while (1) { eb = btrfs_root_node(root); + + btrfs_maybe_reset_lockdep_class(root, eb); btrfs_tree_read_lock(eb); if (eb == root->node) break; diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index bbc45534ae9a..ab268be09bb5 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -131,4 +131,18 @@ void btrfs_drew_write_unlock(struct btrfs_drew_lock *lock); void btrfs_drew_read_lock(struct btrfs_drew_lock *lock); void btrfs_drew_read_unlock(struct btrfs_drew_lock *lock); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level); +void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb); +#else +static inline void btrfs_set_buffer_lockdep_class(u64 objectid, + struct extent_buffer *eb, int level) +{ +} +static inline void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, + struct extent_buffer *eb) +{ +} +#endif + #endif diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index a6dc827e75af..45c02aba2492 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1326,7 +1326,9 @@ again: btrfs_release_path(path); path->lowest_level = level; + set_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state); ret = btrfs_search_slot(trans, src, &key, path, 0, 1); + clear_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state); path->lowest_level = 0; if (ret) { if (ret > 0) @@ -3573,7 +3575,12 @@ int prepare_to_relocate(struct reloc_control *rc) */ return PTR_ERR(trans); } - return btrfs_commit_transaction(trans); + + ret = btrfs_commit_transaction(trans); + if (ret) + unset_reloc_control(rc); + + return ret; } static noinline_for_stack int relocate_block_group(struct reloc_control *rc) diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index a64b26b16904..d647cb2938c0 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -349,9 +349,10 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, key.offset = ref_id; again: ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); - if (ret < 0) + if (ret < 0) { + err = ret; goto out; - if (ret == 0) { + } else if (ret == 0) { leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index d0cbeb7ae81c..435559ba94fa 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -199,7 +199,7 @@ static u64 calc_chunk_size(const struct btrfs_fs_info *fs_info, u64 flags) ASSERT(flags & BTRFS_BLOCK_GROUP_TYPE_MASK); if (flags & BTRFS_BLOCK_GROUP_DATA) - return SZ_1G; + return BTRFS_MAX_DATA_CHUNK_SIZE; else if (flags & BTRFS_BLOCK_GROUP_SYSTEM) return SZ_32M; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 4c7089b1681b..f89beac3c665 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1816,6 +1816,8 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, error = -EBUSY; } else { snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); + shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name, + s->s_id); btrfs_sb(s)->bdev_holder = fs_type; if (!strstr(crc32c_impl(), "generic")) set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 9e0e0ae2288c..43f905ab0a18 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1233,7 +1233,8 @@ static void extent_err(const struct extent_buffer *eb, int slot, } static int check_extent_item(struct extent_buffer *leaf, - struct btrfs_key *key, int slot) + struct btrfs_key *key, int slot, + struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_extent_item *ei; @@ -1453,6 +1454,26 @@ static int check_extent_item(struct extent_buffer *leaf, total_refs, inline_refs); return -EUCLEAN; } + + if ((prev_key->type == BTRFS_EXTENT_ITEM_KEY) || + (prev_key->type == BTRFS_METADATA_ITEM_KEY)) { + u64 prev_end = prev_key->objectid; + + if (prev_key->type == BTRFS_METADATA_ITEM_KEY) + prev_end += fs_info->nodesize; + else + prev_end += prev_key->offset; + + if (unlikely(prev_end > key->objectid)) { + extent_err(leaf, slot, + "previous extent [%llu %u %llu] overlaps current extent [%llu %u %llu]", + prev_key->objectid, prev_key->type, + prev_key->offset, key->objectid, key->type, + key->offset); + return -EUCLEAN; + } + } + return 0; } @@ -1621,7 +1642,7 @@ static int check_leaf_item(struct extent_buffer *leaf, break; case BTRFS_EXTENT_ITEM_KEY: case BTRFS_METADATA_ITEM_KEY: - ret = check_extent_item(leaf, key, slot); + ret = check_extent_item(leaf, key, slot, prev_key); break; case BTRFS_TREE_BLOCK_REF_KEY: case BTRFS_SHARED_DATA_REF_KEY: diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index dcf75a8daa20..9205c4a5ca81 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1146,7 +1146,9 @@ again: extref = btrfs_lookup_inode_extref(NULL, root, path, name, namelen, inode_objectid, parent_objectid, 0, 0); - if (!IS_ERR_OR_NULL(extref)) { + if (IS_ERR(extref)) { + return PTR_ERR(extref); + } else if (extref) { u32 item_size; u32 cur_offset = 0; unsigned long base; @@ -1457,7 +1459,7 @@ static int add_link(struct btrfs_trans_handle *trans, * on the inode will not free it. We will fixup the link count later. */ if (other_inode->i_nlink == 0) - inc_nlink(other_inode); + set_nlink(other_inode, 1); add_link: ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name, namelen, 0, ref_index); @@ -1600,7 +1602,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, * free it. We will fixup the link count later. */ if (!ret && inode->i_nlink == 0) - inc_nlink(inode); + set_nlink(inode, 1); } if (ret < 0) goto out; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 272901514b0c..f63ff91e2883 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2345,8 +2345,11 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0, &bdev, &disk_super); - if (ret) + if (ret) { + btrfs_put_dev_args_from_path(args); return ret; + } + args->devid = btrfs_stack_device_id(&disk_super->dev_item); memcpy(args->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE); if (btrfs_fs_incompat(fs_info, METADATA_UUID)) @@ -5264,6 +5267,9 @@ static int decide_stripe_size_regular(struct alloc_chunk_ctl *ctl, ctl->stripe_size); } + /* Stripe size should not go beyond 1G. */ + ctl->stripe_size = min_t(u64, ctl->stripe_size, SZ_1G); + /* Align to BTRFS_STRIPE_LEN */ ctl->stripe_size = round_down(ctl->stripe_size, BTRFS_STRIPE_LEN); ctl->chunk_size = ctl->stripe_size * data_stripes; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 7421abcf325a..5bb8d8c86311 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -371,6 +371,9 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler, const char *name, const void *buffer, size_t size, int flags) { + if (btrfs_root_readonly(BTRFS_I(inode)->root)) + return -EROFS; + name = xattr_full_name(handler, name); return btrfs_setxattr_trans(inode, name, buffer, size, flags); } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index b150b07ba1a7..62e7007a7e46 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -421,10 +421,19 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) * since btrfs adds the pages one by one to a bio, and btrfs cannot * increase the metadata reservation even if it increases the number of * extents, it is safe to stick with the limit. + * + * With the zoned emulation, we can have non-zoned device on the zoned + * mode. In this case, we don't have a valid max zone append size. So, + * use max_segments * PAGE_SIZE as the pseudo max_zone_append_size. */ - zone_info->max_zone_append_size = - min_t(u64, (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT, - (u64)bdev_max_segments(bdev) << PAGE_SHIFT); + if (bdev_is_zoned(bdev)) { + zone_info->max_zone_append_size = min_t(u64, + (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT, + (u64)bdev_max_segments(bdev) << PAGE_SHIFT); + } else { + zone_info->max_zone_append_size = + (u64)bdev_max_segments(bdev) << PAGE_SHIFT; + } if (!IS_ALIGNED(nr_sectors, zone_sectors)) zone_info->nr_zones++; @@ -1178,7 +1187,7 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size) * offset. */ static int calculate_alloc_pointer(struct btrfs_block_group *cache, - u64 *offset_ret) + u64 *offset_ret, bool new) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_root *root; @@ -1188,6 +1197,21 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache, int ret; u64 length; + /* + * Avoid tree lookups for a new block group, there's no use for it. + * It must always be 0. + * + * Also, we have a lock chain of extent buffer lock -> chunk mutex. + * For new a block group, this function is called from + * btrfs_make_block_group() which is already taking the chunk mutex. + * Thus, we cannot call calculate_alloc_pointer() which takes extent + * buffer locks to avoid deadlock. + */ + if (new) { + *offset_ret = 0; + return 0; + } + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -1323,6 +1347,13 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) else num_conventional++; + /* + * Consider a zone as active if we can allow any number of + * active zones. + */ + if (!device->zone_info->max_active_zones) + __set_bit(i, active); + if (!is_sequential) { alloc_offsets[i] = WP_CONVENTIONAL; continue; @@ -1389,45 +1420,23 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) __set_bit(i, active); break; } - - /* - * Consider a zone as active if we can allow any number of - * active zones. - */ - if (!device->zone_info->max_active_zones) - __set_bit(i, active); } if (num_sequential > 0) cache->seq_zone = true; if (num_conventional > 0) { - /* - * Avoid calling calculate_alloc_pointer() for new BG. It - * is no use for new BG. It must be always 0. - * - * Also, we have a lock chain of extent buffer lock -> - * chunk mutex. For new BG, this function is called from - * btrfs_make_block_group() which is already taking the - * chunk mutex. Thus, we cannot call - * calculate_alloc_pointer() which takes extent buffer - * locks to avoid deadlock. - */ - /* Zone capacity is always zone size in emulation */ cache->zone_capacity = cache->length; - if (new) { - cache->alloc_offset = 0; - goto out; - } - ret = calculate_alloc_pointer(cache, &last_alloc); - if (ret || map->num_stripes == num_conventional) { - if (!ret) - cache->alloc_offset = last_alloc; - else - btrfs_err(fs_info, + ret = calculate_alloc_pointer(cache, &last_alloc, new); + if (ret) { + btrfs_err(fs_info, "zoned: failed to determine allocation offset of bg %llu", - cache->start); + cache->start); + goto out; + } else if (map->num_stripes == num_conventional) { + cache->alloc_offset = last_alloc; + cache->zone_is_active = 1; goto out; } } @@ -1495,13 +1504,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) goto out; } - if (cache->zone_is_active) { - btrfs_get_block_group(cache); - spin_lock(&fs_info->zone_active_bgs_lock); - list_add_tail(&cache->active_bg_list, &fs_info->zone_active_bgs); - spin_unlock(&fs_info->zone_active_bgs_lock); - } - out: if (cache->alloc_offset > fs_info->zone_size) { btrfs_err(fs_info, @@ -1526,10 +1528,16 @@ out: ret = -EIO; } - if (!ret) + if (!ret) { cache->meta_write_pointer = cache->alloc_offset + cache->start; - - if (ret) { + if (cache->zone_is_active) { + btrfs_get_block_group(cache); + spin_lock(&fs_info->zone_active_bgs_lock); + list_add_tail(&cache->active_bg_list, + &fs_info->zone_active_bgs); + spin_unlock(&fs_info->zone_active_bgs_lock); + } + } else { kfree(cache->physical_map); cache->physical_map = NULL; } @@ -2007,8 +2015,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ /* For active_bg_list */ btrfs_put_block_group(block_group); - clear_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags); - wake_up_all(&fs_info->zone_finish_wait); + clear_and_wake_up_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags); return 0; } diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 6cba2c6de2f9..2ad58c465208 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -111,6 +111,7 @@ struct cachefiles_cache { char *tag; /* cache binding tag */ refcount_t unbind_pincount;/* refcount to do daemon unbind */ struct xarray reqs; /* xarray of pending on-demand requests */ + unsigned long req_id_next; struct xarray ondemand_ids; /* xarray for ondemand_id allocation */ u32 ondemand_id_next; }; diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 1fee702d5529..0254ed39f68c 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -158,9 +158,13 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) /* fail OPEN request if daemon reports an error */ if (size < 0) { - if (!IS_ERR_VALUE(size)) - size = -EINVAL; - req->error = size; + if (!IS_ERR_VALUE(size)) { + req->error = -EINVAL; + ret = -EINVAL; + } else { + req->error = size; + ret = 0; + } goto out; } @@ -238,14 +242,19 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, unsigned long id = 0; size_t n; int ret = 0; - XA_STATE(xas, &cache->reqs, 0); + XA_STATE(xas, &cache->reqs, cache->req_id_next); /* - * Search for a request that has not ever been processed, to prevent - * requests from being processed repeatedly. + * Cyclically search for a request that has not ever been processed, + * to prevent requests from being processed repeatedly, and make + * request distribution fair. */ xa_lock(&cache->reqs); req = xas_find_marked(&xas, UINT_MAX, CACHEFILES_REQ_NEW); + if (!req && cache->req_id_next > 0) { + xas_set(&xas, 0); + req = xas_find_marked(&xas, cache->req_id_next - 1, CACHEFILES_REQ_NEW); + } if (!req) { xa_unlock(&cache->reqs); return 0; @@ -260,6 +269,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, } xas_clear_mark(&xas, CACHEFILES_REQ_NEW); + cache->req_id_next = xas.xa_index + 1; xa_unlock(&cache->reqs); id = xas.xa_index; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index d6e5916138e4..dcf701b05cc1 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -122,7 +122,7 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio) * Reference snap context in folio->private. Also set * PagePrivate so that we get invalidate_folio callback. */ - VM_BUG_ON_FOLIO(folio_test_private(folio), folio); + VM_WARN_ON_FOLIO(folio->private, folio); folio_attach_private(folio, snapc); return ceph_fscache_dirty_folio(mapping, folio); @@ -237,7 +237,7 @@ static void finish_netfs_read(struct ceph_osd_request *req) if (err >= 0 && err < subreq->len) __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - netfs_subreq_terminated(subreq, err, true); + netfs_subreq_terminated(subreq, err, false); num_pages = calc_pages_for(osd_data->alignment, osd_data->length); ceph_put_page_vector(osd_data->pages, num_pages, false); @@ -313,8 +313,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) int err = 0; u64 len = subreq->len; - if (ci->i_inline_version != CEPH_INLINE_NONE && - ceph_netfs_issue_op_inline(subreq)) + if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq)) return; req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len, @@ -329,7 +328,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len); iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len); - err = iov_iter_get_pages_alloc(&iter, &pages, len, &page_off); + err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off); if (err < 0) { dout("%s: iov_ter_get_pages_alloc returned %d\n", __func__, err); goto out; @@ -338,6 +337,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) /* should always give us a page-aligned read */ WARN_ON_ONCE(page_off); len = err; + err = 0; osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false); req->r_callback = finish_netfs_read; @@ -345,9 +345,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) req->r_inode = inode; ihold(inode); - err = ceph_osdc_start_request(req->r_osdc, req, false); - if (err) - iput(inode); + ceph_osdc_start_request(req->r_osdc, req); out: ceph_osdc_put_request(req); if (err) @@ -621,9 +619,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) dout("writepage %llu~%llu (%llu bytes)\n", page_off, len, len); req->r_mtime = inode->i_mtime; - err = ceph_osdc_start_request(osdc, req, true); - if (!err) - err = ceph_osdc_wait_request(osdc, req); + ceph_osdc_start_request(osdc, req); + err = ceph_osdc_wait_request(osdc, req); ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency, req->r_end_latency, len, err); @@ -1151,8 +1148,7 @@ new_request: } req->r_mtime = inode->i_mtime; - rc = ceph_osdc_start_request(&fsc->client->osdc, req, true); - BUG_ON(rc); + ceph_osdc_start_request(&fsc->client->osdc, req); req = NULL; wbc->nr_to_write -= i; @@ -1327,16 +1323,13 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, int r; r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL); - if (r == 0) - folio_wait_fscache(folio); - if (r < 0) { - if (folio) - folio_put(folio); - } else { - WARN_ON_ONCE(!folio_test_locked(folio)); - *pagep = &folio->page; - } - return r; + if (r < 0) + return r; + + folio_wait_fscache(folio); + WARN_ON_ONCE(!folio_test_locked(folio)); + *pagep = &folio->page; + return 0; } /* @@ -1439,7 +1432,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf) inode, off, ceph_cap_string(got)); if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) || - ci->i_inline_version == CEPH_INLINE_NONE) { + !ceph_has_inline_data(ci)) { CEPH_DEFINE_RW_CONTEXT(rw_ctx, got); ceph_add_rw_context(fi, &rw_ctx); ret = filemap_fault(vmf); @@ -1696,9 +1689,8 @@ int ceph_uninline_data(struct file *file) } req->r_mtime = inode->i_mtime; - err = ceph_osdc_start_request(&fsc->client->osdc, req, false); - if (!err) - err = ceph_osdc_wait_request(&fsc->client->osdc, req); + ceph_osdc_start_request(&fsc->client->osdc, req); + err = ceph_osdc_wait_request(&fsc->client->osdc, req); ceph_osdc_put_request(req); if (err < 0) goto out_unlock; @@ -1739,9 +1731,8 @@ int ceph_uninline_data(struct file *file) } req->r_mtime = inode->i_mtime; - err = ceph_osdc_start_request(&fsc->client->osdc, req, false); - if (!err) - err = ceph_osdc_wait_request(&fsc->client->osdc, req); + ceph_osdc_start_request(&fsc->client->osdc, req); + err = ceph_osdc_wait_request(&fsc->client->osdc, req); ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency, req->r_end_latency, len, err); @@ -1912,15 +1903,13 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, osd_req_op_raw_data_in_pages(rd_req, 0, pages, PAGE_SIZE, 0, false, true); - err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false); + ceph_osdc_start_request(&fsc->client->osdc, rd_req); wr_req->r_mtime = ci->netfs.inode.i_mtime; - err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false); + ceph_osdc_start_request(&fsc->client->osdc, wr_req); - if (!err) - err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req); - if (!err2) - err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req); + err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req); + err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req); if (err >= 0 || err == -ENOENT) have |= POOL_READ; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index ac8fd5e7f540..53cfe026b3ea 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -602,8 +602,8 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap, * @ci: inode to be moved * @session: new auth caps session */ -static void change_auth_cap_ses(struct ceph_inode_info *ci, - struct ceph_mds_session *session) +void change_auth_cap_ses(struct ceph_inode_info *ci, + struct ceph_mds_session *session) { lockdep_assert_held(&ci->i_ceph_lock); @@ -1978,14 +1978,15 @@ retry: } dout("check_caps %llx.%llx file_want %s used %s dirty %s flushing %s" - " issued %s revoking %s retain %s %s%s\n", ceph_vinop(inode), + " issued %s revoking %s retain %s %s%s%s\n", ceph_vinop(inode), ceph_cap_string(file_wanted), ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps), ceph_cap_string(ci->i_flushing_caps), ceph_cap_string(issued), ceph_cap_string(revoking), ceph_cap_string(retain), (flags & CHECK_CAPS_AUTHONLY) ? " AUTHONLY" : "", - (flags & CHECK_CAPS_FLUSH) ? " FLUSH" : ""); + (flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "", + (flags & CHECK_CAPS_NOINVAL) ? " NOINVAL" : ""); /* * If we no longer need to hold onto old our caps, and we may @@ -3005,7 +3006,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got } if (S_ISREG(ci->netfs.inode.i_mode) && - ci->i_inline_version != CEPH_INLINE_NONE && + ceph_has_inline_data(ci) && (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) && i_size_read(inode) > 0) { struct page *page = @@ -3578,24 +3579,23 @@ static void handle_cap_grant(struct inode *inode, fill_inline = true; } - if (ci->i_auth_cap == cap && - le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) { - if (newcaps & ~extra_info->issued) - wake = true; + if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) { + if (ci->i_auth_cap == cap) { + if (newcaps & ~extra_info->issued) + wake = true; - if (ci->i_requested_max_size > max_size || - !(le32_to_cpu(grant->wanted) & CEPH_CAP_ANY_FILE_WR)) { - /* re-request max_size if necessary */ - ci->i_requested_max_size = 0; - wake = true; - } + if (ci->i_requested_max_size > max_size || + !(le32_to_cpu(grant->wanted) & CEPH_CAP_ANY_FILE_WR)) { + /* re-request max_size if necessary */ + ci->i_requested_max_size = 0; + wake = true; + } - ceph_kick_flushing_inode_caps(session, ci); - spin_unlock(&ci->i_ceph_lock); + ceph_kick_flushing_inode_caps(session, ci); + } up_read(&session->s_mdsc->snap_rwsem); - } else { - spin_unlock(&ci->i_ceph_lock); } + spin_unlock(&ci->i_ceph_lock); if (fill_inline) ceph_fill_inline_data(inode, NULL, extra_info->inline_data, diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index eae417d71136..e7e2ebac330d 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -856,6 +856,10 @@ static int ceph_mknod(struct user_namespace *mnt_userns, struct inode *dir, if (ceph_snap(dir) != CEPH_NOSNAP) return -EROFS; + err = ceph_wait_on_conflict_unlink(dentry); + if (err) + return err; + if (ceph_quota_is_max_files_exceeded(dir)) { err = -EDQUOT; goto out; @@ -918,6 +922,10 @@ static int ceph_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (ceph_snap(dir) != CEPH_NOSNAP) return -EROFS; + err = ceph_wait_on_conflict_unlink(dentry); + if (err) + return err; + if (ceph_quota_is_max_files_exceeded(dir)) { err = -EDQUOT; goto out; @@ -968,9 +976,13 @@ static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir, struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb); struct ceph_mds_request *req; struct ceph_acl_sec_ctx as_ctx = {}; - int err = -EROFS; + int err; int op; + err = ceph_wait_on_conflict_unlink(dentry); + if (err) + return err; + if (ceph_snap(dir) == CEPH_SNAPDIR) { /* mkdir .snap/foo is a MKSNAP */ op = CEPH_MDS_OP_MKSNAP; @@ -980,6 +992,7 @@ static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir, dout("mkdir dir %p dn %p mode 0%ho\n", dir, dentry, mode); op = CEPH_MDS_OP_MKDIR; } else { + err = -EROFS; goto out; } @@ -1037,6 +1050,10 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir, struct ceph_mds_request *req; int err; + err = ceph_wait_on_conflict_unlink(dentry); + if (err) + return err; + if (ceph_snap(dir) != CEPH_NOSNAP) return -EROFS; @@ -1071,9 +1088,27 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir, static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, struct ceph_mds_request *req) { + struct dentry *dentry = req->r_dentry; + struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb); + struct ceph_dentry_info *di = ceph_dentry(dentry); int result = req->r_err ? req->r_err : le32_to_cpu(req->r_reply_info.head->result); + if (!test_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags)) + pr_warn("%s dentry %p:%pd async unlink bit is not set\n", + __func__, dentry, dentry); + + spin_lock(&fsc->async_unlink_conflict_lock); + hash_del_rcu(&di->hnode); + spin_unlock(&fsc->async_unlink_conflict_lock); + + spin_lock(&dentry->d_lock); + di->flags &= ~CEPH_DENTRY_ASYNC_UNLINK; + wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_UNLINK_BIT); + spin_unlock(&dentry->d_lock); + + synchronize_rcu(); + if (result == -EJUKEBOX) goto out; @@ -1081,7 +1116,7 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, if (result) { int pathlen = 0; u64 base = 0; - char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen, + char *path = ceph_mdsc_build_path(dentry, &pathlen, &base, 0); /* mark error on parent + clear complete */ @@ -1089,13 +1124,13 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, ceph_dir_clear_complete(req->r_parent); /* drop the dentry -- we don't know its status */ - if (!d_unhashed(req->r_dentry)) - d_drop(req->r_dentry); + if (!d_unhashed(dentry)) + d_drop(dentry); /* mark inode itself for an error (since metadata is bogus) */ mapping_set_error(req->r_old_inode->i_mapping, result); - pr_warn("ceph: async unlink failure path=(%llx)%s result=%d!\n", + pr_warn("async unlink failure path=(%llx)%s result=%d!\n", base, IS_ERR(path) ? "<<bad>>" : path, result); ceph_mdsc_free_path(path, pathlen); } @@ -1180,6 +1215,8 @@ retry: if (try_async && op == CEPH_MDS_OP_UNLINK && (req->r_dir_caps = get_caps_for_async_unlink(dir, dentry))) { + struct ceph_dentry_info *di = ceph_dentry(dentry); + dout("async unlink on %llu/%.*s caps=%s", ceph_ino(dir), dentry->d_name.len, dentry->d_name.name, ceph_cap_string(req->r_dir_caps)); @@ -1187,6 +1224,16 @@ retry: req->r_callback = ceph_async_unlink_cb; req->r_old_inode = d_inode(dentry); ihold(req->r_old_inode); + + spin_lock(&dentry->d_lock); + di->flags |= CEPH_DENTRY_ASYNC_UNLINK; + spin_unlock(&dentry->d_lock); + + spin_lock(&fsc->async_unlink_conflict_lock); + hash_add_rcu(fsc->async_unlink_conflict, &di->hnode, + dentry->d_name.hash); + spin_unlock(&fsc->async_unlink_conflict_lock); + err = ceph_mdsc_submit_request(mdsc, dir, req); if (!err) { /* @@ -1195,10 +1242,20 @@ retry: */ drop_nlink(inode); d_delete(dentry); - } else if (err == -EJUKEBOX) { - try_async = false; - ceph_mdsc_put_request(req); - goto retry; + } else { + spin_lock(&fsc->async_unlink_conflict_lock); + hash_del_rcu(&di->hnode); + spin_unlock(&fsc->async_unlink_conflict_lock); + + spin_lock(&dentry->d_lock); + di->flags &= ~CEPH_DENTRY_ASYNC_UNLINK; + spin_unlock(&dentry->d_lock); + + if (err == -EJUKEBOX) { + try_async = false; + ceph_mdsc_put_request(req); + goto retry; + } } } else { set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); @@ -1237,6 +1294,10 @@ static int ceph_rename(struct user_namespace *mnt_userns, struct inode *old_dir, (!ceph_quota_is_same_realm(old_dir, new_dir))) return -EXDEV; + err = ceph_wait_on_conflict_unlink(new_dentry); + if (err) + return err; + dout("rename dir %p dentry %p to dir %p dentry %p\n", old_dir, old_dentry, new_dir, new_dentry); req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index da59e836a06e..04fd34557de8 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -95,12 +95,11 @@ static ssize_t __iter_get_bvecs(struct iov_iter *iter, size_t maxsize, size_t start; int idx = 0; - bytes = iov_iter_get_pages(iter, pages, maxsize - size, + bytes = iov_iter_get_pages2(iter, pages, maxsize - size, ITER_GET_BVECS_PAGES, &start); if (bytes < 0) return size ?: bytes; - iov_iter_advance(iter, bytes); size += bytes; for ( ; bytes; idx++, bvec_idx++) { @@ -241,8 +240,7 @@ static int ceph_init_file_info(struct inode *inode, struct file *file, INIT_LIST_HEAD(&fi->rw_contexts); fi->filp_gen = READ_ONCE(ceph_inode_to_client(inode)->filp_gen); - if ((file->f_mode & FMODE_WRITE) && - ci->i_inline_version != CEPH_INLINE_NONE) { + if ((file->f_mode & FMODE_WRITE) && ceph_has_inline_data(ci)) { ret = ceph_uninline_data(file); if (ret < 0) goto error; @@ -569,7 +567,7 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc, char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen, &base, 0); - pr_warn("ceph: async create failure path=(%llx)%s result=%d!\n", + pr_warn("async create failure path=(%llx)%s result=%d!\n", base, IS_ERR(path) ? "<<bad>>" : path, result); ceph_mdsc_free_path(path, pathlen); @@ -612,6 +610,7 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, struct ceph_mds_reply_inode in = { }; struct ceph_mds_reply_info_in iinfo = { .in = &in }; struct ceph_inode_info *ci = ceph_inode(dir); + struct ceph_dentry_info *di = ceph_dentry(dentry); struct inode *inode; struct timespec64 now; struct ceph_string *pool_ns; @@ -657,10 +656,6 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, /* Directories always inherit the setgid bit. */ if (S_ISDIR(mode)) mode |= S_ISGID; - else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && - !in_group_p(dir->i_gid) && - !capable_wrt_inode_uidgid(&init_user_ns, dir, CAP_FSETID)) - mode &= ~S_ISGID; } else { in.gid = cpu_to_le32(from_kgid(&init_user_ns, current_fsgid())); } @@ -714,6 +709,12 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, file->f_mode |= FMODE_CREATED; ret = finish_open(file, dentry, ceph_open); } + + spin_lock(&dentry->d_lock); + di->flags &= ~CEPH_DENTRY_ASYNC_CREATE; + wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_CREATE_BIT); + spin_unlock(&dentry->d_lock); + return ret; } @@ -740,6 +741,15 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, if (dentry->d_name.len > NAME_MAX) return -ENAMETOOLONG; + err = ceph_wait_on_conflict_unlink(dentry); + if (err) + return err; + /* + * Do not truncate the file, since atomic_open is called before the + * permission check. The caller will do the truncation afterward. + */ + flags &= ~O_TRUNC; + if (flags & O_CREAT) { if (ceph_quota_is_max_files_exceeded(dir)) return -EDQUOT; @@ -786,9 +796,16 @@ retry: (req->r_dir_caps = try_prep_async_create(dir, dentry, &lo, &req->r_deleg_ino))) { + struct ceph_dentry_info *di = ceph_dentry(dentry); + set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags); req->r_args.open.flags |= cpu_to_le32(CEPH_O_EXCL); req->r_callback = ceph_async_create_cb; + + spin_lock(&dentry->d_lock); + di->flags |= CEPH_DENTRY_ASYNC_CREATE; + spin_unlock(&dentry->d_lock); + err = ceph_mdsc_submit_request(mdsc, dir, req); if (!err) { err = ceph_finish_async_create(dir, dentry, @@ -807,9 +824,7 @@ retry: } set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); - err = ceph_mdsc_do_request(mdsc, - (flags & (O_CREAT|O_TRUNC)) ? dir : NULL, - req); + err = ceph_mdsc_do_request(mdsc, (flags & O_CREAT) ? dir : NULL, req); if (err == -ENOENT) { dentry = ceph_handle_snapdir(req, dentry); if (IS_ERR(dentry)) { @@ -965,9 +980,8 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off, false, false); - ret = ceph_osdc_start_request(osdc, req, false); - if (!ret) - ret = ceph_osdc_wait_request(osdc, req); + ceph_osdc_start_request(osdc, req); + ret = ceph_osdc_wait_request(osdc, req); ceph_update_read_metrics(&fsc->mdsc->metric, req->r_start_latency, @@ -1230,7 +1244,7 @@ static void ceph_aio_retry_work(struct work_struct *work) req->r_inode = inode; req->r_priv = aio_req; - ret = ceph_osdc_start_request(req->r_osdc, req, false); + ceph_osdc_start_request(req->r_osdc, req); out: if (ret < 0) { req->r_result = ret; @@ -1262,7 +1276,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); loff_t pos = iocb->ki_pos; bool write = iov_iter_rw(iter) == WRITE; - bool should_dirty = !write && iter_is_iovec(iter); + bool should_dirty = !write && user_backed_iter(iter); if (write && ceph_snap(file_inode(file)) != CEPH_NOSNAP) return -EROFS; @@ -1367,9 +1381,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, continue; } - ret = ceph_osdc_start_request(req->r_osdc, req, false); - if (!ret) - ret = ceph_osdc_wait_request(&fsc->client->osdc, req); + ceph_osdc_start_request(req->r_osdc, req); + ret = ceph_osdc_wait_request(&fsc->client->osdc, req); if (write) ceph_update_write_metrics(metric, req->r_start_latency, @@ -1432,8 +1445,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, r_private_item); list_del_init(&req->r_private_item); if (ret >= 0) - ret = ceph_osdc_start_request(req->r_osdc, - req, false); + ceph_osdc_start_request(req->r_osdc, req); if (ret < 0) { req->r_result = ret; ceph_aio_complete_req(req); @@ -1546,9 +1558,8 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos, false, true); req->r_mtime = mtime; - ret = ceph_osdc_start_request(&fsc->client->osdc, req, false); - if (!ret) - ret = ceph_osdc_wait_request(&fsc->client->osdc, req); + ceph_osdc_start_request(&fsc->client->osdc, req); + ret = ceph_osdc_wait_request(&fsc->client->osdc, req); ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency, req->r_end_latency, len, ret); @@ -1632,7 +1643,7 @@ again: inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, ceph_cap_string(got)); - if (ci->i_inline_version == CEPH_INLINE_NONE) { + if (!ceph_has_inline_data(ci)) { if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) { ret = ceph_direct_read_write(iocb, to, NULL, NULL); @@ -1895,7 +1906,7 @@ retry_snap: if (dirty) __mark_inode_dirty(inode, dirty); if (ceph_quota_is_max_bytes_approaching(inode, iocb->ki_pos)) - ceph_check_caps(ci, 0, NULL); + ceph_check_caps(ci, CHECK_CAPS_FLUSH, NULL); } dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n", @@ -1935,57 +1946,15 @@ out_unlocked: */ static loff_t ceph_llseek(struct file *file, loff_t offset, int whence) { - struct inode *inode = file->f_mapping->host; - struct ceph_fs_client *fsc = ceph_inode_to_client(inode); - loff_t i_size; - loff_t ret; - - inode_lock(inode); - if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) { + struct inode *inode = file_inode(file); + int ret; + ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false); if (ret < 0) - goto out; - } - - i_size = i_size_read(inode); - switch (whence) { - case SEEK_END: - offset += i_size; - break; - case SEEK_CUR: - /* - * Here we special-case the lseek(fd, 0, SEEK_CUR) - * position-querying operation. Avoid rewriting the "same" - * f_pos value back to the file because a concurrent read(), - * write() or lseek() might have altered it - */ - if (offset == 0) { - ret = file->f_pos; - goto out; - } - offset += file->f_pos; - break; - case SEEK_DATA: - if (offset < 0 || offset >= i_size) { - ret = -ENXIO; - goto out; - } - break; - case SEEK_HOLE: - if (offset < 0 || offset >= i_size) { - ret = -ENXIO; - goto out; - } - offset = i_size; - break; + return ret; } - - ret = vfs_setpos(file, offset, max(i_size, fsc->max_file_size)); - -out: - inode_unlock(inode); - return ret; + return generic_file_llseek(file, offset, whence); } static inline void ceph_zero_partial_page( @@ -2054,12 +2023,10 @@ static int ceph_zero_partial_object(struct inode *inode, } req->r_mtime = inode->i_mtime; - ret = ceph_osdc_start_request(&fsc->client->osdc, req, false); - if (!ret) { - ret = ceph_osdc_wait_request(&fsc->client->osdc, req); - if (ret == -ENOENT) - ret = 0; - } + ceph_osdc_start_request(&fsc->client->osdc, req); + ret = ceph_osdc_wait_request(&fsc->client->osdc, req); + if (ret == -ENOENT) + ret = 0; ceph_osdc_put_request(req); out: @@ -2361,7 +2328,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off if (IS_ERR(req)) ret = PTR_ERR(req); else { - ceph_osdc_start_request(osdc, req, false); + ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); ceph_update_copyfrom_metrics(&fsc->mdsc->metric, req->r_start_latency, @@ -2554,7 +2521,8 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, /* Let the MDS know about dst file size change */ if (ceph_inode_set_size(dst_inode, dst_off) || ceph_quota_is_max_bytes_approaching(dst_inode, dst_off)) - ceph_check_caps(dst_ci, CHECK_CAPS_AUTHONLY, NULL); + ceph_check_caps(dst_ci, CHECK_CAPS_AUTHONLY | CHECK_CAPS_FLUSH, + NULL); } /* Mark Fw dirty */ spin_lock(&dst_ci->i_ceph_lock); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 56c53ab3618e..42351d7a0dd6 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1049,7 +1049,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page, iinfo->inline_version >= ci->i_inline_version) { int cache_caps = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO; ci->i_inline_version = iinfo->inline_version; - if (ci->i_inline_version != CEPH_INLINE_NONE && + if (ceph_has_inline_data(ci) && (locked_page || (info_caps & cache_caps))) fill_inline = true; } @@ -2275,9 +2275,15 @@ int ceph_try_to_choose_auth_mds(struct inode *inode, int mask) * * This cost much when doing the Locker state transition and * usually will need to revoke caps from clients. + * + * And for the 'Xs' caps for getxattr we will also choose the + * auth MDS, because the MDS side code is buggy due to setxattr + * won't notify the replica MDSes when the values changed and + * the replica MDS will return the old values. Though we will + * fix it in MDS code, but this still makes sense for old ceph. */ if (((mask & CEPH_CAP_ANY_SHARED) && (issued & CEPH_CAP_ANY_EXCL)) - || (mask & CEPH_STAT_RSTAT)) + || (mask & (CEPH_STAT_RSTAT | CEPH_STAT_CAP_XATTR))) return USE_AUTH_MDS; else return USE_ANY_MDS; @@ -2321,7 +2327,8 @@ int __ceph_do_getattr(struct inode *inode, struct page *locked_page, if (inline_version == 0) { /* the reply is supposed to contain inline data */ err = -EINVAL; - } else if (inline_version == CEPH_INLINE_NONE) { + } else if (inline_version == CEPH_INLINE_NONE || + inline_version == 1) { err = -ENODATA; } else { err = req->r_reply_info.targeti.inline_len; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 33f517d549ce..80f8b9ec1a31 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -456,7 +456,7 @@ static int ceph_parse_deleg_inos(void **p, void *end, dout("added delegated inode 0x%llx\n", start - 1); } else if (err == -EBUSY) { - pr_warn("ceph: MDS delegated inode 0x%llx more than once.\n", + pr_warn("MDS delegated inode 0x%llx more than once.\n", start - 1); } else { return err; @@ -655,6 +655,79 @@ static void destroy_reply_info(struct ceph_mds_reply_info_parsed *info) free_pages((unsigned long)info->dir_entries, get_order(info->dir_buf_size)); } +/* + * In async unlink case the kclient won't wait for the first reply + * from MDS and just drop all the links and unhash the dentry and then + * succeeds immediately. + * + * For any new create/link/rename,etc requests followed by using the + * same file names we must wait for the first reply of the inflight + * unlink request, or the MDS possibly will fail these following + * requests with -EEXIST if the inflight async unlink request was + * delayed for some reasons. + * + * And the worst case is that for the none async openc request it will + * successfully open the file if the CDentry hasn't been unlinked yet, + * but later the previous delayed async unlink request will remove the + * CDenty. That means the just created file is possiblly deleted later + * by accident. + * + * We need to wait for the inflight async unlink requests to finish + * when creating new files/directories by using the same file names. + */ +int ceph_wait_on_conflict_unlink(struct dentry *dentry) +{ + struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb); + struct dentry *pdentry = dentry->d_parent; + struct dentry *udentry, *found = NULL; + struct ceph_dentry_info *di; + struct qstr dname; + u32 hash = dentry->d_name.hash; + int err; + + dname.name = dentry->d_name.name; + dname.len = dentry->d_name.len; + + rcu_read_lock(); + hash_for_each_possible_rcu(fsc->async_unlink_conflict, di, + hnode, hash) { + udentry = di->dentry; + + spin_lock(&udentry->d_lock); + if (udentry->d_name.hash != hash) + goto next; + if (unlikely(udentry->d_parent != pdentry)) + goto next; + if (!hash_hashed(&di->hnode)) + goto next; + + if (!test_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags)) + pr_warn("%s dentry %p:%pd async unlink bit is not set\n", + __func__, dentry, dentry); + + if (!d_same_name(udentry, pdentry, &dname)) + goto next; + + spin_unlock(&udentry->d_lock); + found = dget(udentry); + break; +next: + spin_unlock(&udentry->d_lock); + } + rcu_read_unlock(); + + if (likely(!found)) + return 0; + + dout("%s dentry %p:%pd conflict with old %p:%pd\n", __func__, + dentry, dentry, found, found); + + err = wait_on_bit(&di->flags, CEPH_DENTRY_ASYNC_UNLINK_BIT, + TASK_KILLABLE); + dput(found); + return err; +} + /* * sessions @@ -1220,14 +1293,17 @@ static int encode_supported_features(void **p, void *end) if (count > 0) { size_t i; size_t size = FEATURE_BYTES(count); + unsigned long bit; if (WARN_ON_ONCE(*p + 4 + size > end)) return -ERANGE; ceph_encode_32(p, size); memset(*p, 0, size); - for (i = 0; i < count; i++) - ((unsigned char*)(*p))[i / 8] |= BIT(feature_bits[i] % 8); + for (i = 0; i < count; i++) { + bit = feature_bits[i]; + ((unsigned char *)(*p))[bit / 8] |= BIT(bit % 8); + } *p += size; } else { if (WARN_ON_ONCE(*p + 4 > end)) @@ -2884,6 +2960,64 @@ static void __do_request(struct ceph_mds_client *mdsc, if (req->r_request_started == 0) /* note request start time */ req->r_request_started = jiffies; + /* + * For async create we will choose the auth MDS of frag in parent + * directory to send the request and ususally this works fine, but + * if the migrated the dirtory to another MDS before it could handle + * it the request will be forwarded. + * + * And then the auth cap will be changed. + */ + if (test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags) && req->r_num_fwd) { + struct ceph_dentry_info *di = ceph_dentry(req->r_dentry); + struct ceph_inode_info *ci; + struct ceph_cap *cap; + + /* + * The request maybe handled very fast and the new inode + * hasn't been linked to the dentry yet. We need to wait + * for the ceph_finish_async_create(), which shouldn't be + * stuck too long or fail in thoery, to finish when forwarding + * the request. + */ + if (!d_inode(req->r_dentry)) { + err = wait_on_bit(&di->flags, CEPH_DENTRY_ASYNC_CREATE_BIT, + TASK_KILLABLE); + if (err) { + mutex_lock(&req->r_fill_mutex); + set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags); + mutex_unlock(&req->r_fill_mutex); + goto out_session; + } + } + + ci = ceph_inode(d_inode(req->r_dentry)); + + spin_lock(&ci->i_ceph_lock); + cap = ci->i_auth_cap; + if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE && mds != cap->mds) { + dout("do_request session changed for auth cap %d -> %d\n", + cap->session->s_mds, session->s_mds); + + /* Remove the auth cap from old session */ + spin_lock(&cap->session->s_cap_lock); + cap->session->s_nr_caps--; + list_del_init(&cap->session_caps); + spin_unlock(&cap->session->s_cap_lock); + + /* Add the auth cap to the new session */ + cap->mds = mds; + cap->session = session; + spin_lock(&session->s_cap_lock); + session->s_nr_caps++; + list_add_tail(&cap->session_caps, &session->s_caps); + spin_unlock(&session->s_cap_lock); + + change_auth_cap_ses(ci, session); + } + spin_unlock(&ci->i_ceph_lock); + } + err = __send_request(session, req, false); out_session: @@ -3464,11 +3598,26 @@ static void handle_session(struct ceph_mds_session *session, case CEPH_SESSION_OPEN: if (session->s_state == CEPH_MDS_SESSION_RECONNECTING) pr_info("mds%d reconnect success\n", session->s_mds); - session->s_state = CEPH_MDS_SESSION_OPEN; - session->s_features = features; - renewed_caps(mdsc, session, 0); - if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features)) - metric_schedule_delayed(&mdsc->metric); + + if (session->s_state == CEPH_MDS_SESSION_OPEN) { + pr_notice("mds%d is already opened\n", session->s_mds); + } else { + session->s_state = CEPH_MDS_SESSION_OPEN; + session->s_features = features; + renewed_caps(mdsc, session, 0); + if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, + &session->s_features)) + metric_schedule_delayed(&mdsc->metric); + } + + /* + * The connection maybe broken and the session in client + * side has been reinitialized, need to update the seq + * anyway. + */ + if (!session->s_seq && seq) + session->s_seq = seq; + wake = 1; if (mdsc->stopping) __close_session(mdsc, session); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 1140aecd82ce..256e3eada6c1 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -29,14 +29,12 @@ enum ceph_feature_type { CEPHFS_FEATURE_MULTI_RECONNECT, CEPHFS_FEATURE_DELEG_INO, CEPHFS_FEATURE_METRIC_COLLECT, + CEPHFS_FEATURE_ALTERNATE_NAME, + CEPHFS_FEATURE_NOTIFY_SESSION_STATE, - CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT, + CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_NOTIFY_SESSION_STATE, }; -/* - * This will always have the highest feature bit value - * as the last element of the array. - */ #define CEPHFS_FEATURES_CLIENT_SUPPORTED { \ 0, 1, 2, 3, 4, 5, 6, 7, \ CEPHFS_FEATURE_MIMIC, \ @@ -45,10 +43,8 @@ enum ceph_feature_type { CEPHFS_FEATURE_MULTI_RECONNECT, \ CEPHFS_FEATURE_DELEG_INO, \ CEPHFS_FEATURE_METRIC_COLLECT, \ - \ - CEPHFS_FEATURE_MAX, \ + CEPHFS_FEATURE_NOTIFY_SESSION_STATE, \ } -#define CEPHFS_FEATURES_CLIENT_REQUIRED {} /* * Some lock dependencies: @@ -582,6 +578,7 @@ static inline int ceph_wait_on_async_create(struct inode *inode) TASK_KILLABLE); } +extern int ceph_wait_on_conflict_unlink(struct dentry *dentry); extern u64 ceph_get_deleg_ino(struct ceph_mds_session *session); extern int ceph_restore_deleg_ino(struct ceph_mds_session *session, u64 ino); #endif diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 30387733765d..8d0a6d2c2da4 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -352,12 +352,10 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2) __decode_and_drop_type(p, end, u8, bad_ext); } if (mdsmap_ev >= 8) { - u32 name_len; /* enabled */ ceph_decode_8_safe(p, end, m->m_enabled, bad_ext); - ceph_decode_32_safe(p, end, name_len, bad_ext); - ceph_decode_need(p, end, name_len, bad_ext); - *p += name_len; + /* fs_name */ + ceph_decode_skip_string(p, end, bad_ext); } /* damaged */ if (mdsmap_ev >= 9) { @@ -370,6 +368,22 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2) } else { m->m_damaged = false; } + if (mdsmap_ev >= 17) { + /* balancer */ + ceph_decode_skip_string(p, end, bad_ext); + /* standby_count_wanted */ + ceph_decode_skip_32(p, end, bad_ext); + /* old_max_mds */ + ceph_decode_skip_32(p, end, bad_ext); + /* min_compat_client */ + ceph_decode_skip_8(p, end, bad_ext); + /* required_client_features */ + ceph_decode_skip_set(p, end, 64, bad_ext); + ceph_decode_64_safe(p, end, m->m_max_xattr_size, bad_ext); + } else { + /* This forces the usage of the (sync) SETXATTR Op */ + m->m_max_xattr_size = 0; + } bad_ext: dout("mdsmap_decode m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n", !!m->m_enabled, !!m->m_damaged, m->m_num_laggy); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 40140805bdcf..3fc48b43cab0 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -72,15 +72,9 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_type = CEPH_SUPER_MAGIC; /* ?? */ /* - * express utilization in terms of large blocks to avoid + * Express utilization in terms of large blocks to avoid * overflow on 32-bit machines. - * - * NOTE: for the time being, we make bsize == frsize to humor - * not-yet-ancient versions of glibc that are broken. - * Someday, we will probably want to report a real block - * size... whatever that may mean for a network file system! */ - buf->f_bsize = 1 << CEPH_BLOCK_SHIFT; buf->f_frsize = 1 << CEPH_BLOCK_SHIFT; /* @@ -95,6 +89,14 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10); } + /* + * NOTE: for the time being, we make bsize == frsize to humor + * not-yet-ancient versions of glibc that are broken. + * Someday, we will probably want to report a real block + * size... whatever that may mean for a network file system! + */ + buf->f_bsize = buf->f_frsize; + buf->f_files = le64_to_cpu(st.num_objects); buf->f_ffree = -1; buf->f_namelen = NAME_MAX; @@ -816,6 +818,9 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, if (!fsc->cap_wq) goto fail_inode_wq; + hash_init(fsc->async_unlink_conflict); + spin_lock_init(&fsc->async_unlink_conflict_lock); + spin_lock(&ceph_fsc_lock); list_add_tail(&fsc->metric_wakeup, &ceph_fsc_list); spin_unlock(&ceph_fsc_lock); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index f59dac66955b..40630e6f691c 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -19,6 +19,7 @@ #include <linux/security.h> #include <linux/netfs.h> #include <linux/fscache.h> +#include <linux/hashtable.h> #include <linux/ceph/libceph.h> @@ -99,6 +100,8 @@ struct ceph_mount_options { char *mon_addr; }; +#define CEPH_ASYNC_CREATE_CONFLICT_BITS 8 + struct ceph_fs_client { struct super_block *sb; @@ -124,6 +127,9 @@ struct ceph_fs_client { struct workqueue_struct *inode_wq; struct workqueue_struct *cap_wq; + DECLARE_HASHTABLE(async_unlink_conflict, CEPH_ASYNC_CREATE_CONFLICT_BITS); + spinlock_t async_unlink_conflict_lock; + #ifdef CONFIG_DEBUG_FS struct dentry *debugfs_dentry_lru, *debugfs_caps; struct dentry *debugfs_congestion_kb; @@ -280,7 +286,8 @@ struct ceph_dentry_info { struct dentry *dentry; struct ceph_mds_session *lease_session; struct list_head lease_list; - unsigned flags; + struct hlist_node hnode; + unsigned long flags; int lease_shared_gen; u32 lease_gen; u32 lease_seq; @@ -289,10 +296,14 @@ struct ceph_dentry_info { u64 offset; }; -#define CEPH_DENTRY_REFERENCED 1 -#define CEPH_DENTRY_LEASE_LIST 2 -#define CEPH_DENTRY_SHRINK_LIST 4 -#define CEPH_DENTRY_PRIMARY_LINK 8 +#define CEPH_DENTRY_REFERENCED (1 << 0) +#define CEPH_DENTRY_LEASE_LIST (1 << 1) +#define CEPH_DENTRY_SHRINK_LIST (1 << 2) +#define CEPH_DENTRY_PRIMARY_LINK (1 << 3) +#define CEPH_DENTRY_ASYNC_UNLINK_BIT (4) +#define CEPH_DENTRY_ASYNC_UNLINK (1 << CEPH_DENTRY_ASYNC_UNLINK_BIT) +#define CEPH_DENTRY_ASYNC_CREATE_BIT (5) +#define CEPH_DENTRY_ASYNC_CREATE (1 << CEPH_DENTRY_ASYNC_CREATE_BIT) struct ceph_inode_xattrs_info { /* @@ -758,6 +769,8 @@ extern void ceph_unreserve_caps(struct ceph_mds_client *mdsc, extern void ceph_reservation_status(struct ceph_fs_client *client, int *total, int *avail, int *used, int *reserved, int *min); +extern void change_auth_cap_ses(struct ceph_inode_info *ci, + struct ceph_mds_session *session); @@ -1218,6 +1231,14 @@ extern int ceph_pool_perm_check(struct inode *inode, int need); extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc); int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate); +static inline bool ceph_has_inline_data(struct ceph_inode_info *ci) +{ + if (ci->i_inline_version == CEPH_INLINE_NONE || + ci->i_inline_version == 1) /* initial version, no data */ + return false; + return true; +} + /* file.c */ extern const struct file_operations ceph_file_fops; diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index f141f5246163..f31350cda960 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1086,7 +1086,7 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name, flags |= CEPH_XATTR_REMOVE; } - dout("setxattr value=%.*s\n", (int)size, value); + dout("setxattr value size: %zu\n", size); /* do request */ req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS); @@ -1184,8 +1184,14 @@ int __ceph_setxattr(struct inode *inode, const char *name, spin_lock(&ci->i_ceph_lock); retry: issued = __ceph_caps_issued(ci, NULL); - if (ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL)) + required_blob_size = __get_required_blob_size(ci, name_len, val_len); + if ((ci->i_xattrs.version == 0) || !(issued & CEPH_CAP_XATTR_EXCL) || + (required_blob_size > mdsc->mdsmap->m_max_xattr_size)) { + dout("%s do sync setxattr: version: %llu size: %d max: %llu\n", + __func__, ci->i_xattrs.version, required_blob_size, + mdsc->mdsmap->m_max_xattr_size); goto do_sync; + } if (!lock_snap_rwsem && !ci->i_head_snapc) { lock_snap_rwsem = true; @@ -1201,8 +1207,6 @@ retry: ceph_cap_string(issued)); __build_xattrs(inode); - required_blob_size = __get_required_blob_size(ci, name_len, val_len); - if (!ci->i_xattrs.prealloc_blob || required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) { struct ceph_buffer *blob; diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index 8c9f2c00be72..7c9785973f49 100644 --- a/fs/cifs/Makefile +++ b/fs/cifs/Makefile @@ -5,9 +5,9 @@ ccflags-y += -I$(src) # needed for trace events obj-$(CONFIG_CIFS) += cifs.o -cifs-y := trace.o cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o \ +cifs-y := trace.o cifsfs.o cifs_debug.o connect.o dir.o file.o \ inode.o link.o misc.o netmisc.o smbencrypt.o transport.o \ - cifs_unicode.o nterr.o cifsencrypt.o \ + cached_dir.o cifs_unicode.o nterr.o cifsencrypt.o \ readdir.o ioctl.o sess.o export.o unc.o winucase.o \ smb2ops.o smb2maperror.o smb2transport.o \ smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o \ @@ -31,4 +31,4 @@ cifs-$(CONFIG_CIFS_SMB_DIRECT) += smbdirect.o cifs-$(CONFIG_CIFS_ROOT) += cifsroot.o -cifs-$(CONFIG_CIFS_ALLOW_INSECURE_LEGACY) += smb1ops.o +cifs-$(CONFIG_CIFS_ALLOW_INSECURE_LEGACY) += smb1ops.o cifssmb.o diff --git a/fs/cifs/cached_dir.c b/fs/cifs/cached_dir.c new file mode 100644 index 000000000000..b401339f6e73 --- /dev/null +++ b/fs/cifs/cached_dir.c @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Functions to handle the cached directory entries + * + * Copyright (c) 2022, Ronnie Sahlberg <lsahlber@redhat.com> + */ + +#include "cifsglob.h" +#include "cifsproto.h" +#include "cifs_debug.h" +#include "smb2proto.h" +#include "cached_dir.h" + +/* + * Open the and cache a directory handle. + * If error then *cfid is not initialized. + */ +int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, + const char *path, + struct cifs_sb_info *cifs_sb, + bool lookup_only, struct cached_fid **ret_cfid) +{ + struct cifs_ses *ses; + struct TCP_Server_Info *server; + struct cifs_open_parms oparms; + struct smb2_create_rsp *o_rsp = NULL; + struct smb2_query_info_rsp *qi_rsp = NULL; + int resp_buftype[2]; + struct smb_rqst rqst[2]; + struct kvec rsp_iov[2]; + struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; + struct kvec qi_iov[1]; + int rc, flags = 0; + __le16 utf16_path = 0; /* Null - since an open of top of share */ + u8 oplock = SMB2_OPLOCK_LEVEL_II; + struct cifs_fid *pfid; + struct dentry *dentry; + struct cached_fid *cfid; + + if (tcon == NULL || tcon->nohandlecache || + is_smb1_server(tcon->ses->server)) + return -EOPNOTSUPP; + + ses = tcon->ses; + server = ses->server; + + if (cifs_sb->root == NULL) + return -ENOENT; + + if (strlen(path)) + return -ENOENT; + + dentry = cifs_sb->root; + + cfid = tcon->cfid; + mutex_lock(&cfid->fid_mutex); + if (cfid->is_valid) { + cifs_dbg(FYI, "found a cached root file handle\n"); + *ret_cfid = cfid; + kref_get(&cfid->refcount); + mutex_unlock(&cfid->fid_mutex); + return 0; + } + + /* + * We do not hold the lock for the open because in case + * SMB2_open needs to reconnect, it will end up calling + * cifs_mark_open_files_invalid() which takes the lock again + * thus causing a deadlock + */ + mutex_unlock(&cfid->fid_mutex); + + if (lookup_only) + return -ENOENT; + + if (smb3_encryption_required(tcon)) + flags |= CIFS_TRANSFORM_REQ; + + if (!server->ops->new_lease_key) + return -EIO; + + pfid = &cfid->fid; + server->ops->new_lease_key(pfid); + + memset(rqst, 0, sizeof(rqst)); + resp_buftype[0] = resp_buftype[1] = CIFS_NO_BUFFER; + memset(rsp_iov, 0, sizeof(rsp_iov)); + + /* Open */ + memset(&open_iov, 0, sizeof(open_iov)); + rqst[0].rq_iov = open_iov; + rqst[0].rq_nvec = SMB2_CREATE_IOV_SIZE; + + oparms.tcon = tcon; + oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_FILE); + oparms.desired_access = FILE_READ_ATTRIBUTES; + oparms.disposition = FILE_OPEN; + oparms.fid = pfid; + oparms.reconnect = false; + + rc = SMB2_open_init(tcon, server, + &rqst[0], &oplock, &oparms, &utf16_path); + if (rc) + goto oshr_free; + smb2_set_next_command(tcon, &rqst[0]); + + memset(&qi_iov, 0, sizeof(qi_iov)); + rqst[1].rq_iov = qi_iov; + rqst[1].rq_nvec = 1; + + rc = SMB2_query_info_init(tcon, server, + &rqst[1], COMPOUND_FID, + COMPOUND_FID, FILE_ALL_INFORMATION, + SMB2_O_INFO_FILE, 0, + sizeof(struct smb2_file_all_info) + + PATH_MAX * 2, 0, NULL); + if (rc) + goto oshr_free; + + smb2_set_related(&rqst[1]); + + rc = compound_send_recv(xid, ses, server, + flags, 2, rqst, + resp_buftype, rsp_iov); + mutex_lock(&cfid->fid_mutex); + + /* + * Now we need to check again as the cached root might have + * been successfully re-opened from a concurrent process + */ + + if (cfid->is_valid) { + /* work was already done */ + + /* stash fids for close() later */ + struct cifs_fid fid = { + .persistent_fid = pfid->persistent_fid, + .volatile_fid = pfid->volatile_fid, + }; + + /* + * caller expects this func to set the fid in cfid to valid + * cached root, so increment the refcount. + */ + kref_get(&cfid->refcount); + + mutex_unlock(&cfid->fid_mutex); + + if (rc == 0) { + /* close extra handle outside of crit sec */ + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + } + rc = 0; + goto oshr_free; + } + + /* Cached root is still invalid, continue normaly */ + + if (rc) { + if (rc == -EREMCHG) { + tcon->need_reconnect = true; + pr_warn_once("server share %s deleted\n", + tcon->treeName); + } + goto oshr_exit; + } + + atomic_inc(&tcon->num_remote_opens); + + o_rsp = (struct smb2_create_rsp *)rsp_iov[0].iov_base; + oparms.fid->persistent_fid = o_rsp->PersistentFileId; + oparms.fid->volatile_fid = o_rsp->VolatileFileId; +#ifdef CONFIG_CIFS_DEBUG2 + oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId); +#endif /* CIFS_DEBUG2 */ + + cfid->tcon = tcon; + cfid->is_valid = true; + cfid->dentry = dentry; + dget(dentry); + kref_init(&cfid->refcount); + + /* BB TBD check to see if oplock level check can be removed below */ + if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { + /* + * See commit 2f94a3125b87. Increment the refcount when we + * get a lease for root, release it if lease break occurs + */ + kref_get(&cfid->refcount); + cfid->has_lease = true; + smb2_parse_contexts(server, o_rsp, + &oparms.fid->epoch, + oparms.fid->lease_key, &oplock, + NULL, NULL); + } else + goto oshr_exit; + + qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; + if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info)) + goto oshr_exit; + if (!smb2_validate_and_copy_iov( + le16_to_cpu(qi_rsp->OutputBufferOffset), + sizeof(struct smb2_file_all_info), + &rsp_iov[1], sizeof(struct smb2_file_all_info), + (char *)&cfid->file_all_info)) + cfid->file_all_info_is_valid = true; + + cfid->time = jiffies; + +oshr_exit: + mutex_unlock(&cfid->fid_mutex); +oshr_free: + SMB2_open_free(&rqst[0]); + SMB2_query_info_free(&rqst[1]); + free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); + free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); + if (rc == 0) + *ret_cfid = cfid; + + return rc; +} + +int open_cached_dir_by_dentry(struct cifs_tcon *tcon, + struct dentry *dentry, + struct cached_fid **ret_cfid) +{ + struct cached_fid *cfid; + + cfid = tcon->cfid; + + mutex_lock(&cfid->fid_mutex); + if (cfid->dentry == dentry) { + cifs_dbg(FYI, "found a cached root file handle by dentry\n"); + *ret_cfid = cfid; + kref_get(&cfid->refcount); + mutex_unlock(&cfid->fid_mutex); + return 0; + } + mutex_unlock(&cfid->fid_mutex); + return -ENOENT; +} + +static void +smb2_close_cached_fid(struct kref *ref) +{ + struct cached_fid *cfid = container_of(ref, struct cached_fid, + refcount); + struct cached_dirent *dirent, *q; + + if (cfid->is_valid) { + cifs_dbg(FYI, "clear cached root file handle\n"); + SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, + cfid->fid.volatile_fid); + } + + /* + * We only check validity above to send SMB2_close, + * but we still need to invalidate these entries + * when this function is called + */ + cfid->is_valid = false; + cfid->file_all_info_is_valid = false; + cfid->has_lease = false; + if (cfid->dentry) { + dput(cfid->dentry); + cfid->dentry = NULL; + } + /* + * Delete all cached dirent names + */ + mutex_lock(&cfid->dirents.de_mutex); + list_for_each_entry_safe(dirent, q, &cfid->dirents.entries, entry) { + list_del(&dirent->entry); + kfree(dirent->name); + kfree(dirent); + } + cfid->dirents.is_valid = 0; + cfid->dirents.is_failed = 0; + cfid->dirents.ctx = NULL; + cfid->dirents.pos = 0; + mutex_unlock(&cfid->dirents.de_mutex); + +} + +void close_cached_dir(struct cached_fid *cfid) +{ + mutex_lock(&cfid->fid_mutex); + kref_put(&cfid->refcount, smb2_close_cached_fid); + mutex_unlock(&cfid->fid_mutex); +} + +void close_cached_dir_lease_locked(struct cached_fid *cfid) +{ + if (cfid->has_lease) { + cfid->has_lease = false; + kref_put(&cfid->refcount, smb2_close_cached_fid); + } +} + +void close_cached_dir_lease(struct cached_fid *cfid) +{ + mutex_lock(&cfid->fid_mutex); + close_cached_dir_lease_locked(cfid); + mutex_unlock(&cfid->fid_mutex); +} + +/* + * Called from cifs_kill_sb when we unmount a share + */ +void close_all_cached_dirs(struct cifs_sb_info *cifs_sb) +{ + struct rb_root *root = &cifs_sb->tlink_tree; + struct rb_node *node; + struct cached_fid *cfid; + struct cifs_tcon *tcon; + struct tcon_link *tlink; + + for (node = rb_first(root); node; node = rb_next(node)) { + tlink = rb_entry(node, struct tcon_link, tl_rbnode); + tcon = tlink_tcon(tlink); + if (IS_ERR(tcon)) + continue; + cfid = tcon->cfid; + mutex_lock(&cfid->fid_mutex); + if (cfid->dentry) { + dput(cfid->dentry); + cfid->dentry = NULL; + } + mutex_unlock(&cfid->fid_mutex); + } +} + +/* + * Invalidate and close all cached dirs when a TCON has been reset + * due to a session loss. + */ +void invalidate_all_cached_dirs(struct cifs_tcon *tcon) +{ + mutex_lock(&tcon->cfid->fid_mutex); + tcon->cfid->is_valid = false; + /* cached handle is not valid, so SMB2_CLOSE won't be sent below */ + close_cached_dir_lease_locked(tcon->cfid); + memset(&tcon->cfid->fid, 0, sizeof(struct cifs_fid)); + mutex_unlock(&tcon->cfid->fid_mutex); +} + +static void +smb2_cached_lease_break(struct work_struct *work) +{ + struct cached_fid *cfid = container_of(work, + struct cached_fid, lease_break); + + close_cached_dir_lease(cfid); +} + +int cached_dir_lease_break(struct cifs_tcon *tcon, __u8 lease_key[16]) +{ + if (tcon->cfid->is_valid && + !memcmp(lease_key, + tcon->cfid->fid.lease_key, + SMB2_LEASE_KEY_SIZE)) { + tcon->cfid->time = 0; + INIT_WORK(&tcon->cfid->lease_break, + smb2_cached_lease_break); + queue_work(cifsiod_wq, + &tcon->cfid->lease_break); + return true; + } + return false; +} + +struct cached_fid *init_cached_dir(void) +{ + struct cached_fid *cfid; + + cfid = kzalloc(sizeof(*cfid), GFP_KERNEL); + if (!cfid) + return NULL; + INIT_LIST_HEAD(&cfid->dirents.entries); + mutex_init(&cfid->dirents.de_mutex); + mutex_init(&cfid->fid_mutex); + return cfid; +} + +void free_cached_dir(struct cifs_tcon *tcon) +{ + kfree(tcon->cfid); +} diff --git a/fs/cifs/cached_dir.h b/fs/cifs/cached_dir.h new file mode 100644 index 000000000000..bd262dc8b179 --- /dev/null +++ b/fs/cifs/cached_dir.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Functions to handle the cached directory entries + * + * Copyright (c) 2022, Ronnie Sahlberg <lsahlber@redhat.com> + */ + +#ifndef _CACHED_DIR_H +#define _CACHED_DIR_H + + +struct cached_dirent { + struct list_head entry; + char *name; + int namelen; + loff_t pos; + + struct cifs_fattr fattr; +}; + +struct cached_dirents { + bool is_valid:1; + bool is_failed:1; + struct dir_context *ctx; /* + * Only used to make sure we only take entries + * from a single context. Never dereferenced. + */ + struct mutex de_mutex; + int pos; /* Expected ctx->pos */ + struct list_head entries; +}; + +struct cached_fid { + bool is_valid:1; /* Do we have a useable root fid */ + bool file_all_info_is_valid:1; + bool has_lease:1; + unsigned long time; /* jiffies of when lease was taken */ + struct kref refcount; + struct cifs_fid fid; + struct mutex fid_mutex; + struct cifs_tcon *tcon; + struct dentry *dentry; + struct work_struct lease_break; + struct smb2_file_all_info file_all_info; + struct cached_dirents dirents; +}; + +extern struct cached_fid *init_cached_dir(void); +extern void free_cached_dir(struct cifs_tcon *tcon); +extern int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, + const char *path, + struct cifs_sb_info *cifs_sb, + bool lookup_only, struct cached_fid **cfid); +extern int open_cached_dir_by_dentry(struct cifs_tcon *tcon, + struct dentry *dentry, + struct cached_fid **cfid); +extern void close_cached_dir(struct cached_fid *cfid); +extern void close_cached_dir_lease(struct cached_fid *cfid); +extern void close_cached_dir_lease_locked(struct cached_fid *cfid); +extern void close_all_cached_dirs(struct cifs_sb_info *cifs_sb); +extern void invalidate_all_cached_dirs(struct cifs_tcon *tcon); +extern int cached_dir_lease_break(struct cifs_tcon *tcon, __u8 lease_key[16]); + +#endif /* _CACHED_DIR_H */ diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 2cfbac8bb965..c05477e28cff 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -36,13 +36,13 @@ cifs_dump_mem(char *label, void *data, int length) void cifs_dump_detail(void *buf, struct TCP_Server_Info *server) { #ifdef CONFIG_CIFS_DEBUG2 - struct smb_hdr *smb = (struct smb_hdr *)buf; + struct smb_hdr *smb = buf; cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d\n", smb->Command, smb->Status.CifsError, smb->Flags, smb->Flags2, smb->Mid, smb->Pid); cifs_dbg(VFS, "smb buf %p len %u\n", smb, - server->ops->calc_smb_size(smb, server)); + server->ops->calc_smb_size(smb)); #endif /* CONFIG_CIFS_DEBUG2 */ } @@ -55,7 +55,7 @@ void cifs_dump_mids(struct TCP_Server_Info *server) return; cifs_dbg(VFS, "Dump pending requests:\n"); - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) { cifs_dbg(VFS, "State: %d Cmd: %d Pid: %d Cbdata: %p Mid %llu\n", mid_entry->mid_state, @@ -78,7 +78,7 @@ void cifs_dump_mids(struct TCP_Server_Info *server) mid_entry->resp_buf, 62); } } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); #endif /* CONFIG_CIFS_DEBUG2 */ } @@ -168,7 +168,6 @@ cifs_dump_iface(struct seq_file *m, struct cifs_server_iface *iface) static int cifs_debug_files_proc_show(struct seq_file *m, void *v) { - struct list_head *tmp, *tmp1, *tmp2; struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; @@ -184,14 +183,10 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) #endif /* CIFS_DEBUG2 */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - list_for_each(tmp, &server->smb_ses_list) { - ses = list_entry(tmp, struct cifs_ses, smb_ses_list); - list_for_each(tmp1, &ses->tcon_list) { - tcon = list_entry(tmp1, struct cifs_tcon, tcon_list); + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); - list_for_each(tmp2, &tcon->openFileList) { - cfile = list_entry(tmp2, struct cifsFileInfo, - tlist); + list_for_each_entry(cfile, &tcon->openFileList, tlist) { seq_printf(m, "0x%x 0x%llx 0x%x %d %d %d %pd", tcon->tid, @@ -218,7 +213,6 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) static int cifs_debug_data_proc_show(struct seq_file *m, void *v) { - struct list_head *tmp2, *tmp3; struct mid_q_entry *mid_entry; struct TCP_Server_Info *server; struct cifs_ses *ses; @@ -381,9 +375,7 @@ skip_rdma: seq_printf(m, "\n\n\tSessions: "); i = 0; - list_for_each(tmp2, &server->smb_ses_list) { - ses = list_entry(tmp2, struct cifs_ses, - smb_ses_list); + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { i++; if ((ses->serverDomain == NULL) || (ses->serverOS == NULL) || @@ -447,9 +439,7 @@ skip_rdma: else seq_puts(m, "none\n"); - list_for_each(tmp3, &ses->tcon_list) { - tcon = list_entry(tmp3, struct cifs_tcon, - tcon_list); + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { ++j; seq_printf(m, "\n\t%d) ", j); cifs_debug_tcon(m, tcon); @@ -473,10 +463,8 @@ skip_rdma: seq_printf(m, "\n\t\t[NONE]"); seq_puts(m, "\n\n\tMIDs: "); - spin_lock(&GlobalMid_Lock); - list_for_each(tmp3, &server->pending_mid_q) { - mid_entry = list_entry(tmp3, struct mid_q_entry, - qhead); + spin_lock(&server->mid_lock); + list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) { seq_printf(m, "\n\tState: %d com: %d pid:" " %d cbdata: %p mid %llu\n", mid_entry->mid_state, @@ -485,7 +473,7 @@ skip_rdma: mid_entry->callback_data, mid_entry->mid); } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); seq_printf(m, "\n--\n"); } if (c == 0) @@ -504,7 +492,6 @@ static ssize_t cifs_stats_proc_write(struct file *file, { bool bv; int rc; - struct list_head *tmp1, *tmp2, *tmp3; struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; @@ -514,8 +501,8 @@ static ssize_t cifs_stats_proc_write(struct file *file, #ifdef CONFIG_CIFS_STATS2 int i; - atomic_set(&totBufAllocCount, 0); - atomic_set(&totSmBufAllocCount, 0); + atomic_set(&total_buf_alloc_count, 0); + atomic_set(&total_small_buf_alloc_count, 0); #endif /* CONFIG_CIFS_STATS2 */ atomic_set(&tcpSesReconnectCount, 0); atomic_set(&tconInfoReconnectCount, 0); @@ -525,9 +512,7 @@ static ssize_t cifs_stats_proc_write(struct file *file, GlobalCurrentXid = 0; spin_unlock(&GlobalMid_Lock); spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp1, &cifs_tcp_ses_list) { - server = list_entry(tmp1, struct TCP_Server_Info, - tcp_ses_list); + list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { server->max_in_flight = 0; #ifdef CONFIG_CIFS_STATS2 for (i = 0; i < NUMBER_OF_SMB2_COMMANDS; i++) { @@ -538,13 +523,8 @@ static ssize_t cifs_stats_proc_write(struct file *file, server->fastest_cmd[0] = 0; } #endif /* CONFIG_CIFS_STATS2 */ - list_for_each(tmp2, &server->smb_ses_list) { - ses = list_entry(tmp2, struct cifs_ses, - smb_ses_list); - list_for_each(tmp3, &ses->tcon_list) { - tcon = list_entry(tmp3, - struct cifs_tcon, - tcon_list); + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { atomic_set(&tcon->num_smbs_sent, 0); spin_lock(&tcon->stat_lock); tcon->bytes_read = 0; @@ -569,7 +549,6 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) #ifdef CONFIG_CIFS_STATS2 int j; #endif /* STATS2 */ - struct list_head *tmp2, *tmp3; struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; @@ -579,17 +558,17 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) seq_printf(m, "Share (unique mount targets): %d\n", tconInfoAllocCount.counter); seq_printf(m, "SMB Request/Response Buffer: %d Pool size: %d\n", - bufAllocCount.counter, + buf_alloc_count.counter, cifs_min_rcv + tcpSesAllocCount.counter); seq_printf(m, "SMB Small Req/Resp Buffer: %d Pool size: %d\n", - smBufAllocCount.counter, cifs_min_small); + small_buf_alloc_count.counter, cifs_min_small); #ifdef CONFIG_CIFS_STATS2 seq_printf(m, "Total Large %d Small %d Allocations\n", - atomic_read(&totBufAllocCount), - atomic_read(&totSmBufAllocCount)); + atomic_read(&total_buf_alloc_count), + atomic_read(&total_small_buf_alloc_count)); #endif /* CONFIG_CIFS_STATS2 */ - seq_printf(m, "Operations (MIDs): %d\n", atomic_read(&midCount)); + seq_printf(m, "Operations (MIDs): %d\n", atomic_read(&mid_count)); seq_printf(m, "\n%d session %d share reconnects\n", tcpSesReconnectCount.counter, tconInfoReconnectCount.counter); @@ -619,13 +598,8 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) atomic_read(&server->smb2slowcmd[j]), server->hostname, j); #endif /* STATS2 */ - list_for_each(tmp2, &server->smb_ses_list) { - ses = list_entry(tmp2, struct cifs_ses, - smb_ses_list); - list_for_each(tmp3, &ses->tcon_list) { - tcon = list_entry(tmp3, - struct cifs_tcon, - tcon_list); + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { i++; seq_printf(m, "\n%d) %s", i, tcon->treeName); if (tcon->need_reconnect) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index bf861fef2f0c..fa480d62f313 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1379,6 +1379,7 @@ chown_chgrp_exit: return rc; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, const struct cifs_fid *cifsfid, u32 *pacllen, u32 __maybe_unused unused) @@ -1512,6 +1513,7 @@ out: cifs_put_tlink(tlink); return rc; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ /* Translate the CIFS ACL (similar to NTFS ACL) for a file into mode bits */ int diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 663cb9db4908..46f5718754f9 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -32,10 +32,9 @@ int __cifs_calc_signature(struct smb_rqst *rqst, int rc; struct kvec *iov = rqst->rq_iov; int n_vec = rqst->rq_nvec; - int is_smb2 = server->vals->header_preamble_size == 0; /* iov[0] is actual data and not the rfc1002 length for SMB2+ */ - if (is_smb2) { + if (!is_smb1(server)) { if (iov[0].iov_len <= 4) return -EIO; i = 0; @@ -141,13 +140,13 @@ int cifs_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server, if ((cifs_pdu == NULL) || (server == NULL)) return -EINVAL; - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (!(cifs_pdu->Flags2 & SMBFLG2_SECURITY_SIGNATURE) || server->tcpStatus == CifsNeedNegotiate) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return rc; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); if (!server->session_estab) { memcpy(cifs_pdu->Signature.SecuritySignature, "BSRSPYL", 8); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8f2e003e0590..8042d7280dec 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -46,6 +46,7 @@ #include "netlink.h" #endif #include "fs_context.h" +#include "cached_dir.h" /* * DOS dates from 1980/1/1 through 2107/12/31 @@ -68,6 +69,34 @@ bool enable_negotiate_signing; /* false by default */ unsigned int global_secflags = CIFSSEC_DEF; /* unsigned int ntlmv2_support = 0; */ unsigned int sign_CIFS_PDUs = 1; + +/* + * Global transaction id (XID) information + */ +unsigned int GlobalCurrentXid; /* protected by GlobalMid_Sem */ +unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Sem */ +unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Sem */ +spinlock_t GlobalMid_Lock; /* protects above & list operations on midQ entries */ + +/* + * Global counters, updated atomically + */ +atomic_t sesInfoAllocCount; +atomic_t tconInfoAllocCount; +atomic_t tcpSesNextId; +atomic_t tcpSesAllocCount; +atomic_t tcpSesReconnectCount; +atomic_t tconInfoReconnectCount; + +atomic_t mid_count; +atomic_t buf_alloc_count; +atomic_t small_buf_alloc_count; +#ifdef CONFIG_CIFS_STATS2 +atomic_t total_buf_alloc_count; +atomic_t total_small_buf_alloc_count; +#endif/* STATS2 */ +struct list_head cifs_tcp_ses_list; +spinlock_t cifs_tcp_ses_lock; static const struct super_operations cifs_super_ops; unsigned int CIFSMaxBufSize = CIFS_MAX_MSGSIZE; module_param(CIFSMaxBufSize, uint, 0444); @@ -255,30 +284,13 @@ out_no_root: static void cifs_kill_sb(struct super_block *sb) { struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - struct cifs_tcon *tcon; - struct cached_fid *cfid; - struct rb_root *root = &cifs_sb->tlink_tree; - struct rb_node *node; - struct tcon_link *tlink; /* * We ned to release all dentries for the cached directories * before we kill the sb. */ if (cifs_sb->root) { - for (node = rb_first(root); node; node = rb_next(node)) { - tlink = rb_entry(node, struct tcon_link, tl_rbnode); - tcon = tlink_tcon(tlink); - if (IS_ERR(tcon)) - continue; - cfid = &tcon->crfid; - mutex_lock(&cfid->fid_mutex); - if (cfid->dentry) { - dput(cfid->dentry); - cfid->dentry = NULL; - } - mutex_unlock(&cfid->fid_mutex); - } + close_all_cached_dirs(cifs_sb); /* finally release root dentry */ dput(cifs_sb->root); @@ -681,6 +693,7 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_printf(s, ",acdirmax=%lu", cifs_sb->ctx->acdirmax / HZ); seq_printf(s, ",acregmax=%lu", cifs_sb->ctx->acregmax / HZ); } + seq_printf(s, ",closetimeo=%lu", cifs_sb->ctx->closetimeo / HZ); if (tcon->ses->chan_max > 1) seq_printf(s, ",multichannel,max_channels=%zu", @@ -703,14 +716,17 @@ static void cifs_umount_begin(struct super_block *sb) tcon = cifs_sb_master_tcon(cifs_sb); spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->tc_lock); if ((tcon->tc_count > 1) || (tcon->status == TID_EXITING)) { /* we have other mounts to same share or we have already tried to force umount this and woken up all waiting network requests, nothing to do */ + spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); return; } else if (tcon->tc_count == 1) tcon->status = TID_EXITING; + spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); /* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */ @@ -1232,6 +1248,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, lock_two_nondirectories(target_inode, src_inode); cifs_dbg(FYI, "about to flush pages\n"); + + rc = filemap_write_and_wait_range(src_inode->i_mapping, off, + off + len - 1); + if (rc) + goto out; + /* should we flush first and last page first */ truncate_inode_pages(&target_inode->i_data, 0); @@ -1537,8 +1559,7 @@ cifs_destroy_request_bufs(void) kmem_cache_destroy(cifs_sm_req_cachep); } -static int -cifs_init_mids(void) +static int init_mids(void) { cifs_mid_cachep = kmem_cache_create("cifs_mpx_ids", sizeof(struct mid_q_entry), 0, @@ -1556,8 +1577,7 @@ cifs_init_mids(void) return 0; } -static void -cifs_destroy_mids(void) +static void destroy_mids(void) { mempool_destroy(cifs_mid_poolp); kmem_cache_destroy(cifs_mid_cachep); @@ -1579,11 +1599,11 @@ init_cifs(void) atomic_set(&tcpSesReconnectCount, 0); atomic_set(&tconInfoReconnectCount, 0); - atomic_set(&bufAllocCount, 0); - atomic_set(&smBufAllocCount, 0); + atomic_set(&buf_alloc_count, 0); + atomic_set(&small_buf_alloc_count, 0); #ifdef CONFIG_CIFS_STATS2 - atomic_set(&totBufAllocCount, 0); - atomic_set(&totSmBufAllocCount, 0); + atomic_set(&total_buf_alloc_count, 0); + atomic_set(&total_small_buf_alloc_count, 0); if (slow_rsp_threshold < 1) cifs_dbg(FYI, "slow_response_threshold msgs disabled\n"); else if (slow_rsp_threshold > 32767) @@ -1591,7 +1611,7 @@ init_cifs(void) "slow response threshold set higher than recommended (0 to 32767)\n"); #endif /* CONFIG_CIFS_STATS2 */ - atomic_set(&midCount, 0); + atomic_set(&mid_count, 0); GlobalCurrentXid = 0; GlobalTotalActiveXid = 0; GlobalMaxActiveXid = 0; @@ -1654,7 +1674,7 @@ init_cifs(void) if (rc) goto out_destroy_deferredclose_wq; - rc = cifs_init_mids(); + rc = init_mids(); if (rc) goto out_destroy_inodecache; @@ -1711,7 +1731,7 @@ out_destroy_request_bufs: #endif cifs_destroy_request_bufs(); out_destroy_mids: - cifs_destroy_mids(); + destroy_mids(); out_destroy_inodecache: cifs_destroy_inodecache(); out_destroy_deferredclose_wq: @@ -1747,7 +1767,7 @@ exit_cifs(void) dfs_cache_destroy(); #endif cifs_destroy_request_bufs(); - cifs_destroy_mids(); + destroy_mids(); cifs_destroy_inodecache(); destroy_workqueue(deferredclose_wq); destroy_workqueue(cifsoplockd_wq); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index b17be47a8e59..81f4c15936d0 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -153,6 +153,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 37 -#define CIFS_VERSION "2.37" +#define SMB3_PRODUCT_BUILD 38 +#define CIFS_VERSION "2.38" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index a643c84ff1e9..ae7f571a7dba 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -417,7 +417,7 @@ struct smb_version_operations { int (*close_dir)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); /* calculate a size of SMB message */ - unsigned int (*calc_smb_size)(void *buf, struct TCP_Server_Info *ptcpi); + unsigned int (*calc_smb_size)(void *buf); /* check for STATUS_PENDING and process the response if yes */ bool (*is_status_pending)(char *buf, struct TCP_Server_Info *server); /* check for STATUS_NETWORK_SESSION_EXPIRED */ @@ -557,6 +557,8 @@ struct smb_version_values { #define HEADER_SIZE(server) (server->vals->header_size) #define MAX_HEADER_SIZE(server) (server->vals->max_header_size) +#define HEADER_PREAMBLE_SIZE(server) (server->vals->header_preamble_size) +#define MID_HEADER_SIZE(server) (HEADER_SIZE(server) - 1 - HEADER_PREAMBLE_SIZE(server)) /** * CIFS superblock mount flags (mnt_cifs_flags) to consider when @@ -605,6 +607,7 @@ inc_rfc1001_len(void *buf, int count) struct TCP_Server_Info { struct list_head tcp_ses_list; struct list_head smb_ses_list; + spinlock_t srv_lock; /* protect anything here that is not protected */ __u64 conn_id; /* connection identifier (useful for debugging) */ int srv_count; /* reference counter */ /* 15 character server name + 0x20 16th byte indicating type = srv */ @@ -622,6 +625,7 @@ struct TCP_Server_Info { #endif wait_queue_head_t response_q; wait_queue_head_t request_q; /* if more than maxmpx to srvr must block*/ + spinlock_t mid_lock; /* protect mid queue and it's entries */ struct list_head pending_mid_q; bool noblocksnd; /* use blocking sendmsg */ bool noautotune; /* do not autotune send buf sizes */ @@ -748,6 +752,11 @@ struct TCP_Server_Info { #endif }; +static inline bool is_smb1(struct TCP_Server_Info *server) +{ + return HEADER_PREAMBLE_SIZE(server) != 0; +} + static inline void cifs_server_lock(struct TCP_Server_Info *server) { unsigned int nofs_flag = memalloc_nofs_save(); @@ -1008,6 +1017,7 @@ struct cifs_ses { struct list_head rlist; /* reconnect list */ struct list_head tcon_list; struct cifs_tcon *tcon_ipc; + spinlock_t ses_lock; /* protect anything here that is not protected */ struct mutex session_mutex; struct TCP_Server_Info *server; /* pointer to server info */ int ses_count; /* reference counter */ @@ -1125,42 +1135,6 @@ struct cifs_fattr { u32 cf_cifstag; }; -struct cached_dirent { - struct list_head entry; - char *name; - int namelen; - loff_t pos; - - struct cifs_fattr fattr; -}; - -struct cached_dirents { - bool is_valid:1; - bool is_failed:1; - struct dir_context *ctx; /* - * Only used to make sure we only take entries - * from a single context. Never dereferenced. - */ - struct mutex de_mutex; - int pos; /* Expected ctx->pos */ - struct list_head entries; -}; - -struct cached_fid { - bool is_valid:1; /* Do we have a useable root fid */ - bool file_all_info_is_valid:1; - bool has_lease:1; - unsigned long time; /* jiffies of when lease was taken */ - struct kref refcount; - struct cifs_fid *fid; - struct mutex fid_mutex; - struct cifs_tcon *tcon; - struct dentry *dentry; - struct work_struct lease_break; - struct smb2_file_all_info file_all_info; - struct cached_dirents dirents; -}; - /* * there is one of these for each connection to a resource on a particular * session @@ -1169,6 +1143,7 @@ struct cifs_tcon { struct list_head tcon_list; int tc_count; struct list_head rlist; /* reconnect list */ + spinlock_t tc_lock; /* protect anything here that is not protected */ atomic_t num_local_opens; /* num of all opens including disconnected */ atomic_t num_remote_opens; /* num of all network opens on server */ struct list_head openFileList; @@ -1253,7 +1228,7 @@ struct cifs_tcon { struct fscache_volume *fscache; /* cookie for share */ #endif struct list_head pending_opens; /* list of incomplete opens */ - struct cached_fid crfid; /* Cached root fid */ + struct cached_fid *cfid; /* Cached root fid */ /* BB add field for back pointer to sb struct(s)? */ #ifdef CONFIG_CIFS_DFS_UPCALL struct list_head ulist; /* cache update list */ @@ -1899,33 +1874,78 @@ require use of the stronger protocol */ */ /**************************************************************************** - * Locking notes. All updates to global variables and lists should be - * protected by spinlocks or semaphores. + * Here are all the locks (spinlock, mutex, semaphore) in cifs.ko, arranged according + * to the locking order. i.e. if two locks are to be held together, the lock that + * appears higher in this list needs to be taken before the other. + * + * If you hold a lock that is lower in this list, and you need to take a higher lock + * (or if you think that one of the functions that you're calling may need to), first + * drop the lock you hold, pick up the higher lock, then the lower one. This will + * ensure that locks are picked up only in one direction in the below table + * (top to bottom). * - * Spinlocks - * --------- - * GlobalMid_Lock protects: - * list operations on pending_mid_q and oplockQ - * updates to XID counters, multiplex id and SMB sequence numbers - * list operations on global DnotifyReqList - * updates to ses->status and TCP_Server_Info->tcpStatus - * updates to server->CurrentMid - * tcp_ses_lock protects: - * list operations on tcp and SMB session lists - * tcon->open_file_lock protects the list of open files hanging off the tcon - * inode->open_file_lock protects the openFileList hanging off the inode - * cfile->file_info_lock protects counters and fields in cifs file struct - * f_owner.lock protects certain per file struct operations - * mapping->page_lock protects certain per page operations + * Also, if you expect a function to be called with a lock held, explicitly document + * this in the comments on top of your function definition. * - * Note that the cifs_tcon.open_file_lock should be taken before - * not after the cifsInodeInfo.open_file_lock + * And also, try to keep the critical sections (lock hold time) to be as minimal as + * possible. Blocking / calling other functions with a lock held always increase + * the risk of a possible deadlock. * - * Semaphores - * ---------- - * cifsInodeInfo->lock_sem protects: - * the list of locks held by the inode + * Following this rule will avoid unnecessary deadlocks, which can get really hard to + * debug. Also, any new lock that you introduce, please add to this list in the correct + * order. * + * Please populate this list whenever you introduce new locks in your changes. Or in + * case I've missed some existing locks. Please ensure that it's added in the list + * based on the locking order expected. + * + * ===================================================================================== + * Lock Protects Initialization fn + * ===================================================================================== + * vol_list_lock + * vol_info->ctx_lock vol_info->ctx + * cifs_sb_info->tlink_tree_lock cifs_sb_info->tlink_tree cifs_setup_cifs_sb + * TCP_Server_Info-> TCP_Server_Info cifs_get_tcp_session + * reconnect_mutex + * TCP_Server_Info->srv_mutex TCP_Server_Info cifs_get_tcp_session + * cifs_ses->session_mutex cifs_ses sesInfoAlloc + * cifs_tcon + * cifs_tcon->open_file_lock cifs_tcon->openFileList tconInfoAlloc + * cifs_tcon->pending_opens + * cifs_tcon->stat_lock cifs_tcon->bytes_read tconInfoAlloc + * cifs_tcon->bytes_written + * cifs_tcp_ses_lock cifs_tcp_ses_list sesInfoAlloc + * GlobalMid_Lock GlobalMaxActiveXid init_cifs + * GlobalCurrentXid + * GlobalTotalActiveXid + * TCP_Server_Info->srv_lock (anything in struct not protected by another lock and can change) + * TCP_Server_Info->mid_lock TCP_Server_Info->pending_mid_q cifs_get_tcp_session + * ->CurrentMid + * (any changes in mid_q_entry fields) + * TCP_Server_Info->req_lock TCP_Server_Info->in_flight cifs_get_tcp_session + * ->credits + * ->echo_credits + * ->oplock_credits + * ->reconnect_instance + * cifs_ses->ses_lock (anything that is not protected by another lock and can change) + * cifs_ses->iface_lock cifs_ses->iface_list sesInfoAlloc + * ->iface_count + * ->iface_last_update + * cifs_ses->chan_lock cifs_ses->chans + * ->chans_need_reconnect + * ->chans_in_reconnect + * cifs_tcon->tc_lock (anything that is not protected by another lock and can change) + * cifsInodeInfo->open_file_lock cifsInodeInfo->openFileList cifs_alloc_inode + * cifsInodeInfo->writers_lock cifsInodeInfo->writers cifsInodeInfo_alloc + * cifsInodeInfo->lock_sem cifsInodeInfo->llist cifs_init_once + * ->can_cache_brlcks + * cifsInodeInfo->deferred_lock cifsInodeInfo->deferred_closes cifsInodeInfo_alloc + * cached_fid->fid_mutex cifs_tcon->crfid tconInfoAlloc + * cifsFileInfo->fh_mutex cifsFileInfo cifs_new_fileinfo + * cifsFileInfo->file_info_lock cifsFileInfo->count cifs_new_fileinfo + * ->invalidHandle initiate_cifs_search + * ->oplock_break_cancelled + * cifs_aio_ctx->aio_mutex cifs_aio_ctx cifs_aio_ctx_alloc ****************************************************************************/ #ifdef DECLARE_GLOBALS_HERE @@ -1941,47 +1961,44 @@ require use of the stronger protocol */ * sessions (and from that the tree connections) can be found * by iterating over cifs_tcp_ses_list */ -GLOBAL_EXTERN struct list_head cifs_tcp_ses_list; +extern struct list_head cifs_tcp_ses_list; /* * This lock protects the cifs_tcp_ses_list, the list of smb sessions per * tcp session, and the list of tcon's per smb session. It also protects - * the reference counters for the server, smb session, and tcon. It also - * protects some fields in the TCP_Server_Info struct such as dstaddr. Finally, - * changes to the tcon->tidStatus should be done while holding this lock. + * the reference counters for the server, smb session, and tcon. * generally the locks should be taken in order tcp_ses_lock before * tcon->open_file_lock and that before file->file_info_lock since the * structure order is cifs_socket-->cifs_ses-->cifs_tcon-->cifs_file */ -GLOBAL_EXTERN spinlock_t cifs_tcp_ses_lock; +extern spinlock_t cifs_tcp_ses_lock; /* * Global transaction id (XID) information */ -GLOBAL_EXTERN unsigned int GlobalCurrentXid; /* protected by GlobalMid_Sem */ -GLOBAL_EXTERN unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Sem */ -GLOBAL_EXTERN unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Sem */ -GLOBAL_EXTERN spinlock_t GlobalMid_Lock; /* protects above & list operations */ - /* on midQ entries */ +extern unsigned int GlobalCurrentXid; /* protected by GlobalMid_Sem */ +extern unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Sem */ +extern unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Sem */ +extern spinlock_t GlobalMid_Lock; /* protects above & list operations on midQ entries */ + /* * Global counters, updated atomically */ -GLOBAL_EXTERN atomic_t sesInfoAllocCount; -GLOBAL_EXTERN atomic_t tconInfoAllocCount; -GLOBAL_EXTERN atomic_t tcpSesNextId; -GLOBAL_EXTERN atomic_t tcpSesAllocCount; -GLOBAL_EXTERN atomic_t tcpSesReconnectCount; -GLOBAL_EXTERN atomic_t tconInfoReconnectCount; +extern atomic_t sesInfoAllocCount; +extern atomic_t tconInfoAllocCount; +extern atomic_t tcpSesNextId; +extern atomic_t tcpSesAllocCount; +extern atomic_t tcpSesReconnectCount; +extern atomic_t tconInfoReconnectCount; /* Various Debug counters */ -GLOBAL_EXTERN atomic_t bufAllocCount; /* current number allocated */ +extern atomic_t buf_alloc_count; /* current number allocated */ +extern atomic_t small_buf_alloc_count; #ifdef CONFIG_CIFS_STATS2 -GLOBAL_EXTERN atomic_t totBufAllocCount; /* total allocated over all time */ -GLOBAL_EXTERN atomic_t totSmBufAllocCount; +extern atomic_t total_buf_alloc_count; /* total allocated over all time */ +extern atomic_t total_small_buf_alloc_count; extern unsigned int slow_rsp_threshold; /* number of secs before logging */ #endif -GLOBAL_EXTERN atomic_t smBufAllocCount; -GLOBAL_EXTERN atomic_t midCount; /* Misc globals */ extern bool enable_oplocks; /* enable or disable oplocks */ @@ -1998,6 +2015,7 @@ extern unsigned int cifs_min_rcv; /* min size of big ntwrk buf pool */ extern unsigned int cifs_min_small; /* min size of small buf pool */ extern unsigned int cifs_max_pending; /* MAX requests at once to server*/ extern bool disable_legacy_dialects; /* forbid vers=1.0 and vers=2.0 mounts */ +extern atomic_t mid_count; void cifs_oplock_break(struct work_struct *work); void cifs_queue_oplock_break(struct cifsFileInfo *cfile); @@ -2085,9 +2103,9 @@ static inline bool cifs_is_referral_server(struct cifs_tcon *tcon, return is_tcon_dfs(tcon) || (ref && (ref->flags & DFSREF_REFERRAL_SERVER)); } -static inline u64 cifs_flock_len(struct file_lock *fl) +static inline u64 cifs_flock_len(const struct file_lock *fl) { - return fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; + return (u64)fl->fl_end - fl->fl_start + 1; } static inline size_t ntlmssp_workstation_name_size(const struct cifs_ses *ses) diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index d59aebefa71c..3bc94bcc7177 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -78,12 +78,8 @@ extern char *build_wildcard_path_from_dentry(struct dentry *direntry); extern char *cifs_compose_mount_options(const char *sb_mountdata, const char *fullpath, const struct dfs_info3_param *ref, char **devname); -/* extern void renew_parental_timestamps(struct dentry *direntry);*/ -extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer, - struct TCP_Server_Info *server); -extern void DeleteMidQEntry(struct mid_q_entry *midEntry); -extern void cifs_delete_mid(struct mid_q_entry *mid); -extern void cifs_mid_q_entry_release(struct mid_q_entry *midEntry); +extern void delete_mid(struct mid_q_entry *mid); +extern void release_mid(struct mid_q_entry *mid); extern void cifs_wake_up_task(struct mid_q_entry *mid); extern int cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid); @@ -155,7 +151,7 @@ extern int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool); extern int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, struct cifsFileInfo **ret_file); -extern unsigned int smbCalcSize(void *buf, struct TCP_Server_Info *server); +extern unsigned int smbCalcSize(void *buf); extern int decode_negTokenInit(unsigned char *security_blob, int length, struct TCP_Server_Info *server); extern int cifs_convert_address(struct sockaddr *dst, const char *src, int len); @@ -521,6 +517,7 @@ extern int generate_smb30signingkey(struct cifs_ses *ses, extern int generate_smb311signingkey(struct cifs_ses *ses, struct TCP_Server_Info *server); +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY extern int CIFSSMBCopy(unsigned int xid, struct cifs_tcon *source_tcon, const char *fromName, @@ -551,6 +548,7 @@ extern int CIFSSMBSetPosixACL(const unsigned int xid, struct cifs_tcon *tcon, const struct nls_table *nls_codepage, int remap_special_chars); extern int CIFSGetExtAttr(const unsigned int xid, struct cifs_tcon *tcon, const int netfid, __u64 *pExtAttrBits, __u64 *pMask); +#endif /* CIFS_ALLOW_INSECURE_LEGACY */ extern void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb); extern bool couldbe_mf_symlink(const struct cifs_fattr *fattr); extern int check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, @@ -599,7 +597,6 @@ enum securityEnum cifs_select_sectype(struct TCP_Server_Info *, struct cifs_aio_ctx *cifs_aio_ctx_alloc(void); void cifs_aio_ctx_release(struct kref *refcount); int setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw); -void smb2_cached_lease_break(struct work_struct *work); int cifs_alloc_hash(const char *name, struct crypto_shash **shash, struct sdesc **sdesc); diff --git a/fs/cifs/cifsroot.c b/fs/cifs/cifsroot.c index 9e91a5a40aae..56ec1b233f52 100644 --- a/fs/cifs/cifsroot.c +++ b/fs/cifs/cifsroot.c @@ -59,7 +59,7 @@ static int __init cifs_root_setup(char *line) pr_err("Root-CIFS: UNC path too long\n"); return 1; } - strlcpy(root_dev, line, len); + strscpy(root_dev, line, len); srvaddr = parse_srvaddr(&line[2], s); if (*s) { int n = snprintf(root_opts, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 6371b9eebdad..7aa91e272027 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -29,7 +29,6 @@ #include "cifsproto.h" #include "cifs_unicode.h" #include "cifs_debug.h" -#include "smb2proto.h" #include "fscache.h" #include "smbdirect.h" #ifdef CONFIG_CIFS_DFS_UPCALL @@ -62,52 +61,6 @@ static struct { #define CIFS_NUM_PROT 1 #endif /* CIFS_POSIX */ -/* - * Mark as invalid, all open files on tree connections since they - * were closed when session to server was lost. - */ -void -cifs_mark_open_files_invalid(struct cifs_tcon *tcon) -{ - struct cifsFileInfo *open_file = NULL; - struct list_head *tmp; - struct list_head *tmp1; - - /* only send once per connect */ - spin_lock(&cifs_tcp_ses_lock); - if ((tcon->ses->ses_status != SES_GOOD) || (tcon->status != TID_NEED_RECON)) { - spin_unlock(&cifs_tcp_ses_lock); - return; - } - tcon->status = TID_IN_FILES_INVALIDATE; - spin_unlock(&cifs_tcp_ses_lock); - - /* list all files open on tree connection and mark them invalid */ - spin_lock(&tcon->open_file_lock); - list_for_each_safe(tmp, tmp1, &tcon->openFileList) { - open_file = list_entry(tmp, struct cifsFileInfo, tlist); - open_file->invalidHandle = true; - open_file->oplock_break_cancelled = true; - } - spin_unlock(&tcon->open_file_lock); - - mutex_lock(&tcon->crfid.fid_mutex); - tcon->crfid.is_valid = false; - /* cached handle is not valid, so SMB2_CLOSE won't be sent below */ - close_cached_dir_lease_locked(&tcon->crfid); - memset(tcon->crfid.fid, 0, sizeof(struct cifs_fid)); - mutex_unlock(&tcon->crfid.fid_mutex); - - spin_lock(&cifs_tcp_ses_lock); - if (tcon->status == TID_IN_FILES_INVALIDATE) - tcon->status = TID_NEED_TCON; - spin_unlock(&cifs_tcp_ses_lock); - - /* - * BB Add call to invalidate_inodes(sb) for all superblocks mounted - * to this tcon. - */ -} /* reconnect the socket, tcon, and smb session if needed */ static int @@ -134,18 +87,18 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) * only tree disconnect, open, and write, (and ulogoff which does not * have tcon) are allowed as we start force umount */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->tc_lock); if (tcon->status == TID_EXITING) { if (smb_command != SMB_COM_WRITE_ANDX && smb_command != SMB_COM_OPEN_ANDX && smb_command != SMB_COM_TREE_DISCONNECT) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->tc_lock); cifs_dbg(FYI, "can not send cmd %d while umounting\n", smb_command); return -ENODEV; } } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->tc_lock); retries = server->nr_targets; @@ -165,12 +118,12 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) } /* are we still trying to reconnect? */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus != CifsNeedReconnect) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); break; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); if (retries && --retries) continue; @@ -201,13 +154,13 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) * and the server never sends an answer the socket will be closed * and tcpStatus set to reconnect. */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsNeedReconnect) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); rc = -EHOSTDOWN; goto out; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); /* * need to prevent multiple threads trying to simultaneously @@ -457,52 +410,6 @@ decode_ext_sec_blob(struct cifs_ses *ses, NEGOTIATE_RSP *pSMBr) return 0; } -int -cifs_enable_signing(struct TCP_Server_Info *server, bool mnt_sign_required) -{ - bool srv_sign_required = server->sec_mode & server->vals->signing_required; - bool srv_sign_enabled = server->sec_mode & server->vals->signing_enabled; - bool mnt_sign_enabled = global_secflags & CIFSSEC_MAY_SIGN; - - /* - * Is signing required by mnt options? If not then check - * global_secflags to see if it is there. - */ - if (!mnt_sign_required) - mnt_sign_required = ((global_secflags & CIFSSEC_MUST_SIGN) == - CIFSSEC_MUST_SIGN); - - /* - * If signing is required then it's automatically enabled too, - * otherwise, check to see if the secflags allow it. - */ - mnt_sign_enabled = mnt_sign_required ? mnt_sign_required : - (global_secflags & CIFSSEC_MAY_SIGN); - - /* If server requires signing, does client allow it? */ - if (srv_sign_required) { - if (!mnt_sign_enabled) { - cifs_dbg(VFS, "Server requires signing, but it's disabled in SecurityFlags!\n"); - return -ENOTSUPP; - } - server->sign = true; - } - - /* If client requires signing, does server allow it? */ - if (mnt_sign_required) { - if (!srv_sign_enabled) { - cifs_dbg(VFS, "Server does not support signing!\n"); - return -ENOTSUPP; - } - server->sign = true; - } - - if (cifs_rdma_enabled(server) && server->sign) - cifs_dbg(VFS, "Signing is enabled, and RDMA read/write will be disabled\n"); - - return 0; -} - static bool should_set_ext_sec_flag(enum securityEnum sectype) { @@ -684,7 +591,7 @@ cifs_echo_callback(struct mid_q_entry *mid) struct TCP_Server_Info *server = mid->callback_data; struct cifs_credits credits = { .value = 1, .instance = 0 }; - DeleteMidQEntry(mid); + release_mid(mid); add_credits(server, &credits, CIFS_ECHO_OP); } @@ -1379,184 +1286,6 @@ openRetry: return rc; } -/* - * Discard any remaining data in the current SMB. To do this, we borrow the - * current bigbuf. - */ -int -cifs_discard_remaining_data(struct TCP_Server_Info *server) -{ - unsigned int rfclen = server->pdu_size; - int remaining = rfclen + server->vals->header_preamble_size - - server->total_read; - - while (remaining > 0) { - int length; - - length = cifs_discard_from_socket(server, - min_t(size_t, remaining, - CIFSMaxBufSize + MAX_HEADER_SIZE(server))); - if (length < 0) - return length; - server->total_read += length; - remaining -= length; - } - - return 0; -} - -static int -__cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid, - bool malformed) -{ - int length; - - length = cifs_discard_remaining_data(server); - dequeue_mid(mid, malformed); - mid->resp_buf = server->smallbuf; - server->smallbuf = NULL; - return length; -} - -static int -cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) -{ - struct cifs_readdata *rdata = mid->callback_data; - - return __cifs_readv_discard(server, mid, rdata->result); -} - -int -cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) -{ - int length, len; - unsigned int data_offset, data_len; - struct cifs_readdata *rdata = mid->callback_data; - char *buf = server->smallbuf; - unsigned int buflen = server->pdu_size + - server->vals->header_preamble_size; - bool use_rdma_mr = false; - - cifs_dbg(FYI, "%s: mid=%llu offset=%llu bytes=%u\n", - __func__, mid->mid, rdata->offset, rdata->bytes); - - /* - * read the rest of READ_RSP header (sans Data array), or whatever we - * can if there's not enough data. At this point, we've read down to - * the Mid. - */ - len = min_t(unsigned int, buflen, server->vals->read_rsp_size) - - HEADER_SIZE(server) + 1; - - length = cifs_read_from_socket(server, - buf + HEADER_SIZE(server) - 1, len); - if (length < 0) - return length; - server->total_read += length; - - if (server->ops->is_session_expired && - server->ops->is_session_expired(buf)) { - cifs_reconnect(server, true); - return -1; - } - - if (server->ops->is_status_pending && - server->ops->is_status_pending(buf, server)) { - cifs_discard_remaining_data(server); - return -1; - } - - /* set up first two iov for signature check and to get credits */ - rdata->iov[0].iov_base = buf; - rdata->iov[0].iov_len = server->vals->header_preamble_size; - rdata->iov[1].iov_base = buf + server->vals->header_preamble_size; - rdata->iov[1].iov_len = - server->total_read - server->vals->header_preamble_size; - cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n", - rdata->iov[0].iov_base, rdata->iov[0].iov_len); - cifs_dbg(FYI, "1: iov_base=%p iov_len=%zu\n", - rdata->iov[1].iov_base, rdata->iov[1].iov_len); - - /* Was the SMB read successful? */ - rdata->result = server->ops->map_error(buf, false); - if (rdata->result != 0) { - cifs_dbg(FYI, "%s: server returned error %d\n", - __func__, rdata->result); - /* normal error on read response */ - return __cifs_readv_discard(server, mid, false); - } - - /* Is there enough to get to the rest of the READ_RSP header? */ - if (server->total_read < server->vals->read_rsp_size) { - cifs_dbg(FYI, "%s: server returned short header. got=%u expected=%zu\n", - __func__, server->total_read, - server->vals->read_rsp_size); - rdata->result = -EIO; - return cifs_readv_discard(server, mid); - } - - data_offset = server->ops->read_data_offset(buf) + - server->vals->header_preamble_size; - if (data_offset < server->total_read) { - /* - * win2k8 sometimes sends an offset of 0 when the read - * is beyond the EOF. Treat it as if the data starts just after - * the header. - */ - cifs_dbg(FYI, "%s: data offset (%u) inside read response header\n", - __func__, data_offset); - data_offset = server->total_read; - } else if (data_offset > MAX_CIFS_SMALL_BUFFER_SIZE) { - /* data_offset is beyond the end of smallbuf */ - cifs_dbg(FYI, "%s: data offset (%u) beyond end of smallbuf\n", - __func__, data_offset); - rdata->result = -EIO; - return cifs_readv_discard(server, mid); - } - - cifs_dbg(FYI, "%s: total_read=%u data_offset=%u\n", - __func__, server->total_read, data_offset); - - len = data_offset - server->total_read; - if (len > 0) { - /* read any junk before data into the rest of smallbuf */ - length = cifs_read_from_socket(server, - buf + server->total_read, len); - if (length < 0) - return length; - server->total_read += length; - } - - /* how much data is in the response? */ -#ifdef CONFIG_CIFS_SMB_DIRECT - use_rdma_mr = rdata->mr; -#endif - data_len = server->ops->read_data_length(buf, use_rdma_mr); - if (!use_rdma_mr && (data_offset + data_len > buflen)) { - /* data_len is corrupt -- discard frame */ - rdata->result = -EIO; - return cifs_readv_discard(server, mid); - } - - length = rdata->read_into_pages(server, rdata, data_len); - if (length < 0) - return length; - - server->total_read += length; - - cifs_dbg(FYI, "total_read=%u buflen=%u remaining=%u\n", - server->total_read, buflen, data_len); - - /* discard anything left over */ - if (server->total_read < buflen) - return cifs_readv_discard(server, mid); - - dequeue_mid(mid, false); - mid->resp_buf = server->smallbuf; - server->smallbuf = NULL; - return length; -} - static void cifs_readv_callback(struct mid_q_entry *mid) { @@ -1607,7 +1336,7 @@ cifs_readv_callback(struct mid_q_entry *mid) } queue_work(cifsiod_wq, &rdata->work); - DeleteMidQEntry(mid); + release_mid(mid); add_credits(server, &credits, 0); } @@ -1909,183 +1638,6 @@ CIFSSMBWrite(const unsigned int xid, struct cifs_io_parms *io_parms, return rc; } -void -cifs_writedata_release(struct kref *refcount) -{ - struct cifs_writedata *wdata = container_of(refcount, - struct cifs_writedata, refcount); -#ifdef CONFIG_CIFS_SMB_DIRECT - if (wdata->mr) { - smbd_deregister_mr(wdata->mr); - wdata->mr = NULL; - } -#endif - - if (wdata->cfile) - cifsFileInfo_put(wdata->cfile); - - kvfree(wdata->pages); - kfree(wdata); -} - -/* - * Write failed with a retryable error. Resend the write request. It's also - * possible that the page was redirtied so re-clean the page. - */ -static void -cifs_writev_requeue(struct cifs_writedata *wdata) -{ - int i, rc = 0; - struct inode *inode = d_inode(wdata->cfile->dentry); - struct TCP_Server_Info *server; - unsigned int rest_len; - - server = tlink_tcon(wdata->cfile->tlink)->ses->server; - i = 0; - rest_len = wdata->bytes; - do { - struct cifs_writedata *wdata2; - unsigned int j, nr_pages, wsize, tailsz, cur_len; - - wsize = server->ops->wp_retry_size(inode); - if (wsize < rest_len) { - nr_pages = wsize / PAGE_SIZE; - if (!nr_pages) { - rc = -ENOTSUPP; - break; - } - cur_len = nr_pages * PAGE_SIZE; - tailsz = PAGE_SIZE; - } else { - nr_pages = DIV_ROUND_UP(rest_len, PAGE_SIZE); - cur_len = rest_len; - tailsz = rest_len - (nr_pages - 1) * PAGE_SIZE; - } - - wdata2 = cifs_writedata_alloc(nr_pages, cifs_writev_complete); - if (!wdata2) { - rc = -ENOMEM; - break; - } - - for (j = 0; j < nr_pages; j++) { - wdata2->pages[j] = wdata->pages[i + j]; - lock_page(wdata2->pages[j]); - clear_page_dirty_for_io(wdata2->pages[j]); - } - - wdata2->sync_mode = wdata->sync_mode; - wdata2->nr_pages = nr_pages; - wdata2->offset = page_offset(wdata2->pages[0]); - wdata2->pagesz = PAGE_SIZE; - wdata2->tailsz = tailsz; - wdata2->bytes = cur_len; - - rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, - &wdata2->cfile); - if (!wdata2->cfile) { - cifs_dbg(VFS, "No writable handle to retry writepages rc=%d\n", - rc); - if (!is_retryable_error(rc)) - rc = -EBADF; - } else { - wdata2->pid = wdata2->cfile->pid; - rc = server->ops->async_writev(wdata2, - cifs_writedata_release); - } - - for (j = 0; j < nr_pages; j++) { - unlock_page(wdata2->pages[j]); - if (rc != 0 && !is_retryable_error(rc)) { - SetPageError(wdata2->pages[j]); - end_page_writeback(wdata2->pages[j]); - put_page(wdata2->pages[j]); - } - } - - kref_put(&wdata2->refcount, cifs_writedata_release); - if (rc) { - if (is_retryable_error(rc)) - continue; - i += nr_pages; - break; - } - - rest_len -= cur_len; - i += nr_pages; - } while (i < wdata->nr_pages); - - /* cleanup remaining pages from the original wdata */ - for (; i < wdata->nr_pages; i++) { - SetPageError(wdata->pages[i]); - end_page_writeback(wdata->pages[i]); - put_page(wdata->pages[i]); - } - - if (rc != 0 && !is_retryable_error(rc)) - mapping_set_error(inode->i_mapping, rc); - kref_put(&wdata->refcount, cifs_writedata_release); -} - -void -cifs_writev_complete(struct work_struct *work) -{ - struct cifs_writedata *wdata = container_of(work, - struct cifs_writedata, work); - struct inode *inode = d_inode(wdata->cfile->dentry); - int i = 0; - - if (wdata->result == 0) { - spin_lock(&inode->i_lock); - cifs_update_eof(CIFS_I(inode), wdata->offset, wdata->bytes); - spin_unlock(&inode->i_lock); - cifs_stats_bytes_written(tlink_tcon(wdata->cfile->tlink), - wdata->bytes); - } else if (wdata->sync_mode == WB_SYNC_ALL && wdata->result == -EAGAIN) - return cifs_writev_requeue(wdata); - - for (i = 0; i < wdata->nr_pages; i++) { - struct page *page = wdata->pages[i]; - if (wdata->result == -EAGAIN) - __set_page_dirty_nobuffers(page); - else if (wdata->result < 0) - SetPageError(page); - end_page_writeback(page); - cifs_readpage_to_fscache(inode, page); - put_page(page); - } - if (wdata->result != -EAGAIN) - mapping_set_error(inode->i_mapping, wdata->result); - kref_put(&wdata->refcount, cifs_writedata_release); -} - -struct cifs_writedata * -cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete) -{ - struct page **pages = - kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); - if (pages) - return cifs_writedata_direct_alloc(pages, complete); - - return NULL; -} - -struct cifs_writedata * -cifs_writedata_direct_alloc(struct page **pages, work_func_t complete) -{ - struct cifs_writedata *wdata; - - wdata = kzalloc(sizeof(*wdata), GFP_NOFS); - if (wdata != NULL) { - wdata->pages = pages; - kref_init(&wdata->refcount); - INIT_LIST_HEAD(&wdata->list); - init_completion(&wdata->done); - INIT_WORK(&wdata->work, complete); - } - return wdata; -} - /* * Check the mid_state and signature on received buffer (if any), and queue the * workqueue completion task. @@ -2132,7 +1684,7 @@ cifs_writev_callback(struct mid_q_entry *mid) } queue_work(cifsiod_wq, &wdata->work); - DeleteMidQEntry(mid); + release_mid(mid); add_credits(tcon->ses->server, &credits, 0); } @@ -3660,7 +3212,6 @@ setACLerrorExit: return rc; } -/* BB fix tabs in this function FIXME BB */ int CIFSGetExtAttr(const unsigned int xid, struct cifs_tcon *tcon, const int netfid, __u64 *pExtAttrBits, __u64 *pMask) @@ -3677,7 +3228,7 @@ CIFSGetExtAttr(const unsigned int xid, struct cifs_tcon *tcon, GetExtAttrRetry: rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB, - (void **) &pSMBr); + (void **) &pSMBr); if (rc) return rc; @@ -3723,7 +3274,7 @@ GetExtAttrRetry: __u16 data_offset = le16_to_cpu(pSMBr->t2.DataOffset); __u16 count = le16_to_cpu(pSMBr->t2.DataCount); struct file_chattr_info *pfinfo; - /* BB Do we need a cast or hash here ? */ + if (count != 16) { cifs_dbg(FYI, "Invalid size ret in GetExtAttr\n"); rc = -EIO; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 386bb523c69e..a0a06b6f252b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -119,10 +119,10 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) goto requeue_resolve; } - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); rc = cifs_convert_address((struct sockaddr *)&server->dstaddr, ipaddr, strlen(ipaddr)); - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); kfree(ipaddr); /* rc == 1 means success here */ @@ -205,17 +205,22 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, /* If server is a channel, select the primary channel */ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&pserver->srv_lock); if (!all_channels) { pserver->tcpStatus = CifsNeedReconnect; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&pserver->srv_lock); return; } + spin_unlock(&pserver->srv_lock); + spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { spin_lock(&ses->chan_lock); - for (i = 0; i < ses->chan_count; i++) + for (i = 0; i < ses->chan_count; i++) { + spin_lock(&ses->chans[i].server->srv_lock); ses->chans[i].server->tcpStatus = CifsNeedReconnect; + spin_unlock(&ses->chans[i].server->srv_lock); + } spin_unlock(&ses->chan_lock); } spin_unlock(&cifs_tcp_ses_lock); @@ -252,17 +257,8 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) { /* check if iface is still active */ - if (!cifs_chan_is_iface_active(ses, server)) { - /* - * HACK: drop the lock before calling - * cifs_chan_update_iface to avoid deadlock - */ - ses->ses_count++; - spin_unlock(&cifs_tcp_ses_lock); + if (!cifs_chan_is_iface_active(ses, server)) cifs_chan_update_iface(ses, server); - spin_lock(&cifs_tcp_ses_lock); - ses->ses_count--; - } spin_lock(&ses->chan_lock); if (!mark_smb_session && cifs_chan_needs_reconnect(ses, server)) @@ -323,7 +319,7 @@ cifs_abort_connection(struct TCP_Server_Info *server) /* mark submitted MIDs for retry and issue callback */ INIT_LIST_HEAD(&retry_list); cifs_dbg(FYI, "%s: moving mids to private list\n", __func__); - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); list_for_each_entry_safe(mid, nmid, &server->pending_mid_q, qhead) { kref_get(&mid->refcount); if (mid->mid_state == MID_REQUEST_SUBMITTED) @@ -331,14 +327,14 @@ cifs_abort_connection(struct TCP_Server_Info *server) list_move(&mid->qhead, &retry_list); mid->mid_flags |= MID_DELETED; } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); cifs_server_unlock(server); cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__); list_for_each_entry_safe(mid, nmid, &retry_list, qhead) { list_del_init(&mid->qhead); mid->callback(mid); - cifs_mid_q_entry_release(mid); + release_mid(mid); } if (cifs_rdma_enabled(server)) { @@ -350,11 +346,11 @@ cifs_abort_connection(struct TCP_Server_Info *server) static bool cifs_tcp_ses_needs_reconnect(struct TCP_Server_Info *server, int num_targets) { - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); server->nr_targets = num_targets; if (server->tcpStatus == CifsExiting) { /* the demux thread will exit normally next time through the loop */ - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); wake_up(&server->response_q); return false; } @@ -364,7 +360,7 @@ static bool cifs_tcp_ses_needs_reconnect(struct TCP_Server_Info *server, int num server->hostname); server->tcpStatus = CifsNeedReconnect; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return true; } @@ -414,20 +410,20 @@ static int __cifs_reconnect(struct TCP_Server_Info *server, } else { atomic_inc(&tcpSesReconnectCount); set_credits(server, 1); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus != CifsExiting) server->tcpStatus = CifsNeedNegotiate; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); cifs_swn_reset_server_dstaddr(server); cifs_server_unlock(server); mod_delayed_work(cifsiod_wq, &server->reconnect, 0); } } while (server->tcpStatus == CifsNeedReconnect); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsNeedNegotiate) mod_delayed_work(cifsiod_wq, &server->echo, 0); - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); wake_up(&server->response_q); return rc; @@ -541,10 +537,10 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) */ atomic_inc(&tcpSesReconnectCount); set_credits(server, 1); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus != CifsExiting) server->tcpStatus = CifsNeedNegotiate; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); cifs_swn_reset_server_dstaddr(server); cifs_server_unlock(server); mod_delayed_work(cifsiod_wq, &server->reconnect, 0); @@ -556,11 +552,10 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) dfs_cache_free_tgts(&tl); /* Need to set up echo worker again once connection has been established */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsNeedNegotiate) mod_delayed_work(cifsiod_wq, &server->echo, 0); - - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); wake_up(&server->response_q); return rc; @@ -569,12 +564,12 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) { /* If tcp session is not an dfs connection, then reconnect to last target server */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (!server->is_dfs_conn) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return __cifs_reconnect(server, mark_smb_session); } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); mutex_lock(&server->refpath_lock); if (!server->origin_fullpath || !server->leaf_fullpath) { @@ -670,18 +665,18 @@ server_unresponsive(struct TCP_Server_Info *server) * 65s kernel_recvmsg times out, and we see that we haven't gotten * a response in >60s. */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if ((server->tcpStatus == CifsGood || server->tcpStatus == CifsNeedNegotiate) && (!server->ops->can_echo || server->ops->can_echo(server)) && time_after(jiffies, server->lstrp + 3 * server->echo_interval)) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); cifs_server_dbg(VFS, "has not responded in %lu seconds. Reconnecting...\n", (3 * server->echo_interval) / HZ); cifs_reconnect(server, false); return true; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return false; } @@ -726,18 +721,18 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg) else length = sock_recvmsg(server->ssocket, smb_msg, 0); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsExiting) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return -ESHUTDOWN; } if (server->tcpStatus == CifsNeedReconnect) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); cifs_reconnect(server, false); return -ECONNABORTED; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); if (length == -ERESTARTSYS || length == -EAGAIN || @@ -849,7 +844,7 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed) #ifdef CONFIG_CIFS_STATS2 mid->when_received = jiffies; #endif - spin_lock(&GlobalMid_Lock); + spin_lock(&mid->server->mid_lock); if (!malformed) mid->mid_state = MID_RESPONSE_RECEIVED; else @@ -859,12 +854,12 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed) * function has finished processing it is a bug. */ if (mid->mid_flags & MID_DELETED) { - spin_unlock(&GlobalMid_Lock); + spin_unlock(&mid->server->mid_lock); pr_warn_once("trying to dequeue a deleted mid\n"); } else { list_del_init(&mid->qhead); mid->mid_flags |= MID_DELETED; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&mid->server->mid_lock); } } @@ -876,7 +871,7 @@ smb2_get_credits_from_hdr(char *buffer, struct TCP_Server_Info *server) /* * SMB1 does not use credits. */ - if (server->vals->header_preamble_size) + if (is_smb1(server)) return 0; return le16_to_cpu(shdr->CreditRequest); @@ -903,21 +898,68 @@ handle_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server, dequeue_mid(mid, malformed); } +int +cifs_enable_signing(struct TCP_Server_Info *server, bool mnt_sign_required) +{ + bool srv_sign_required = server->sec_mode & server->vals->signing_required; + bool srv_sign_enabled = server->sec_mode & server->vals->signing_enabled; + bool mnt_sign_enabled; + + /* + * Is signing required by mnt options? If not then check + * global_secflags to see if it is there. + */ + if (!mnt_sign_required) + mnt_sign_required = ((global_secflags & CIFSSEC_MUST_SIGN) == + CIFSSEC_MUST_SIGN); + + /* + * If signing is required then it's automatically enabled too, + * otherwise, check to see if the secflags allow it. + */ + mnt_sign_enabled = mnt_sign_required ? mnt_sign_required : + (global_secflags & CIFSSEC_MAY_SIGN); + + /* If server requires signing, does client allow it? */ + if (srv_sign_required) { + if (!mnt_sign_enabled) { + cifs_dbg(VFS, "Server requires signing, but it's disabled in SecurityFlags!\n"); + return -EOPNOTSUPP; + } + server->sign = true; + } + + /* If client requires signing, does server allow it? */ + if (mnt_sign_required) { + if (!srv_sign_enabled) { + cifs_dbg(VFS, "Server does not support signing!\n"); + return -EOPNOTSUPP; + } + server->sign = true; + } + + if (cifs_rdma_enabled(server) && server->sign) + cifs_dbg(VFS, "Signing is enabled, and RDMA read/write will be disabled\n"); + + return 0; +} + + static void clean_demultiplex_info(struct TCP_Server_Info *server) { int length; /* take it off the list, if it's not already */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); list_del_init(&server->tcp_ses_list); - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); cancel_delayed_work_sync(&server->echo); cancel_delayed_work_sync(&server->resolve); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); server->tcpStatus = CifsExiting; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); wake_up_all(&server->response_q); /* check if we have blocked requests that need to free */ @@ -948,7 +990,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) struct list_head *tmp, *tmp2; INIT_LIST_HEAD(&dispose_list); - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); list_for_each_safe(tmp, tmp2, &server->pending_mid_q) { mid_entry = list_entry(tmp, struct mid_q_entry, qhead); cifs_dbg(FYI, "Clearing mid %llu\n", mid_entry->mid); @@ -957,7 +999,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) list_move(&mid_entry->qhead, &dispose_list); mid_entry->mid_flags |= MID_DELETED; } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); /* now walk dispose list and issue callbacks */ list_for_each_safe(tmp, tmp2, &dispose_list) { @@ -965,7 +1007,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) cifs_dbg(FYI, "Callback mid %llu\n", mid_entry->mid); list_del_init(&mid_entry->qhead); mid_entry->callback(mid_entry); - cifs_mid_q_entry_release(mid_entry); + release_mid(mid_entry); } /* 1/8th of sec is more than enough time for them to exit */ msleep(125); @@ -1008,7 +1050,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) /* make sure this will fit in a large buffer */ if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server) - - server->vals->header_preamble_size) { + HEADER_PREAMBLE_SIZE(server)) { cifs_server_dbg(VFS, "SMB response too long (%u bytes)\n", pdu_length); cifs_reconnect(server, true); return -ECONNABORTED; @@ -1023,8 +1065,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) /* now read the rest */ length = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1, - pdu_length - HEADER_SIZE(server) + 1 - + server->vals->header_preamble_size); + pdu_length - MID_HEADER_SIZE(server)); if (length < 0) return length; @@ -1039,19 +1080,18 @@ int cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid) { char *buf = server->large_buf ? server->bigbuf : server->smallbuf; - int length; + int rc; /* * We know that we received enough to get to the MID as we * checked the pdu_length earlier. Now check to see - * if the rest of the header is OK. We borrow the length - * var for the rest of the loop to avoid a new stack var. + * if the rest of the header is OK. * * 48 bytes is enough to display the header and a little bit * into the payload for debugging purposes. */ - length = server->ops->check_message(buf, server->total_read, server); - if (length != 0) + rc = server->ops->check_message(buf, server->total_read, server); + if (rc) cifs_dump_mem("Bad SMB: ", buf, min_t(unsigned int, server->total_read, 48)); @@ -1066,9 +1106,9 @@ cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid) return -1; if (!mid) - return length; + return rc; - handle_mid(mid, server, buf, length); + handle_mid(mid, server, buf, rc); return 0; } @@ -1081,7 +1121,7 @@ smb2_add_credits_from_hdr(char *buffer, struct TCP_Server_Info *server) /* * SMB1 does not use credits. */ - if (server->vals->header_preamble_size) + if (is_smb1(server)) return; if (shdr->CreditRequest) { @@ -1139,10 +1179,10 @@ cifs_demultiplex_thread(void *p) if (length < 0) continue; - if (server->vals->header_preamble_size == 0) - server->total_read = 0; - else + if (is_smb1(server)) server->total_read = length; + else + server->total_read = 0; /* * The right amount was read from socket - 4 bytes, @@ -1157,8 +1197,7 @@ next_pdu: server->pdu_size = pdu_length; /* make sure we have enough to get to the MID */ - if (server->pdu_size < HEADER_SIZE(server) - 1 - - server->vals->header_preamble_size) { + if (server->pdu_size < MID_HEADER_SIZE(server)) { cifs_server_dbg(VFS, "SMB response too short (%u bytes)\n", server->pdu_size); cifs_reconnect(server, true); @@ -1167,9 +1206,8 @@ next_pdu: /* read down to the MID */ length = cifs_read_from_socket(server, - buf + server->vals->header_preamble_size, - HEADER_SIZE(server) - 1 - - server->vals->header_preamble_size); + buf + HEADER_PREAMBLE_SIZE(server), + MID_HEADER_SIZE(server)); if (length < 0) continue; server->total_read += length; @@ -1205,7 +1243,7 @@ next_pdu: if (length < 0) { for (i = 0; i < num_mids; i++) if (mids[i]) - cifs_mid_q_entry_release(mids[i]); + release_mid(mids[i]); continue; } @@ -1232,7 +1270,7 @@ next_pdu: if (!mids[i]->multiRsp || mids[i]->multiEnd) mids[i]->callback(mids[i]); - cifs_mid_q_entry_release(mids[i]); + release_mid(mids[i]); } else if (server->ops->is_oplock_break && server->ops->is_oplock_break(bufs[i], server)) { @@ -1240,7 +1278,7 @@ next_pdu: cifs_dbg(FYI, "Received oplock break\n"); } else { cifs_server_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n", - atomic_read(&midCount)); + atomic_read(&mid_count)); cifs_dump_mem("Received Data is: ", bufs[i], HEADER_SIZE(server)); smb2_add_credits_from_hdr(bufs[i], server); @@ -1411,6 +1449,7 @@ match_security(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) return true; } +/* this function must be called with srv_lock held */ static int match_server(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) { struct sockaddr *addr = (struct sockaddr *)&ctx->dstaddr; @@ -1471,6 +1510,7 @@ cifs_find_tcp_session(struct smb3_fs_context *ctx) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { + spin_lock(&server->srv_lock); #ifdef CONFIG_CIFS_DFS_UPCALL /* * DFS failover implementation in cifs_reconnect() requires unique tcp sessions for @@ -1478,15 +1518,20 @@ cifs_find_tcp_session(struct smb3_fs_context *ctx) * shares or even links that may connect to same server but having completely * different failover targets. */ - if (server->is_dfs_conn) + if (server->is_dfs_conn) { + spin_unlock(&server->srv_lock); continue; + } #endif /* * Skip ses channels since they're only handled in lower layers * (e.g. cifs_send_recv). */ - if (CIFS_SERVER_IS_CHAN(server) || !match_server(server, ctx)) + if (CIFS_SERVER_IS_CHAN(server) || !match_server(server, ctx)) { + spin_unlock(&server->srv_lock); continue; + } + spin_unlock(&server->srv_lock); ++server->srv_count; spin_unlock(&cifs_tcp_ses_lock); @@ -1534,9 +1579,9 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) else cancel_delayed_work_sync(&server->reconnect); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); server->tcpStatus = CifsExiting; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); cifs_crypto_secmech_release(server); @@ -1595,8 +1640,8 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, if (primary_server) { spin_lock(&cifs_tcp_ses_lock); ++primary_server->srv_count; - tcp_ses->primary_server = primary_server; spin_unlock(&cifs_tcp_ses_lock); + tcp_ses->primary_server = primary_server; } init_waitqueue_head(&tcp_ses->response_q); init_waitqueue_head(&tcp_ses->request_q); @@ -1612,6 +1657,8 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, tcp_ses->lstrp = jiffies; tcp_ses->compress_algorithm = cpu_to_le16(ctx->compression); spin_lock_init(&tcp_ses->req_lock); + spin_lock_init(&tcp_ses->srv_lock); + spin_lock_init(&tcp_ses->mid_lock); INIT_LIST_HEAD(&tcp_ses->tcp_ses_list); INIT_LIST_HEAD(&tcp_ses->smb_ses_list); INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request); @@ -1685,9 +1732,9 @@ smbd_connected: * to the struct since the kernel thread not created yet * no need to spinlock this update of tcpStatus */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcp_ses->srv_lock); tcp_ses->tcpStatus = CifsNeedNegotiate; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcp_ses->srv_lock); if ((ctx->max_credits < 20) || (ctx->max_credits > 60000)) tcp_ses->max_credits = SMB2_MAX_CREDITS_AVAILABLE; @@ -1729,6 +1776,7 @@ out_err: return ERR_PTR(rc); } +/* this function must be called with ses_lock held */ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) { if (ctx->sectype != Unspecified && @@ -1864,10 +1912,17 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { - if (ses->ses_status == SES_EXITING) + spin_lock(&ses->ses_lock); + if (ses->ses_status == SES_EXITING) { + spin_unlock(&ses->ses_lock); continue; - if (!match_session(ses, ctx)) + } + if (!match_session(ses, ctx)) { + spin_unlock(&ses->ses_lock); continue; + } + spin_unlock(&ses->ses_lock); + ++ses->ses_count; spin_unlock(&cifs_tcp_ses_lock); return ses; @@ -1882,26 +1937,28 @@ void cifs_put_smb_ses(struct cifs_ses *ses) unsigned int chan_count; struct TCP_Server_Info *server = ses->server; - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&ses->ses_lock); if (ses->ses_status == SES_EXITING) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); return; } + spin_unlock(&ses->ses_lock); cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count); cifs_dbg(FYI, "%s: ses ipc: %s\n", __func__, ses->tcon_ipc ? ses->tcon_ipc->treeName : "NONE"); + spin_lock(&cifs_tcp_ses_lock); if (--ses->ses_count > 0) { spin_unlock(&cifs_tcp_ses_lock); return; } + spin_unlock(&cifs_tcp_ses_lock); /* ses_count can never go negative */ WARN_ON(ses->ses_count < 0); if (ses->ses_status == SES_GOOD) ses->ses_status = SES_EXITING; - spin_unlock(&cifs_tcp_ses_lock); cifs_free_ipc(ses); @@ -2236,6 +2293,7 @@ get_ses_fail: return ERR_PTR(rc); } +/* this function must be called with tc_lock held */ static int match_tcon(struct cifs_tcon *tcon, struct smb3_fs_context *ctx) { if (tcon->status == TID_EXITING) @@ -2258,16 +2316,17 @@ static int match_tcon(struct cifs_tcon *tcon, struct smb3_fs_context *ctx) static struct cifs_tcon * cifs_find_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) { - struct list_head *tmp; struct cifs_tcon *tcon; spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &ses->tcon_list) { - tcon = list_entry(tmp, struct cifs_tcon, tcon_list); - - if (!match_tcon(tcon, ctx)) + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { + spin_lock(&tcon->tc_lock); + if (!match_tcon(tcon, ctx)) { + spin_unlock(&tcon->tc_lock); continue; + } ++tcon->tc_count; + spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); return tcon; } @@ -2619,6 +2678,8 @@ compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data) return 0; if (old->ctx->acdirmax != new->ctx->acdirmax) return 0; + if (old->ctx->closetimeo != new->ctx->closetimeo) + return 0; return 1; } @@ -2644,7 +2705,7 @@ match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data) int cifs_match_super(struct super_block *sb, void *data) { - struct cifs_mnt_data *mnt_data = (struct cifs_mnt_data *)data; + struct cifs_mnt_data *mnt_data = data; struct smb3_fs_context *ctx; struct cifs_sb_info *cifs_sb; struct TCP_Server_Info *tcp_srv; @@ -2667,6 +2728,9 @@ cifs_match_super(struct super_block *sb, void *data) ctx = mnt_data->ctx; + spin_lock(&tcp_srv->srv_lock); + spin_lock(&ses->ses_lock); + spin_lock(&tcon->tc_lock); if (!match_server(tcp_srv, ctx) || !match_session(ses, ctx) || !match_tcon(tcon, ctx) || @@ -2677,6 +2741,10 @@ cifs_match_super(struct super_block *sb, void *data) rc = compare_mount_options(sb, mnt_data); out: + spin_unlock(&tcon->tc_lock); + spin_unlock(&ses->ses_lock); + spin_unlock(&tcp_srv->srv_lock); + spin_unlock(&cifs_tcp_ses_lock); cifs_put_tlink(tlink); return rc; @@ -2954,6 +3022,7 @@ ip_connect(struct TCP_Server_Info *server) return generic_ip_connect(server); } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) { @@ -3059,6 +3128,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon, } } } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb) { @@ -3175,6 +3245,7 @@ static int mount_get_conns(struct mount_ctx *mnt_ctx) if (tcon->posix_extensions) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* tell server which Unix caps we support */ if (cap_unix(tcon->ses)) { /* @@ -3182,16 +3253,17 @@ static int mount_get_conns(struct mount_ctx *mnt_ctx) * for just this mount. */ reset_cifs_unix_caps(xid, tcon, cifs_sb, ctx); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->ses->server->srv_lock); if ((tcon->ses->server->tcpStatus == CifsNeedReconnect) && (le64_to_cpu(tcon->fsUnixInfo.Capability) & CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->ses->server->srv_lock); rc = -EACCES; goto out; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->ses->server->srv_lock); } else +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ tcon->unix_ext = 0; /* server does not support them */ /* do not care if a following call succeed - informational */ @@ -3273,9 +3345,9 @@ static int mount_get_dfs_conns(struct mount_ctx *mnt_ctx) rc = mount_get_conns(mnt_ctx); if (mnt_ctx->server) { cifs_dbg(FYI, "%s: marking tcp session as a dfs connection\n", __func__); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&mnt_ctx->server->srv_lock); mnt_ctx->server->is_dfs_conn = true; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&mnt_ctx->server->srv_lock); } return rc; } @@ -3919,7 +3991,7 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses, } bcc_ptr += length + 1; bytes_left -= (length + 1); - strlcpy(tcon->treeName, tree, sizeof(tcon->treeName)); + strscpy(tcon->treeName, tree, sizeof(tcon->treeName)); /* mostly informational -- no need to fail on error here */ kfree(tcon->nativeFileSystem); @@ -3990,28 +4062,28 @@ cifs_negotiate_protocol(const unsigned int xid, struct cifs_ses *ses, return -ENOSYS; /* only send once per connect */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (!server->ops->need_neg(server) || server->tcpStatus != CifsNeedNegotiate) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return 0; } server->tcpStatus = CifsInNegotiate; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); rc = server->ops->negotiate(xid, ses, server); if (rc == 0) { - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsInNegotiate) server->tcpStatus = CifsGood; else rc = -EHOSTDOWN; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); } else { - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsInNegotiate) server->tcpStatus = CifsNeedNegotiate; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); } return rc; @@ -4027,7 +4099,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr; bool is_binding = false; - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&ses->ses_lock); if (server->dstaddr.ss_family == AF_INET6) scnprintf(ses->ip_addr, sizeof(ses->ip_addr), "%pI6", &addr6->sin6_addr); else @@ -4036,7 +4108,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, if (ses->ses_status != SES_GOOD && ses->ses_status != SES_NEW && ses->ses_status != SES_NEED_RECON) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); return 0; } @@ -4045,7 +4117,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, if (CIFS_ALL_CHANS_GOOD(ses) || cifs_chan_in_reconnect(ses, server)) { spin_unlock(&ses->chan_lock); - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); return 0; } is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); @@ -4054,7 +4126,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, if (!is_binding) ses->ses_status = SES_IN_SETUP; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); if (!is_binding) { ses->capabilities = server->capabilities; @@ -4078,22 +4150,22 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, if (rc) { cifs_server_dbg(VFS, "Send error in SessSetup = %d\n", rc); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&ses->ses_lock); if (ses->ses_status == SES_IN_SETUP) ses->ses_status = SES_NEED_RECON; spin_lock(&ses->chan_lock); cifs_chan_clear_in_reconnect(ses, server); spin_unlock(&ses->chan_lock); - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); } else { - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&ses->ses_lock); if (ses->ses_status == SES_IN_SETUP) ses->ses_status = SES_GOOD; spin_lock(&ses->chan_lock); cifs_chan_clear_in_reconnect(ses, server); cifs_chan_clear_need_reconnect(ses, server); spin_unlock(&ses->chan_lock); - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); } return rc; @@ -4167,8 +4239,10 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) goto out; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(ses)) reset_cifs_unix_caps(0, tcon, NULL, ctx); +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ out: kfree(ctx->username); @@ -4557,15 +4631,15 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru struct dfs_info3_param ref = {0}; /* only send once per connect */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->tc_lock); if (tcon->ses->ses_status != SES_GOOD || (tcon->status != TID_NEW && tcon->status != TID_NEED_TCON)) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->tc_lock); return 0; } tcon->status = TID_IN_TCON; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->tc_lock); tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL); if (!tree) { @@ -4604,15 +4678,15 @@ out: cifs_put_tcp_super(sb); if (rc) { - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->tc_lock); if (tcon->status == TID_IN_TCON) tcon->status = TID_NEED_TCON; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->tc_lock); } else { - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->tc_lock); if (tcon->status == TID_IN_TCON) tcon->status = TID_GOOD; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->tc_lock); tcon->need_reconnect = false; } @@ -4625,28 +4699,28 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru const struct smb_version_operations *ops = tcon->ses->server->ops; /* only send once per connect */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->tc_lock); if (tcon->ses->ses_status != SES_GOOD || (tcon->status != TID_NEW && tcon->status != TID_NEED_TCON)) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->tc_lock); return 0; } tcon->status = TID_IN_TCON; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->tc_lock); rc = ops->tree_connect(xid, tcon->ses, tcon->treeName, tcon, nlsc); if (rc) { - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->tc_lock); if (tcon->status == TID_IN_TCON) tcon->status = TID_NEED_TCON; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->tc_lock); } else { - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->tc_lock); if (tcon->status == TID_IN_TCON) tcon->status = TID_GOOD; - spin_unlock(&cifs_tcp_ses_lock); tcon->need_reconnect = false; + spin_unlock(&tcon->tc_lock); } return rc; diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 34a8f3baed5e..a9b6c3eba6de 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1526,15 +1526,21 @@ static void refresh_mounts(struct cifs_ses **sessions) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - if (!server->is_dfs_conn) + spin_lock(&server->srv_lock); + if (!server->is_dfs_conn) { + spin_unlock(&server->srv_lock); continue; + } + spin_unlock(&server->srv_lock); list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { + spin_lock(&tcon->tc_lock); if (!tcon->ipc && !tcon->need_reconnect) { tcon->tc_count++; list_add_tail(&tcon->ulist, &tcons); } + spin_unlock(&tcon->tc_lock); } } } diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index ce9b22aecfba..08f7392716e2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -193,6 +193,7 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, return PTR_ERR(full_path); } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { @@ -261,6 +262,7 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, * rare for path not covered on files) */ } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ desired_access = 0; if (OPEN_FMODE(oflags) & FMODE_READ) @@ -316,6 +318,7 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, goto out; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* * If Open reported that we actually created a file then we now have to * set the mode if possible. @@ -357,6 +360,9 @@ cifs_create_get_file_info: rc = cifs_get_inode_info_unix(&newinode, full_path, inode->i_sb, xid); else { +#else + { +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ /* TODO: Add support for calling POSIX query info here, but passing in fid */ rc = cifs_get_inode_info(&newinode, full_path, buf, inode->i_sb, xid, fid); @@ -377,7 +383,9 @@ cifs_create_get_file_info: } } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY cifs_create_set_dentry: +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ if (rc != 0) { cifs_dbg(FYI, "Create worked, get_inode_info failed rc = %d\n", rc); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index e64cda7a7610..fa738adc031f 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -26,6 +26,7 @@ #include "cifspdu.h" #include "cifsglob.h" #include "cifsproto.h" +#include "smb2proto.h" #include "cifs_unicode.h" #include "cifs_debug.h" #include "cifs_fs_sb.h" @@ -33,6 +34,48 @@ #include "smbdirect.h" #include "fs_context.h" #include "cifs_ioctl.h" +#include "cached_dir.h" + +/* + * Mark as invalid, all open files on tree connections since they + * were closed when session to server was lost. + */ +void +cifs_mark_open_files_invalid(struct cifs_tcon *tcon) +{ + struct cifsFileInfo *open_file = NULL; + struct list_head *tmp; + struct list_head *tmp1; + + /* only send once per connect */ + spin_lock(&tcon->ses->ses_lock); + if ((tcon->ses->ses_status != SES_GOOD) || (tcon->status != TID_NEED_RECON)) { + spin_unlock(&tcon->ses->ses_lock); + return; + } + tcon->status = TID_IN_FILES_INVALIDATE; + spin_unlock(&tcon->ses->ses_lock); + + /* list all files open on tree connection and mark them invalid */ + spin_lock(&tcon->open_file_lock); + list_for_each_safe(tmp, tmp1, &tcon->openFileList) { + open_file = list_entry(tmp, struct cifsFileInfo, tlist); + open_file->invalidHandle = true; + open_file->oplock_break_cancelled = true; + } + spin_unlock(&tcon->open_file_lock); + + invalidate_all_cached_dirs(tcon); + spin_lock(&tcon->tc_lock); + if (tcon->status == TID_IN_FILES_INVALIDATE) + tcon->status = TID_NEED_TCON; + spin_unlock(&tcon->tc_lock); + + /* + * BB Add call to invalidate_inodes(sb) for all superblocks mounted + * to this tcon. + */ +} static inline int cifs_convert_flags(unsigned int flags) { @@ -52,6 +95,7 @@ static inline int cifs_convert_flags(unsigned int flags) FILE_READ_DATA); } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY static u32 cifs_posix_convert_flags(unsigned int flags) { u32 posix_flags = 0; @@ -85,6 +129,7 @@ static u32 cifs_posix_convert_flags(unsigned int flags) return posix_flags; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ static inline int cifs_get_disposition(unsigned int flags) { @@ -100,6 +145,7 @@ static inline int cifs_get_disposition(unsigned int flags) return FILE_OPEN; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY int cifs_posix_open(const char *full_path, struct inode **pinode, struct super_block *sb, int mode, unsigned int f_flags, __u32 *poplock, __u16 *pnetfid, unsigned int xid) @@ -161,6 +207,7 @@ posix_open_ret: kfree(presp_data); return rc; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, @@ -579,6 +626,7 @@ int cifs_open(struct inode *inode, struct file *file) else oplock = 0; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (!tcon->broken_posix_open && tcon->unix_ext && cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { @@ -603,6 +651,7 @@ int cifs_open(struct inode *inode, struct file *file) * or DFS errors. */ } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &fid); @@ -630,6 +679,7 @@ int cifs_open(struct inode *inode, struct file *file) goto out; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if ((oplock & CIFS_CREATE_ACTION) && !posix_open_ok && tcon->unix_ext) { /* * Time to set mode which we can not set earlier due to @@ -647,6 +697,7 @@ int cifs_open(struct inode *inode, struct file *file) CIFSSMBUnixSetFileInfo(xid, tcon, &args, fid.netfid, cfile->pid); } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ use_cache: fscache_use_cookie(cifs_inode_cookie(file_inode(file)), @@ -664,7 +715,9 @@ out: return rc; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY static int cifs_push_posix_locks(struct cifsFileInfo *cfile); +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ /* * Try to reacquire byte range locks that were released when session @@ -673,10 +726,12 @@ static int cifs_push_posix_locks(struct cifsFileInfo *cfile); static int cifs_relock_file(struct cifsFileInfo *cfile) { - struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb); struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry)); struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); int rc = 0; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY + struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb); +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ down_read_nested(&cinode->lock_sem, SINGLE_DEPTH_NESTING); if (cinode->can_cache_brlcks) { @@ -685,11 +740,13 @@ cifs_relock_file(struct cifsFileInfo *cfile) return rc; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) rc = cifs_push_posix_locks(cfile); else +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ rc = tcon->ses->server->ops->push_mand_locks(cfile); up_read(&cinode->lock_sem); @@ -750,6 +807,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) else oplock = 0; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tcon->unix_ext && cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { @@ -773,6 +831,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) * in the reconnect path it is important to retry hard */ } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ desired_access = cifs_convert_flags(cfile->f_flags); @@ -817,7 +876,9 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) goto reopen_error_exit; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY reopen_success: +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ cfile->invalidHandle = false; mutex_unlock(&cfile->fh_mutex); cinode = CIFS_I(inode); @@ -903,12 +964,12 @@ int cifs_close(struct inode *inode, struct file *file) * So, Increase the ref count to avoid use-after-free. */ if (!mod_delayed_work(deferredclose_wq, - &cfile->deferred, cifs_sb->ctx->acregmax)) + &cfile->deferred, cifs_sb->ctx->closetimeo)) cifsFileInfo_get(cfile); } else { /* Deferred close for files */ queue_delayed_work(deferredclose_wq, - &cfile->deferred, cifs_sb->ctx->acregmax); + &cfile->deferred, cifs_sb->ctx->closetimeo); cfile->deferred_close_scheduled = true; spin_unlock(&cinode->deferred_lock); return 0; @@ -928,9 +989,7 @@ int cifs_close(struct inode *inode, struct file *file) void cifs_reopen_persistent_handles(struct cifs_tcon *tcon) { - struct cifsFileInfo *open_file; - struct list_head *tmp; - struct list_head *tmp1; + struct cifsFileInfo *open_file, *tmp; struct list_head tmp_list; if (!tcon->use_persistent || !tcon->need_reopen_files) @@ -943,8 +1002,7 @@ cifs_reopen_persistent_handles(struct cifs_tcon *tcon) /* list all files open on tree connection, reopen resilient handles */ spin_lock(&tcon->open_file_lock); - list_for_each(tmp, &tcon->openFileList) { - open_file = list_entry(tmp, struct cifsFileInfo, tlist); + list_for_each_entry(open_file, &tcon->openFileList, tlist) { if (!open_file->invalidHandle) continue; cifsFileInfo_get(open_file); @@ -952,8 +1010,7 @@ cifs_reopen_persistent_handles(struct cifs_tcon *tcon) } spin_unlock(&tcon->open_file_lock); - list_for_each_safe(tmp, tmp1, &tmp_list) { - open_file = list_entry(tmp, struct cifsFileInfo, rlist); + list_for_each_entry_safe(open_file, tmp, &tmp_list, rlist) { if (cifs_reopen_file(open_file, false /* do not flush */)) tcon->need_reopen_files = true; list_del_init(&open_file->rlist); @@ -1196,6 +1253,7 @@ try_again: return rc; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* * Check if there is another lock that prevents us to set the lock (posix * style). If such a lock exists, update the flock structure with its @@ -1334,6 +1392,7 @@ hash_lockowner(fl_owner_t owner) { return cifs_lock_secret ^ hash32_ptr((const void *)owner); } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ struct lock_to_push { struct list_head llist; @@ -1344,6 +1403,7 @@ struct lock_to_push { __u8 type; }; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY static int cifs_push_posix_locks(struct cifsFileInfo *cfile) { @@ -1431,14 +1491,17 @@ err_out: } goto out; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ static int cifs_push_locks(struct cifsFileInfo *cfile) { - struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb); struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry)); struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); int rc = 0; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY + struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb); +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ /* we are going to update can_cache_brlcks here - need a write access */ cifs_down_write(&cinode->lock_sem); @@ -1447,11 +1510,13 @@ cifs_push_locks(struct cifsFileInfo *cfile) return rc; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) rc = cifs_push_posix_locks(cfile); else +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ rc = tcon->ses->server->ops->push_mand_locks(cfile); cinode->can_cache_brlcks = false; @@ -1515,6 +1580,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type, struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY __u16 netfid = cfile->fid.netfid; if (posix_lck) { @@ -1534,6 +1600,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type, posix_lock_type, wait_flag); return rc; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ rc = cifs_lock_test(cfile, flock->fl_start, length, type, flock); if (!rc) @@ -1594,6 +1661,7 @@ cifs_free_llist(struct list_head *llist) } } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY int cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, unsigned int xid) @@ -1706,6 +1774,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, kfree(buf); return rc; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ static int cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, @@ -1719,6 +1788,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, struct TCP_Server_Info *server = tcon->ses->server; struct inode *inode = d_inode(cfile->dentry); +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (posix_lck) { int posix_lock_type; @@ -1740,7 +1810,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, NULL, posix_lock_type, wait_flag); goto out; } - +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ if (lock) { struct cifsLockInfo *lock; @@ -1861,9 +1931,9 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock) rc = -EACCES; xid = get_xid(); - cifs_dbg(FYI, "Lock parm: 0x%x flockflags: 0x%x flocktype: 0x%x start: %lld end: %lld\n", - cmd, flock->fl_flags, flock->fl_type, - flock->fl_start, flock->fl_end); + cifs_dbg(FYI, "%s: %pD2 cmd=0x%x type=0x%x flags=0x%x r=%lld:%lld\n", __func__, file, cmd, + flock->fl_flags, flock->fl_type, (long long)flock->fl_start, + (long long)flock->fl_end); cfile = (struct cifsFileInfo *)file->private_data; tcon = tlink_tcon(cfile->tlink); @@ -2204,6 +2274,185 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, return -ENOENT; } +void +cifs_writedata_release(struct kref *refcount) +{ + struct cifs_writedata *wdata = container_of(refcount, + struct cifs_writedata, refcount); +#ifdef CONFIG_CIFS_SMB_DIRECT + if (wdata->mr) { + smbd_deregister_mr(wdata->mr); + wdata->mr = NULL; + } +#endif + + if (wdata->cfile) + cifsFileInfo_put(wdata->cfile); + + kvfree(wdata->pages); + kfree(wdata); +} + +/* + * Write failed with a retryable error. Resend the write request. It's also + * possible that the page was redirtied so re-clean the page. + */ +static void +cifs_writev_requeue(struct cifs_writedata *wdata) +{ + int i, rc = 0; + struct inode *inode = d_inode(wdata->cfile->dentry); + struct TCP_Server_Info *server; + unsigned int rest_len; + + server = tlink_tcon(wdata->cfile->tlink)->ses->server; + i = 0; + rest_len = wdata->bytes; + do { + struct cifs_writedata *wdata2; + unsigned int j, nr_pages, wsize, tailsz, cur_len; + + wsize = server->ops->wp_retry_size(inode); + if (wsize < rest_len) { + nr_pages = wsize / PAGE_SIZE; + if (!nr_pages) { + rc = -EOPNOTSUPP; + break; + } + cur_len = nr_pages * PAGE_SIZE; + tailsz = PAGE_SIZE; + } else { + nr_pages = DIV_ROUND_UP(rest_len, PAGE_SIZE); + cur_len = rest_len; + tailsz = rest_len - (nr_pages - 1) * PAGE_SIZE; + } + + wdata2 = cifs_writedata_alloc(nr_pages, cifs_writev_complete); + if (!wdata2) { + rc = -ENOMEM; + break; + } + + for (j = 0; j < nr_pages; j++) { + wdata2->pages[j] = wdata->pages[i + j]; + lock_page(wdata2->pages[j]); + clear_page_dirty_for_io(wdata2->pages[j]); + } + + wdata2->sync_mode = wdata->sync_mode; + wdata2->nr_pages = nr_pages; + wdata2->offset = page_offset(wdata2->pages[0]); + wdata2->pagesz = PAGE_SIZE; + wdata2->tailsz = tailsz; + wdata2->bytes = cur_len; + + rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, + &wdata2->cfile); + if (!wdata2->cfile) { + cifs_dbg(VFS, "No writable handle to retry writepages rc=%d\n", + rc); + if (!is_retryable_error(rc)) + rc = -EBADF; + } else { + wdata2->pid = wdata2->cfile->pid; + rc = server->ops->async_writev(wdata2, + cifs_writedata_release); + } + + for (j = 0; j < nr_pages; j++) { + unlock_page(wdata2->pages[j]); + if (rc != 0 && !is_retryable_error(rc)) { + SetPageError(wdata2->pages[j]); + end_page_writeback(wdata2->pages[j]); + put_page(wdata2->pages[j]); + } + } + + kref_put(&wdata2->refcount, cifs_writedata_release); + if (rc) { + if (is_retryable_error(rc)) + continue; + i += nr_pages; + break; + } + + rest_len -= cur_len; + i += nr_pages; + } while (i < wdata->nr_pages); + + /* cleanup remaining pages from the original wdata */ + for (; i < wdata->nr_pages; i++) { + SetPageError(wdata->pages[i]); + end_page_writeback(wdata->pages[i]); + put_page(wdata->pages[i]); + } + + if (rc != 0 && !is_retryable_error(rc)) + mapping_set_error(inode->i_mapping, rc); + kref_put(&wdata->refcount, cifs_writedata_release); +} + +void +cifs_writev_complete(struct work_struct *work) +{ + struct cifs_writedata *wdata = container_of(work, + struct cifs_writedata, work); + struct inode *inode = d_inode(wdata->cfile->dentry); + int i = 0; + + if (wdata->result == 0) { + spin_lock(&inode->i_lock); + cifs_update_eof(CIFS_I(inode), wdata->offset, wdata->bytes); + spin_unlock(&inode->i_lock); + cifs_stats_bytes_written(tlink_tcon(wdata->cfile->tlink), + wdata->bytes); + } else if (wdata->sync_mode == WB_SYNC_ALL && wdata->result == -EAGAIN) + return cifs_writev_requeue(wdata); + + for (i = 0; i < wdata->nr_pages; i++) { + struct page *page = wdata->pages[i]; + + if (wdata->result == -EAGAIN) + __set_page_dirty_nobuffers(page); + else if (wdata->result < 0) + SetPageError(page); + end_page_writeback(page); + cifs_readpage_to_fscache(inode, page); + put_page(page); + } + if (wdata->result != -EAGAIN) + mapping_set_error(inode->i_mapping, wdata->result); + kref_put(&wdata->refcount, cifs_writedata_release); +} + +struct cifs_writedata * +cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete) +{ + struct page **pages = + kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); + if (pages) + return cifs_writedata_direct_alloc(pages, complete); + + return NULL; +} + +struct cifs_writedata * +cifs_writedata_direct_alloc(struct page **pages, work_func_t complete) +{ + struct cifs_writedata *wdata; + + wdata = kzalloc(sizeof(*wdata), GFP_NOFS); + if (wdata != NULL) { + wdata->pages = pages; + kref_init(&wdata->refcount); + INIT_LIST_HEAD(&wdata->list); + init_completion(&wdata->done); + INIT_WORK(&wdata->work, complete); + } + return wdata; +} + + static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) { struct address_space *mapping = page->mapping; @@ -3022,7 +3271,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, if (ctx->direct_io) { ssize_t result; - result = iov_iter_get_pages_alloc( + result = iov_iter_get_pages_alloc2( from, &pagevec, cur_len, &start); if (result < 0) { cifs_dbg(VFS, @@ -3036,7 +3285,6 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, break; } cur_len = (size_t)result; - iov_iter_advance(from, cur_len); nr_pages = (cur_len + start + PAGE_SIZE - 1) / PAGE_SIZE; @@ -3758,7 +4006,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, if (ctx->direct_io) { ssize_t result; - result = iov_iter_get_pages_alloc( + result = iov_iter_get_pages_alloc2( &direct_iov, &pagevec, cur_len, &start); if (result < 0) { @@ -3774,7 +4022,6 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, break; } cur_len = (size_t)result; - iov_iter_advance(&direct_iov, cur_len); rdata = cifs_readdata_direct_alloc( pagevec, cifs_uncached_readv_complete); @@ -4004,7 +4251,7 @@ static ssize_t __cifs_readv( if (!is_sync_kiocb(iocb)) ctx->iocb = iocb; - if (iter_is_iovec(to)) + if (user_backed_iter(to)) ctx->should_dirty = true; if (direct) { @@ -4459,10 +4706,11 @@ static void cifs_readahead(struct readahead_control *ractl) * TODO: Send a whole batch of pages to be read * by the cache. */ - page = readahead_page(ractl); - last_batch_size = 1 << thp_order(page); + struct folio *folio = readahead_folio(ractl); + + last_batch_size = folio_nr_pages(folio); if (cifs_readpage_from_fscache(ractl->mapping->host, - page) < 0) { + &folio->page) < 0) { /* * TODO: Deal with cache read failure * here, but for the moment, delegate @@ -4470,7 +4718,7 @@ static void cifs_readahead(struct readahead_control *ractl) */ caching = false; } - unlock_page(page); + folio_unlock(folio); next_cached++; cache_nr_pages--; if (cache_nr_pages == 0) @@ -4811,8 +5059,6 @@ void cifs_oplock_break(struct work_struct *work) struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; bool purge_cache = false; - bool is_deferred = false; - struct cifs_deferred_close *dclose; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -4849,22 +5095,6 @@ void cifs_oplock_break(struct work_struct *work) oplock_break_ack: /* - * When oplock break is received and there are no active - * file handles but cached, then schedule deferred close immediately. - * So, new open will not use cached handle. - */ - spin_lock(&CIFS_I(inode)->deferred_lock); - is_deferred = cifs_is_deferred_close(cfile, &dclose); - spin_unlock(&CIFS_I(inode)->deferred_lock); - if (is_deferred && - cfile->deferred_close_scheduled && - delayed_work_pending(&cfile->deferred)) { - if (cancel_delayed_work(&cfile->deferred)) { - _cifsFileInfo_put(cfile, false, false); - goto oplock_break_done; - } - } - /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do * not bother sending an oplock release if session to server still is @@ -4875,7 +5105,7 @@ oplock_break_ack: cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } -oplock_break_done: + _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 8dc0d923ef6a..0e13dec86b25 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -147,6 +147,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_u32("actimeo", Opt_actimeo), fsparam_u32("acdirmax", Opt_acdirmax), fsparam_u32("acregmax", Opt_acregmax), + fsparam_u32("closetimeo", Opt_closetimeo), fsparam_u32("echo_interval", Opt_echo_interval), fsparam_u32("max_credits", Opt_max_credits), fsparam_u32("handletimeout", Opt_handletimeout), @@ -1074,6 +1075,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, } ctx->acdirmax = ctx->acregmax = HZ * result.uint_32; break; + case Opt_closetimeo: + ctx->closetimeo = HZ * result.uint_32; + if (ctx->closetimeo > SMB3_MAX_DCLOSETIMEO) { + cifs_errorf(fc, "closetimeo too large\n"); + goto cifs_parse_mount_err; + } + break; case Opt_echo_interval: ctx->echo_interval = result.uint_32; break; @@ -1521,6 +1529,7 @@ int smb3_init_fs_context(struct fs_context *fc) ctx->acregmax = CIFS_DEF_ACTIMEO; ctx->acdirmax = CIFS_DEF_ACTIMEO; + ctx->closetimeo = SMB3_DEF_DCLOSETIMEO; /* Most clients set timeout to 0, allows server to use its default */ ctx->handle_timeout = 0; /* See MS-SMB2 spec section 2.2.14.2.12 */ diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h index 5f093cb7e9b9..bbaee4c2281f 100644 --- a/fs/cifs/fs_context.h +++ b/fs/cifs/fs_context.h @@ -125,6 +125,7 @@ enum cifs_param { Opt_actimeo, Opt_acdirmax, Opt_acregmax, + Opt_closetimeo, Opt_echo_interval, Opt_max_credits, Opt_snapshot, @@ -247,6 +248,8 @@ struct smb3_fs_context { /* attribute cache timemout for files and directories in jiffies */ unsigned long acregmax; unsigned long acdirmax; + /* timeout for deferred close of files in jiffies */ + unsigned long closetimeo; struct smb_version_operations *ops; struct smb_version_values *vals; char *prepath; @@ -279,4 +282,9 @@ static inline struct smb3_fs_context *smb3_fc2context(const struct fs_context *f extern int smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx); extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb); +/* + * max deferred close timeout (jiffies) - 2^30 + */ +#define SMB3_MAX_DCLOSETIMEO (1 << 30) +#define SMB3_DEF_DCLOSETIMEO (5 * HZ) /* Can increase later, other clients use larger */ #endif diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h index aa3b941a5555..67b601041f0a 100644 --- a/fs/cifs/fscache.h +++ b/fs/cifs/fscache.h @@ -108,17 +108,6 @@ static inline void cifs_readpage_to_fscache(struct inode *inode, __cifs_readpage_to_fscache(inode, page); } -static inline int cifs_fscache_release_page(struct page *page, gfp_t gfp) -{ - if (PageFsCache(page)) { - if (current_is_kswapd() || !(gfp & __GFP_FS)) - return false; - wait_on_page_fscache(page); - fscache_note_page_release(cifs_inode_cookie(page->mapping->host)); - } - return true; -} - #else /* CONFIG_CIFS_FSCACHE */ static inline void cifs_fscache_fill_coherency(struct inode *inode, @@ -154,11 +143,6 @@ cifs_readpage_from_fscache(struct inode *inode, struct page *page) static inline void cifs_readpage_to_fscache(struct inode *inode, struct page *page) {} -static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) -{ - return true; /* May release page */ -} - #endif /* CONFIG_CIFS_FSCACHE */ #endif /* _CIFS_FSCACHE_H */ diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 81da81e18553..bac08c20f559 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -25,6 +25,7 @@ #include "fscache.h" #include "fs_context.h" #include "cifs_ioctl.h" +#include "cached_dir.h" static void cifs_set_ops(struct inode *inode) { @@ -339,6 +340,7 @@ cifs_create_dfs_fattr(struct cifs_fattr *fattr, struct super_block *sb) fattr->cf_flags = CIFS_FATTR_DFS_REFERRAL; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY static int cifs_get_file_info_unix(struct file *filp) { @@ -432,6 +434,14 @@ int cifs_get_inode_info_unix(struct inode **pinode, cgiiu_exit: return rc; } +#else +int cifs_get_inode_info_unix(struct inode **pinode, + const unsigned char *full_path, + struct super_block *sb, unsigned int xid) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ static int cifs_sfu_type(struct cifs_fattr *fattr, const char *path, @@ -795,6 +805,7 @@ static __u64 simple_hashstr(const char *str) return hash; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /** * cifs_backup_query_path_info - SMB1 fallback code to get ino * @@ -847,6 +858,7 @@ cifs_backup_query_path_info(int xid, *data = (FILE_ALL_INFO *)info.srch_entries_start; return 0; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ static void cifs_set_fattr_ino(int xid, @@ -991,6 +1003,7 @@ cifs_get_inode_info(struct inode **inode, rc = 0; break; case -EACCES: +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* * perm errors, try again with backup flags if possible * @@ -1022,6 +1035,9 @@ cifs_get_inode_info(struct inode **inode, /* nothing we can do, bail out */ goto out; } +#else + goto out; +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ break; default: cifs_dbg(FYI, "%s: unhandled err rc %d\n", __func__, rc); @@ -1037,8 +1053,9 @@ cifs_get_inode_info(struct inode **inode, /* * 4. Tweak fattr based on mount options */ - +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY handle_mnt_opt: +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ /* query for SFU type info if supported and needed */ if (fattr.cf_cifsattrs & ATTR_SYSTEM && cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) { @@ -1223,7 +1240,7 @@ static const struct inode_operations cifs_ipc_inode_ops = { static int cifs_find_inode(struct inode *inode, void *opaque) { - struct cifs_fattr *fattr = (struct cifs_fattr *) opaque; + struct cifs_fattr *fattr = opaque; /* don't match inode with different uniqueid */ if (CIFS_I(inode)->uniqueid != fattr->cf_uniqueid) @@ -1247,7 +1264,7 @@ cifs_find_inode(struct inode *inode, void *opaque) static int cifs_init_inode(struct inode *inode, void *opaque) { - struct cifs_fattr *fattr = (struct cifs_fattr *) opaque; + struct cifs_fattr *fattr = opaque; CIFS_I(inode)->uniqueid = fattr->cf_uniqueid; CIFS_I(inode)->createtime = fattr->cf_createtime; @@ -1435,6 +1452,7 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid, return server->ops->set_file_info(inode, full_path, &info_buf, xid); } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* * Open the given file (if it isn't already), set the DELETE_ON_CLOSE bit * and rename it to a random name that hopefully won't conflict with @@ -1565,6 +1583,7 @@ undo_setattr: goto out_close; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ /* copied from fs/nfs/dir.c with small changes */ static void @@ -1627,6 +1646,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) } cifs_close_deferred_file_under_dentry(tcon, full_path); +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { rc = CIFSPOSIXDelFile(xid, tcon, full_path, @@ -1636,6 +1656,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) if ((rc == 0) || (rc == -ENOENT)) goto psx_del_no_retry; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ retry_std_delete: if (!server->ops->unlink) { @@ -1714,9 +1735,11 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode, if (tcon->posix_extensions) rc = smb311_posix_get_inode_info(&inode, full_path, parent->i_sb, xid); +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY else if (tcon->unix_ext) rc = cifs_get_inode_info_unix(&inode, full_path, parent->i_sb, xid); +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ else rc = cifs_get_inode_info(&inode, full_path, NULL, parent->i_sb, xid, NULL); @@ -1746,6 +1769,7 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode, if (parent->i_mode & S_ISGID) mode |= S_ISGID; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tcon->unix_ext) { struct cifs_unix_set_info_args args = { .mode = mode, @@ -1768,6 +1792,9 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode, cifs_sb->local_nls, cifs_remap(cifs_sb)); } else { +#else + { +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ struct TCP_Server_Info *server = tcon->ses->server; if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) && (mode & S_IWUGO) == 0 && server->ops->mkdir_setinfo) @@ -1788,6 +1815,7 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode, return 0; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY static int cifs_posix_mkdir(struct inode *inode, struct dentry *dentry, umode_t mode, const char *full_path, struct cifs_sb_info *cifs_sb, @@ -1850,6 +1878,7 @@ posix_mkdir_get_info: xid); goto posix_mkdir_out; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ int cifs_mkdir(struct user_namespace *mnt_userns, struct inode *inode, struct dentry *direntry, umode_t mode) @@ -1892,6 +1921,7 @@ int cifs_mkdir(struct user_namespace *mnt_userns, struct inode *inode, goto mkdir_out; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { rc = cifs_posix_mkdir(inode, direntry, mode, full_path, cifs_sb, @@ -1899,6 +1929,7 @@ int cifs_mkdir(struct user_namespace *mnt_userns, struct inode *inode, if (rc != -EOPNOTSUPP) goto mkdir_out; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ if (!server->ops->mkdir) { rc = -ENOSYS; @@ -2015,9 +2046,12 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, struct tcon_link *tlink; struct cifs_tcon *tcon; struct TCP_Server_Info *server; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY struct cifs_fid fid; struct cifs_open_parms oparms; - int oplock, rc; + int oplock; +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ + int rc; tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) @@ -2043,6 +2077,7 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, if (server->vals->protocol_id != 0) goto do_rename_exit; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* open-file renames don't work across directories */ if (to_dentry->d_parent != from_dentry->d_parent) goto do_rename_exit; @@ -2064,6 +2099,7 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, cifs_sb->local_nls, cifs_remap(cifs_sb)); CIFSSMBClose(xid, tcon, fid.netfid); } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ do_rename_exit: if (rc == 0) d_move(from_dentry, to_dentry); @@ -2081,11 +2117,13 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, struct cifs_sb_info *cifs_sb; struct tcon_link *tlink; struct cifs_tcon *tcon; - FILE_UNIX_BASIC_INFO *info_buf_source = NULL; - FILE_UNIX_BASIC_INFO *info_buf_target; unsigned int xid; int rc, tmprc; int retry_count = 0; + FILE_UNIX_BASIC_INFO *info_buf_source = NULL; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY + FILE_UNIX_BASIC_INFO *info_buf_target; +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ if (flags & ~RENAME_NOREPLACE) return -EINVAL; @@ -2139,6 +2177,7 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, if (flags & RENAME_NOREPLACE) goto cifs_rename_exit; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (rc == -EEXIST && tcon->unix_ext) { /* * Are src and dst hardlinks of same inode? We can only tell @@ -2178,6 +2217,8 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, */ unlink_target: +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ + /* Try unlinking the target dentry if it's not negative */ if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) { if (d_is_dir(target_dentry)) @@ -2337,14 +2378,18 @@ int cifs_revalidate_file_attr(struct file *filp) { int rc = 0; struct dentry *dentry = file_dentry(filp); +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY struct cifsFileInfo *cfile = (struct cifsFileInfo *) filp->private_data; +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ if (!cifs_dentry_needs_reval(dentry)) return rc; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tlink_tcon(cfile->tlink)->unix_ext) rc = cifs_get_file_info_unix(filp); else +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ rc = cifs_get_file_info(filp); return rc; @@ -2653,6 +2698,7 @@ set_size_out: return rc; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY static int cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) { @@ -2800,6 +2846,7 @@ out: free_xid(xid); return rc; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ static int cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) @@ -2995,16 +3042,20 @@ cifs_setattr(struct user_namespace *mnt_userns, struct dentry *direntry, struct iattr *attrs) { struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); - struct cifs_tcon *pTcon = cifs_sb_master_tcon(cifs_sb); int rc, retries = 0; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY + struct cifs_tcon *pTcon = cifs_sb_master_tcon(cifs_sb); +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ if (unlikely(cifs_forced_shutdown(cifs_sb))) return -EIO; do { +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (pTcon->unix_ext) rc = cifs_setattr_unix(direntry, attrs); else +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ rc = cifs_setattr_nounix(direntry, attrs); retries++; } while (is_retryable_error(rc) && retries < 2); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 0359b604bdbc..b6e6e5d6c8dd 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -333,6 +333,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) tcon = tlink_tcon(pSMBFile->tlink); caps = le64_to_cpu(tcon->fsUnixInfo.Capability); #ifdef CONFIG_CIFS_POSIX +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (CIFS_UNIX_EXTATTR_CAP & caps) { __u64 ExtAttrMask = 0; rc = CIFSGetExtAttr(xid, tcon, @@ -345,6 +346,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) if (rc != EOPNOTSUPP) break; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ #endif /* CONFIG_CIFS_POSIX */ rc = 0; if (CIFS_I(inode)->cifsAttrs & ATTR_COMPRESSED) { diff --git a/fs/cifs/link.c b/fs/cifs/link.c index bbdf3281559c..6803cb27eecc 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -286,6 +286,7 @@ out: return rc; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* * SMB 1.0 Protocol specific functions */ @@ -368,6 +369,7 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, CIFSSMBClose(xid, tcon, fid.netfid); return rc; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ /* * SMB 2.1/SMB3 Protocol specific functions @@ -532,11 +534,15 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode, goto cifs_hl_exit; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tcon->unix_ext) rc = CIFSUnixCreateHardLink(xid, tcon, from_name, to_name, cifs_sb->local_nls, cifs_remap(cifs_sb)); else { +#else + { +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ server = tcon->ses->server; if (!server->ops->create_hardlink) { rc = -ENOSYS; @@ -704,10 +710,12 @@ cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode, /* BB what if DFS and this volume is on different share? BB */ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) rc = create_mf_symlink(xid, pTcon, cifs_sb, full_path, symname); +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY else if (pTcon->unix_ext) rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, symname, cifs_sb->local_nls, cifs_remap(cifs_sb)); +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ /* else rc = CIFSCreateReparseSymLink(xid, pTcon, fromName, toName, cifs_sb_target->local_nls); */ diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 0e84e6fcf8ab..87f60f736731 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -23,6 +23,7 @@ #include "dns_resolve.h" #endif #include "fs_context.h" +#include "cached_dir.h" extern mempool_t *cifs_sm_req_poolp; extern mempool_t *cifs_req_poolp; @@ -69,6 +70,7 @@ sesInfoAlloc(void) ret_buf = kzalloc(sizeof(struct cifs_ses), GFP_KERNEL); if (ret_buf) { atomic_inc(&sesInfoAllocCount); + spin_lock_init(&ret_buf->ses_lock); ret_buf->ses_status = SES_NEW; ++ret_buf->ses_count; INIT_LIST_HEAD(&ret_buf->smb_ses_list); @@ -115,21 +117,19 @@ tconInfoAlloc(void) ret_buf = kzalloc(sizeof(*ret_buf), GFP_KERNEL); if (!ret_buf) return NULL; - ret_buf->crfid.fid = kzalloc(sizeof(*ret_buf->crfid.fid), GFP_KERNEL); - if (!ret_buf->crfid.fid) { + ret_buf->cfid = init_cached_dir(); + if (!ret_buf->cfid) { kfree(ret_buf); return NULL; } - INIT_LIST_HEAD(&ret_buf->crfid.dirents.entries); - mutex_init(&ret_buf->crfid.dirents.de_mutex); atomic_inc(&tconInfoAllocCount); ret_buf->status = TID_NEW; ++ret_buf->tc_count; + spin_lock_init(&ret_buf->tc_lock); INIT_LIST_HEAD(&ret_buf->openFileList); INIT_LIST_HEAD(&ret_buf->tcon_list); spin_lock_init(&ret_buf->open_file_lock); - mutex_init(&ret_buf->crfid.fid_mutex); spin_lock_init(&ret_buf->stat_lock); atomic_set(&ret_buf->num_local_opens, 0); atomic_set(&ret_buf->num_remote_opens, 0); @@ -138,17 +138,17 @@ tconInfoAlloc(void) } void -tconInfoFree(struct cifs_tcon *buf_to_free) +tconInfoFree(struct cifs_tcon *tcon) { - if (buf_to_free == NULL) { + if (tcon == NULL) { cifs_dbg(FYI, "Null buffer passed to tconInfoFree\n"); return; } + free_cached_dir(tcon); atomic_dec(&tconInfoAllocCount); - kfree(buf_to_free->nativeFileSystem); - kfree_sensitive(buf_to_free->password); - kfree(buf_to_free->crfid.fid); - kfree(buf_to_free); + kfree(tcon->nativeFileSystem); + kfree_sensitive(tcon->password); + kfree(tcon); } struct smb_hdr * @@ -172,9 +172,9 @@ cifs_buf_get(void) /* clear the first few header bytes */ /* for most paths, more is cleared in header_assemble */ memset(ret_buf, 0, buf_size + 3); - atomic_inc(&bufAllocCount); + atomic_inc(&buf_alloc_count); #ifdef CONFIG_CIFS_STATS2 - atomic_inc(&totBufAllocCount); + atomic_inc(&total_buf_alloc_count); #endif /* CONFIG_CIFS_STATS2 */ return ret_buf; @@ -189,7 +189,7 @@ cifs_buf_release(void *buf_to_free) } mempool_free(buf_to_free, cifs_req_poolp); - atomic_dec(&bufAllocCount); + atomic_dec(&buf_alloc_count); return; } @@ -205,9 +205,9 @@ cifs_small_buf_get(void) ret_buf = mempool_alloc(cifs_sm_req_poolp, GFP_NOFS); /* No need to clear memory here, cleared in header assemble */ /* memset(ret_buf, 0, sizeof(struct smb_hdr) + 27);*/ - atomic_inc(&smBufAllocCount); + atomic_inc(&small_buf_alloc_count); #ifdef CONFIG_CIFS_STATS2 - atomic_inc(&totSmBufAllocCount); + atomic_inc(&total_small_buf_alloc_count); #endif /* CONFIG_CIFS_STATS2 */ return ret_buf; @@ -223,7 +223,7 @@ cifs_small_buf_release(void *buf_to_free) } mempool_free(buf_to_free, cifs_sm_req_poolp); - atomic_dec(&smBufAllocCount); + atomic_dec(&small_buf_alloc_count); return; } @@ -354,7 +354,7 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server) /* otherwise, there is enough to get to the BCC */ if (check_smb_hdr(smb)) return -EIO; - clc_len = smbCalcSize(smb, server); + clc_len = smbCalcSize(smb); if (4 + rfclen != total_read) { cifs_dbg(VFS, "Length read does not match RFC1001 length %d\n", @@ -400,7 +400,6 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) { struct smb_hdr *buf = (struct smb_hdr *)buffer; struct smb_com_lock_req *pSMB = (struct smb_com_lock_req *)buf; - struct list_head *tmp, *tmp1, *tmp2; struct cifs_ses *ses; struct cifs_tcon *tcon; struct cifsInodeInfo *pCifsInode; @@ -467,18 +466,14 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &srv->smb_ses_list) { - ses = list_entry(tmp, struct cifs_ses, smb_ses_list); - list_for_each(tmp1, &ses->tcon_list) { - tcon = list_entry(tmp1, struct cifs_tcon, tcon_list); + list_for_each_entry(ses, &srv->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid != buf->Tid) continue; cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks); spin_lock(&tcon->open_file_lock); - list_for_each(tmp2, &tcon->openFileList) { - netfile = list_entry(tmp2, struct cifsFileInfo, - tlist); + list_for_each_entry(netfile, &tcon->openFileList, tlist) { if (pSMB->Fid != netfile->fid.netfid) continue; @@ -742,6 +737,8 @@ cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) list_for_each_entry(cfile, &cifs_inode->openFileList, flist) { if (delayed_work_pending(&cfile->deferred)) { if (cancel_delayed_work(&cfile->deferred)) { + cifs_del_deferred_close(cfile); + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) break; @@ -763,16 +760,16 @@ void cifs_close_all_deferred_files(struct cifs_tcon *tcon) { struct cifsFileInfo *cfile; - struct list_head *tmp; struct file_list *tmp_list, *tmp_next_list; struct list_head file_head; INIT_LIST_HEAD(&file_head); spin_lock(&tcon->open_file_lock); - list_for_each(tmp, &tcon->openFileList) { - cfile = list_entry(tmp, struct cifsFileInfo, tlist); + list_for_each_entry(cfile, &tcon->openFileList, tlist) { if (delayed_work_pending(&cfile->deferred)) { if (cancel_delayed_work(&cfile->deferred)) { + cifs_del_deferred_close(cfile); + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) break; @@ -793,7 +790,6 @@ void cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path) { struct cifsFileInfo *cfile; - struct list_head *tmp; struct file_list *tmp_list, *tmp_next_list; struct list_head file_head; void *page; @@ -802,12 +798,13 @@ cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path) INIT_LIST_HEAD(&file_head); page = alloc_dentry_path(); spin_lock(&tcon->open_file_lock); - list_for_each(tmp, &tcon->openFileList) { - cfile = list_entry(tmp, struct cifsFileInfo, tlist); + list_for_each_entry(cfile, &tcon->openFileList, tlist) { full_path = build_path_from_dentry(cfile->dentry, page); if (strstr(full_path, path)) { if (delayed_work_pending(&cfile->deferred)) { if (cancel_delayed_work(&cfile->deferred)) { + cifs_del_deferred_close(cfile); + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) break; @@ -1029,7 +1026,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) saved_len = count; while (count && npages < max_pages) { - rc = iov_iter_get_pages(iter, pages, count, max_pages, &start); + rc = iov_iter_get_pages2(iter, pages, count, max_pages, &start); if (rc < 0) { cifs_dbg(VFS, "Couldn't get user pages (rc=%zd)\n", rc); break; @@ -1041,7 +1038,6 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) break; } - iov_iter_advance(iter, rc); count -= rc; rc += start; cur_npages = DIV_ROUND_UP(rc, PAGE_SIZE); diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index 235aa1b395eb..1b52e6ac431c 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -909,9 +909,9 @@ map_and_check_smb_error(struct mid_q_entry *mid, bool logErr) * portion, the number of word parameters and the data portion of the message */ unsigned int -smbCalcSize(void *buf, struct TCP_Server_Info *server) +smbCalcSize(void *buf) { - struct smb_hdr *ptr = (struct smb_hdr *)buf; + struct smb_hdr *ptr = buf; return (sizeof(struct smb_hdr) + (2 * ptr->WordCount) + 2 /* size of the bcc field */ + get_bcc(ptr)); } diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 384cabdf47ca..8e060c00c969 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -21,6 +21,7 @@ #include "cifsfs.h" #include "smb2proto.h" #include "fs_context.h" +#include "cached_dir.h" /* * To be safe - for UCS to UTF-8 with strings loaded with the rare long @@ -805,8 +806,7 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, end_of_smb = cfile->srch_inf.ntwrk_buf_start + server->ops->calc_smb_size( - cfile->srch_inf.ntwrk_buf_start, - server); + cfile->srch_inf.ntwrk_buf_start); cur_ent = cfile->srch_inf.srch_entries_start; first_entry_in_buffer = cfile->srch_inf.index_of_last_entry @@ -1071,7 +1071,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) tcon = tlink_tcon(cifsFile->tlink); } - rc = open_cached_dir(xid, tcon, full_path, cifs_sb, &cfid); + rc = open_cached_dir(xid, tcon, full_path, cifs_sb, false, &cfid); cifs_put_tlink(tlink); if (rc) goto cache_not_found; @@ -1142,7 +1142,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) tcon = tlink_tcon(cifsFile->tlink); rc = find_cifs_entry(xid, tcon, ctx->pos, file, full_path, ¤t_entry, &num_to_fill); - open_cached_dir(xid, tcon, full_path, cifs_sb, &cfid); + open_cached_dir(xid, tcon, full_path, cifs_sb, false, &cfid); if (rc) { cifs_dbg(FYI, "fce error %d\n", rc); goto rddir2_exit; @@ -1160,8 +1160,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) cifs_dbg(FYI, "loop through %d times filling dir for net buf %p\n", num_to_fill, cifsFile->srch_inf.ntwrk_buf_start); max_len = tcon->ses->server->ops->calc_smb_size( - cifsFile->srch_inf.ntwrk_buf_start, - tcon->ses->server); + cifsFile->srch_inf.ntwrk_buf_start); end_of_smb = cifsFile->srch_inf.ntwrk_buf_start + max_len; tmp_buf = kmalloc(UNICODE_NAME_MAX, GFP_KERNEL); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 02c8b2906196..3af3b05b6c74 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -499,6 +499,7 @@ out: return rc; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, struct TCP_Server_Info *server, SESSION_SETUP_ANDX *pSMB) @@ -591,7 +592,6 @@ static void unicode_domain_string(char **pbcc_area, struct cifs_ses *ses, *pbcc_area = bcc_ptr; } - static void unicode_ssetup_strings(char **pbcc_area, struct cifs_ses *ses, const struct nls_table *nls_cp) { @@ -753,6 +753,7 @@ static void decode_ascii_ssetup(char **pbcc_area, __u16 bleft, for it later, but it is not very important */ cifs_dbg(FYI, "ascii: bytes left %d\n", bleft); } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses) @@ -1170,6 +1171,7 @@ struct sess_data { struct kvec iov[3]; }; +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY static int sess_alloc_buffer(struct sess_data *sess_data, int wct) { @@ -1846,3 +1848,4 @@ out: kfree(sess_data); return rc; } +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 2e20ee4dab7b..f36b2d2d40ca 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -92,17 +92,17 @@ cifs_find_mid(struct TCP_Server_Info *server, char *buffer) struct smb_hdr *buf = (struct smb_hdr *)buffer; struct mid_q_entry *mid; - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); list_for_each_entry(mid, &server->pending_mid_q, qhead) { if (compare_mid(mid->mid, buf) && mid->mid_state == MID_REQUEST_SUBMITTED && le16_to_cpu(mid->command) == buf->Command) { kref_get(&mid->refcount); - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); return mid; } } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); return NULL; } @@ -166,7 +166,7 @@ cifs_get_next_mid(struct TCP_Server_Info *server) __u16 last_mid, cur_mid; bool collision, reconnect = false; - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); /* mid is 16 bit only for CIFS/SMB */ cur_mid = (__u16)((server->CurrentMid) & 0xffff); @@ -225,7 +225,7 @@ cifs_get_next_mid(struct TCP_Server_Info *server) } cur_mid++; } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); if (reconnect) { cifs_signal_cifsd_for_reconnect(server, false); diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index f5dcc4940b6d..9dfd2dd612c2 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -61,7 +61,6 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, nr_ioctl_req.Reserved = 0; rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid, fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, - true /* is_fsctl */, (char *)&nr_ioctl_req, sizeof(nr_ioctl_req), CIFSMaxBufSize, NULL, NULL /* no return info */); if (rc == -EOPNOTSUPP) { diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 8571a459c710..b83f59051b26 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -23,6 +23,7 @@ #include "smb2glob.h" #include "smb2pdu.h" #include "smb2proto.h" +#include "cached_dir.h" static void free_set_inf_compound(struct smb_rqst *rqst) @@ -515,16 +516,16 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, if (strcmp(full_path, "")) rc = -ENOENT; else - rc = open_cached_dir(xid, tcon, full_path, cifs_sb, &cfid); + rc = open_cached_dir(xid, tcon, full_path, cifs_sb, false, &cfid); /* If it is a root and its handle is cached then use it */ if (!rc) { - if (tcon->crfid.file_all_info_is_valid) { + if (cfid->file_all_info_is_valid) { move_smb2_info_to_cifs(data, - &tcon->crfid.file_all_info); + &cfid->file_all_info); } else { rc = SMB2_query_info(xid, tcon, - cfid->fid->persistent_fid, - cfid->fid->volatile_fid, smb2_data); + cfid->fid.persistent_fid, + cfid->fid.volatile_fid, smb2_data); if (!rc) move_smb2_info_to_cifs(data, smb2_data); } diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 17813c3d0c6e..d73e5672aac4 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -16,6 +16,7 @@ #include "smb2status.h" #include "smb2glob.h" #include "nterr.h" +#include "cached_dir.h" static int check_smb2_hdr(struct smb2_hdr *shdr, __u64 mid) @@ -132,15 +133,15 @@ static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, } int -smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) +smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) { struct smb2_hdr *shdr = (struct smb2_hdr *)buf; struct smb2_pdu *pdu = (struct smb2_pdu *)shdr; - __u64 mid; - __u32 clc_len; /* calculated length */ - int command; - int pdu_size = sizeof(struct smb2_pdu); int hdr_size = sizeof(struct smb2_hdr); + int pdu_size = sizeof(struct smb2_pdu); + int command; + __u32 calc_len; /* calculated length */ + __u64 mid; /* * Add function to do table lookup of StructureSize by command @@ -154,7 +155,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) /* decrypt frame now that it is completely read in */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(iter, &srvr->smb_ses_list, smb_ses_list) { + list_for_each_entry(iter, &server->smb_ses_list, smb_ses_list) { if (iter->Suid == le64_to_cpu(thdr->SessionId)) { ses = iter; break; @@ -221,30 +222,33 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) } } - clc_len = smb2_calc_size(buf, srvr); + calc_len = smb2_calc_size(buf); + + /* For SMB2_IOCTL, OutputOffset and OutputLength are optional, so might + * be 0, and not a real miscalculation */ + if (command == SMB2_IOCTL_HE && calc_len == 0) + return 0; - if (shdr->Command == SMB2_NEGOTIATE) - clc_len += get_neg_ctxt_len(shdr, len, clc_len); + if (command == SMB2_NEGOTIATE_HE) + calc_len += get_neg_ctxt_len(shdr, len, calc_len); - if (len != clc_len) { - cifs_dbg(FYI, "Calculated size %u length %u mismatch mid %llu\n", - clc_len, len, mid); + if (len != calc_len) { /* create failed on symlink */ if (command == SMB2_CREATE_HE && shdr->Status == STATUS_STOPPED_ON_SYMLINK) return 0; /* Windows 7 server returns 24 bytes more */ - if (clc_len + 24 == len && command == SMB2_OPLOCK_BREAK_HE) + if (calc_len + 24 == len && command == SMB2_OPLOCK_BREAK_HE) return 0; /* server can return one byte more due to implied bcc[0] */ - if (clc_len == len + 1) + if (calc_len == len + 1) return 0; /* * Some windows servers (win2016) will pad also the final * PDU in a compound to 8 bytes. */ - if (((clc_len + 7) & ~7) == len) + if (((calc_len + 7) & ~7) == len) return 0; /* @@ -253,12 +257,18 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) * SMB2/SMB3 frame length (header + smb2 response specific data) * Some windows servers also pad up to 8 bytes when compounding. */ - if (clc_len < len) + if (calc_len < len) return 0; - pr_warn_once( - "srv rsp too short, len %d not %d. cmd:%d mid:%llu\n", - len, clc_len, command, mid); + /* Only log a message if len was really miscalculated */ + if (unlikely(cifsFYI)) + cifs_dbg(FYI, "Server response too short: calculated " + "length %u doesn't match read length %u (cmd=%d, mid=%llu)\n", + calc_len, len, command, mid); + else + pr_warn("Server response too short: calculated length " + "%u doesn't match read length %u (cmd=%d, mid=%llu)\n", + calc_len, len, command, mid); return 1; } @@ -400,9 +410,9 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr) * portion, the number of word parameters and the data portion of the message. */ unsigned int -smb2_calc_size(void *buf, struct TCP_Server_Info *srvr) +smb2_calc_size(void *buf) { - struct smb2_pdu *pdu = (struct smb2_pdu *)buf; + struct smb2_pdu *pdu = buf; struct smb2_hdr *shdr = &pdu->hdr; int offset; /* the offset from the beginning of SMB to data area */ int data_length; /* the length of the variable length data area */ @@ -639,15 +649,7 @@ smb2_is_valid_lease_break(char *buffer) } spin_unlock(&tcon->open_file_lock); - if (tcon->crfid.is_valid && - !memcmp(rsp->LeaseKey, - tcon->crfid.fid->lease_key, - SMB2_LEASE_KEY_SIZE)) { - tcon->crfid.time = 0; - INIT_WORK(&tcon->crfid.lease_break, - smb2_cached_lease_break); - queue_work(cifsiod_wq, - &tcon->crfid.lease_break); + if (cached_dir_lease_break(tcon, rsp->LeaseKey)) { spin_unlock(&cifs_tcp_ses_lock); return true; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 8802995b2d3d..421be43af425 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -27,6 +27,7 @@ #include "smbdirect.h" #include "fscache.h" #include "fs_context.h" +#include "cached_dir.h" /* Change credits for different ops and return the total number of credits */ static int @@ -126,13 +127,13 @@ smb2_add_credits(struct TCP_Server_Info *server, optype, scredits, add); } - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsNeedReconnect || server->tcpStatus == CifsExiting) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); switch (rc) { case -1: @@ -218,12 +219,12 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, spin_lock(&server->req_lock); } else { spin_unlock(&server->req_lock); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsExiting) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return -ENOENT; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); spin_lock(&server->req_lock); scredits = server->credits; @@ -319,19 +320,19 @@ smb2_get_next_mid(struct TCP_Server_Info *server) { __u64 mid; /* for SMB2 we need the current value */ - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); mid = server->CurrentMid++; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); return mid; } static void smb2_revert_current_mid(struct TCP_Server_Info *server, const unsigned int val) { - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); if (server->CurrentMid >= val) server->CurrentMid -= val; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); } static struct mid_q_entry * @@ -346,7 +347,7 @@ __smb2_find_mid(struct TCP_Server_Info *server, char *buf, bool dequeue) return NULL; } - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); list_for_each_entry(mid, &server->pending_mid_q, qhead) { if ((mid->mid == wire_mid) && (mid->mid_state == MID_REQUEST_SUBMITTED) && @@ -356,11 +357,11 @@ __smb2_find_mid(struct TCP_Server_Info *server, char *buf, bool dequeue) list_del_init(&mid->qhead); mid->mid_flags |= MID_DELETED; } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); return mid; } } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); return NULL; } @@ -386,7 +387,7 @@ smb2_dump_detail(void *buf, struct TCP_Server_Info *server) shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId, shdr->Id.SyncId.ProcessId); cifs_server_dbg(VFS, "smb buf %p len %u\n", buf, - server->ops->calc_smb_size(buf, server)); + server->ops->calc_smb_size(buf)); #endif } @@ -403,9 +404,9 @@ smb2_negotiate(const unsigned int xid, { int rc; - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); server->CurrentMid = 0; - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); rc = SMB2_negotiate(xid, ses, server); /* BB we probably don't need to retry with modern servers */ if (rc == -EAGAIN) @@ -680,7 +681,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) struct cifs_ses *ses = tcon->ses; rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, - FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */, + FSCTL_QUERY_NETWORK_INTERFACE_INFO, NULL /* no data input */, 0 /* no data input */, CIFSMaxBufSize, (char **)&out_buf, &ret_data_len); if (rc == -EOPNOTSUPP) { @@ -702,300 +703,6 @@ out: } static void -smb2_close_cached_fid(struct kref *ref) -{ - struct cached_fid *cfid = container_of(ref, struct cached_fid, - refcount); - struct cached_dirent *dirent, *q; - - if (cfid->is_valid) { - cifs_dbg(FYI, "clear cached root file handle\n"); - SMB2_close(0, cfid->tcon, cfid->fid->persistent_fid, - cfid->fid->volatile_fid); - } - - /* - * We only check validity above to send SMB2_close, - * but we still need to invalidate these entries - * when this function is called - */ - cfid->is_valid = false; - cfid->file_all_info_is_valid = false; - cfid->has_lease = false; - if (cfid->dentry) { - dput(cfid->dentry); - cfid->dentry = NULL; - } - /* - * Delete all cached dirent names - */ - mutex_lock(&cfid->dirents.de_mutex); - list_for_each_entry_safe(dirent, q, &cfid->dirents.entries, entry) { - list_del(&dirent->entry); - kfree(dirent->name); - kfree(dirent); - } - cfid->dirents.is_valid = 0; - cfid->dirents.is_failed = 0; - cfid->dirents.ctx = NULL; - cfid->dirents.pos = 0; - mutex_unlock(&cfid->dirents.de_mutex); - -} - -void close_cached_dir(struct cached_fid *cfid) -{ - mutex_lock(&cfid->fid_mutex); - kref_put(&cfid->refcount, smb2_close_cached_fid); - mutex_unlock(&cfid->fid_mutex); -} - -void close_cached_dir_lease_locked(struct cached_fid *cfid) -{ - if (cfid->has_lease) { - cfid->has_lease = false; - kref_put(&cfid->refcount, smb2_close_cached_fid); - } -} - -void close_cached_dir_lease(struct cached_fid *cfid) -{ - mutex_lock(&cfid->fid_mutex); - close_cached_dir_lease_locked(cfid); - mutex_unlock(&cfid->fid_mutex); -} - -void -smb2_cached_lease_break(struct work_struct *work) -{ - struct cached_fid *cfid = container_of(work, - struct cached_fid, lease_break); - - close_cached_dir_lease(cfid); -} - -/* - * Open the and cache a directory handle. - * Only supported for the root handle. - * If error then *cfid is not initialized. - */ -int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, - const char *path, - struct cifs_sb_info *cifs_sb, - struct cached_fid **cfid) -{ - struct cifs_ses *ses; - struct TCP_Server_Info *server; - struct cifs_open_parms oparms; - struct smb2_create_rsp *o_rsp = NULL; - struct smb2_query_info_rsp *qi_rsp = NULL; - int resp_buftype[2]; - struct smb_rqst rqst[2]; - struct kvec rsp_iov[2]; - struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; - struct kvec qi_iov[1]; - int rc, flags = 0; - __le16 utf16_path = 0; /* Null - since an open of top of share */ - u8 oplock = SMB2_OPLOCK_LEVEL_II; - struct cifs_fid *pfid; - struct dentry *dentry; - - if (tcon == NULL || tcon->nohandlecache || - is_smb1_server(tcon->ses->server)) - return -ENOTSUPP; - - ses = tcon->ses; - server = ses->server; - - if (cifs_sb->root == NULL) - return -ENOENT; - - if (strlen(path)) - return -ENOENT; - - dentry = cifs_sb->root; - - mutex_lock(&tcon->crfid.fid_mutex); - if (tcon->crfid.is_valid) { - cifs_dbg(FYI, "found a cached root file handle\n"); - *cfid = &tcon->crfid; - kref_get(&tcon->crfid.refcount); - mutex_unlock(&tcon->crfid.fid_mutex); - return 0; - } - - /* - * We do not hold the lock for the open because in case - * SMB2_open needs to reconnect, it will end up calling - * cifs_mark_open_files_invalid() which takes the lock again - * thus causing a deadlock - */ - - mutex_unlock(&tcon->crfid.fid_mutex); - - if (smb3_encryption_required(tcon)) - flags |= CIFS_TRANSFORM_REQ; - - if (!server->ops->new_lease_key) - return -EIO; - - pfid = tcon->crfid.fid; - server->ops->new_lease_key(pfid); - - memset(rqst, 0, sizeof(rqst)); - resp_buftype[0] = resp_buftype[1] = CIFS_NO_BUFFER; - memset(rsp_iov, 0, sizeof(rsp_iov)); - - /* Open */ - memset(&open_iov, 0, sizeof(open_iov)); - rqst[0].rq_iov = open_iov; - rqst[0].rq_nvec = SMB2_CREATE_IOV_SIZE; - - oparms.tcon = tcon; - oparms.create_options = cifs_create_options(cifs_sb, CREATE_NOT_FILE); - oparms.desired_access = FILE_READ_ATTRIBUTES; - oparms.disposition = FILE_OPEN; - oparms.fid = pfid; - oparms.reconnect = false; - - rc = SMB2_open_init(tcon, server, - &rqst[0], &oplock, &oparms, &utf16_path); - if (rc) - goto oshr_free; - smb2_set_next_command(tcon, &rqst[0]); - - memset(&qi_iov, 0, sizeof(qi_iov)); - rqst[1].rq_iov = qi_iov; - rqst[1].rq_nvec = 1; - - rc = SMB2_query_info_init(tcon, server, - &rqst[1], COMPOUND_FID, - COMPOUND_FID, FILE_ALL_INFORMATION, - SMB2_O_INFO_FILE, 0, - sizeof(struct smb2_file_all_info) + - PATH_MAX * 2, 0, NULL); - if (rc) - goto oshr_free; - - smb2_set_related(&rqst[1]); - - rc = compound_send_recv(xid, ses, server, - flags, 2, rqst, - resp_buftype, rsp_iov); - mutex_lock(&tcon->crfid.fid_mutex); - - /* - * Now we need to check again as the cached root might have - * been successfully re-opened from a concurrent process - */ - - if (tcon->crfid.is_valid) { - /* work was already done */ - - /* stash fids for close() later */ - struct cifs_fid fid = { - .persistent_fid = pfid->persistent_fid, - .volatile_fid = pfid->volatile_fid, - }; - - /* - * caller expects this func to set the fid in crfid to valid - * cached root, so increment the refcount. - */ - kref_get(&tcon->crfid.refcount); - - mutex_unlock(&tcon->crfid.fid_mutex); - - if (rc == 0) { - /* close extra handle outside of crit sec */ - SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); - } - rc = 0; - goto oshr_free; - } - - /* Cached root is still invalid, continue normaly */ - - if (rc) { - if (rc == -EREMCHG) { - tcon->need_reconnect = true; - pr_warn_once("server share %s deleted\n", - tcon->treeName); - } - goto oshr_exit; - } - - atomic_inc(&tcon->num_remote_opens); - - o_rsp = (struct smb2_create_rsp *)rsp_iov[0].iov_base; - oparms.fid->persistent_fid = o_rsp->PersistentFileId; - oparms.fid->volatile_fid = o_rsp->VolatileFileId; -#ifdef CONFIG_CIFS_DEBUG2 - oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId); -#endif /* CIFS_DEBUG2 */ - - tcon->crfid.tcon = tcon; - tcon->crfid.is_valid = true; - tcon->crfid.dentry = dentry; - dget(dentry); - kref_init(&tcon->crfid.refcount); - - /* BB TBD check to see if oplock level check can be removed below */ - if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { - /* - * See commit 2f94a3125b87. Increment the refcount when we - * get a lease for root, release it if lease break occurs - */ - kref_get(&tcon->crfid.refcount); - tcon->crfid.has_lease = true; - smb2_parse_contexts(server, o_rsp, - &oparms.fid->epoch, - oparms.fid->lease_key, &oplock, - NULL, NULL); - } else - goto oshr_exit; - - qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; - if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info)) - goto oshr_exit; - if (!smb2_validate_and_copy_iov( - le16_to_cpu(qi_rsp->OutputBufferOffset), - sizeof(struct smb2_file_all_info), - &rsp_iov[1], sizeof(struct smb2_file_all_info), - (char *)&tcon->crfid.file_all_info)) - tcon->crfid.file_all_info_is_valid = true; - tcon->crfid.time = jiffies; - - -oshr_exit: - mutex_unlock(&tcon->crfid.fid_mutex); -oshr_free: - SMB2_open_free(&rqst[0]); - SMB2_query_info_free(&rqst[1]); - free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); - free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); - if (rc == 0) - *cfid = &tcon->crfid; - return rc; -} - -int open_cached_dir_by_dentry(struct cifs_tcon *tcon, - struct dentry *dentry, - struct cached_fid **cfid) -{ - mutex_lock(&tcon->crfid.fid_mutex); - if (tcon->crfid.dentry == dentry) { - cifs_dbg(FYI, "found a cached root file handle by dentry\n"); - *cfid = &tcon->crfid; - kref_get(&tcon->crfid.refcount); - mutex_unlock(&tcon->crfid.fid_mutex); - return 0; - } - mutex_unlock(&tcon->crfid.fid_mutex); - return -ENOENT; -} - -static void smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb) { @@ -1013,9 +720,9 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = open_cached_dir(xid, tcon, "", cifs_sb, &cfid); + rc = open_cached_dir(xid, tcon, "", cifs_sb, false, &cfid); if (rc == 0) - memcpy(&fid, cfid->fid, sizeof(struct cifs_fid)); + memcpy(&fid, &cfid->fid, sizeof(struct cifs_fid)); else rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL, NULL, NULL); @@ -1076,9 +783,16 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; struct cifs_open_parms oparms; struct cifs_fid fid; + struct cached_fid *cfid; - if ((*full_path == 0) && tcon->crfid.is_valid) - return 0; + rc = open_cached_dir(xid, tcon, full_path, cifs_sb, true, &cfid); + if (!rc) { + if (cfid->is_valid) { + close_cached_dir(cfid); + return 0; + } + close_cached_dir(cfid); + } utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb); if (!utf16_path) @@ -1145,9 +859,7 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size, size_t name_len, value_len, user_name_len; while (src_size > 0) { - name = &src->ea_data[0]; name_len = (size_t)src->ea_name_length; - value = &src->ea_data[src->ea_name_length + 1]; value_len = (size_t)le16_to_cpu(src->ea_value_length); if (name_len == 0) @@ -1159,6 +871,9 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size, goto out; } + name = &src->ea_data[0]; + value = &src->ea_data[src->ea_name_length + 1]; + if (ea_name) { if (ea_name_len == name_len && memcmp(ea_name, name, name_len) == 0) { @@ -1608,9 +1323,8 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon, struct resume_key_req *res_key; rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, - FSCTL_SRV_REQUEST_RESUME_KEY, true /* is_fsctl */, - NULL, 0 /* no input */, CIFSMaxBufSize, - (char **)&res_key, &ret_data_len); + FSCTL_SRV_REQUEST_RESUME_KEY, NULL, 0 /* no input */, + CIFSMaxBufSize, (char **)&res_key, &ret_data_len); if (rc == -EOPNOTSUPP) { pr_warn_once("Server share %s does not support copy range\n", tcon->treeName); @@ -1752,7 +1466,7 @@ smb2_ioctl_query_info(const unsigned int xid, rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE; rc = SMB2_ioctl_init(tcon, server, &rqst[1], COMPOUND_FID, COMPOUND_FID, - qi.info_type, true, buffer, qi.output_buffer_length, + qi.info_type, buffer, qi.output_buffer_length, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - MAX_SMB2_CLOSE_RESPONSE_SIZE); free_req1_func = SMB2_ioctl_free; @@ -1886,17 +1600,8 @@ smb2_copychunk_range(const unsigned int xid, int chunks_copied = 0; bool chunk_sizes_updated = false; ssize_t bytes_written, total_bytes_written = 0; - struct inode *inode; pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); - - /* - * We need to flush all unwritten data before we can send the - * copychunk ioctl to the server. - */ - inode = d_inode(trgtfile->dentry); - filemap_write_and_wait(inode->i_mapping); - if (pcchunk == NULL) return -ENOMEM; @@ -1928,9 +1633,8 @@ smb2_copychunk_range(const unsigned int xid, retbuf = NULL; rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, - true /* is_fsctl */, (char *)pcchunk, - sizeof(struct copychunk_ioctl), CIFSMaxBufSize, - (char **)&retbuf, &ret_data_len); + (char *)pcchunk, sizeof(struct copychunk_ioctl), + CIFSMaxBufSize, (char **)&retbuf, &ret_data_len); if (rc == 0) { if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) { @@ -2090,7 +1794,6 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_SPARSE, - true /* is_fctl */, &setsparse, 1, CIFSMaxBufSize, NULL, NULL); if (rc) { tcon->broken_sparse_sup = true; @@ -2173,7 +1876,6 @@ smb2_duplicate_extents(const unsigned int xid, rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_DUPLICATE_EXTENTS_TO_FILE, - true /* is_fsctl */, (char *)&dup_ext_buf, sizeof(struct duplicate_extents_to_file), CIFSMaxBufSize, NULL, @@ -2208,7 +1910,6 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon, return SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_INTEGRITY_INFORMATION, - true /* is_fsctl */, (char *)&integr_info, sizeof(struct fsctl_set_integrity_information_req), CIFSMaxBufSize, NULL, @@ -2261,7 +1962,6 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SRV_ENUMERATE_SNAPSHOTS, - true /* is_fsctl */, NULL, 0 /* no input data */, max_response_size, (char **)&retbuf, &ret_data_len); @@ -2574,7 +2274,6 @@ static void smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) { struct smb2_hdr *shdr = (struct smb2_hdr *)buf; - struct list_head *tmp, *tmp1; struct cifs_ses *ses; struct cifs_tcon *tcon; @@ -2582,12 +2281,12 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) return; spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &server->smb_ses_list) { - ses = list_entry(tmp, struct cifs_ses, smb_ses_list); - list_for_each(tmp1, &ses->tcon_list) { - tcon = list_entry(tmp1, struct cifs_tcon, tcon_list); + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) { + spin_lock(&tcon->tc_lock); tcon->need_reconnect = true; + spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); pr_warn_once("Server share %s deleted.\n", tcon->treeName); @@ -2723,8 +2422,12 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER; memset(rsp_iov, 0, sizeof(rsp_iov)); + /* + * We can only call this for things we know are directories. + */ if (!strcmp(path, "")) - open_cached_dir(xid, tcon, path, cifs_sb, &cfid); /* cfid null if open dir failed */ + open_cached_dir(xid, tcon, path, cifs_sb, false, + &cfid); /* cfid null if open dir failed */ memset(&open_iov, 0, sizeof(open_iov)); rqst[0].rq_iov = open_iov; @@ -2750,8 +2453,8 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, if (cfid) { rc = SMB2_query_info_init(tcon, server, &rqst[1], - cfid->fid->persistent_fid, - cfid->fid->volatile_fid, + cfid->fid.persistent_fid, + cfid->fid.volatile_fid, class, type, 0, output_len, 0, NULL); @@ -2981,7 +2684,6 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, do { rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_DFS_GET_REFERRALS, - true /* is_fsctl */, (char *)dfs_req, dfs_req_size, CIFSMaxBufSize, (char **)&dfs_rsp, &dfs_rsp_size); if (!is_retryable_error(rc)) @@ -3188,8 +2890,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl_init(tcon, server, &rqst[1], fid.persistent_fid, - fid.volatile_fid, FSCTL_GET_REPARSE_POINT, - true /* is_fctl */, NULL, 0, + fid.volatile_fid, FSCTL_GET_REPARSE_POINT, NULL, 0, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - MAX_SMB2_CLOSE_RESPONSE_SIZE); @@ -3369,8 +3070,7 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl_init(tcon, server, &rqst[1], COMPOUND_FID, - COMPOUND_FID, FSCTL_GET_REPARSE_POINT, - true /* is_fctl */, NULL, 0, + COMPOUND_FID, FSCTL_GET_REPARSE_POINT, NULL, 0, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - MAX_SMB2_CLOSE_RESPONSE_SIZE); @@ -3598,26 +3298,43 @@ get_smb2_acl(struct cifs_sb_info *cifs_sb, return pntsd; } +static long smb3_zero_data(struct file *file, struct cifs_tcon *tcon, + loff_t offset, loff_t len, unsigned int xid) +{ + struct cifsFileInfo *cfile = file->private_data; + struct file_zero_data_information fsctl_buf; + + cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); + + fsctl_buf.FileOffset = cpu_to_le64(offset); + fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); + + return SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, + (char *)&fsctl_buf, + sizeof(struct file_zero_data_information), + 0, NULL, NULL); +} + static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, loff_t offset, loff_t len, bool keep_size) { struct cifs_ses *ses = tcon->ses; - struct inode *inode; - struct cifsInodeInfo *cifsi; + struct inode *inode = file_inode(file); + struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifsFileInfo *cfile = file->private_data; - struct file_zero_data_information fsctl_buf; long rc; unsigned int xid; __le64 eof; xid = get_xid(); - inode = d_inode(cfile->dentry); - cifsi = CIFS_I(inode); - trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); + inode_lock(inode); + filemap_invalidate_lock(inode->i_mapping); + /* * We zero the range through ioctl, so we need remove the page caches * first, otherwise the data may be inconsistent with the server. @@ -3625,26 +3342,12 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, truncate_pagecache_range(inode, offset, offset + len - 1); /* if file not oplocked can't be sure whether asking to extend size */ - if (!CIFS_CACHE_READ(cifsi)) - if (keep_size == false) { - rc = -EOPNOTSUPP; - trace_smb3_zero_err(xid, cfile->fid.persistent_fid, - tcon->tid, ses->Suid, offset, len, rc); - free_xid(xid); - return rc; - } - - cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); - - fsctl_buf.FileOffset = cpu_to_le64(offset); - fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); + rc = -EOPNOTSUPP; + if (keep_size == false && !CIFS_CACHE_READ(cifsi)) + goto zero_range_exit; - rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, - cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, true, - (char *)&fsctl_buf, - sizeof(struct file_zero_data_information), - 0, NULL, NULL); - if (rc) + rc = smb3_zero_data(file, tcon, offset, len, xid); + if (rc < 0) goto zero_range_exit; /* @@ -3657,6 +3360,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, } zero_range_exit: + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, @@ -3670,7 +3375,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, loff_t offset, loff_t len) { - struct inode *inode; + struct inode *inode = file_inode(file); struct cifsFileInfo *cfile = file->private_data; struct file_zero_data_information fsctl_buf; long rc; @@ -3679,14 +3384,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, xid = get_xid(); - inode = d_inode(cfile->dentry); - + inode_lock(inode); /* Need to make file sparse, if not already, before freeing range. */ /* Consider adding equivalent for compressed since it could also work */ if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) { rc = -EOPNOTSUPP; - free_xid(xid); - return rc; + goto out; } filemap_invalidate_lock(inode->i_mapping); @@ -3703,11 +3406,13 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, - true /* is_fctl */, (char *)&fsctl_buf, + (char *)&fsctl_buf, sizeof(struct file_zero_data_information), CIFSMaxBufSize, NULL, NULL); - free_xid(xid); filemap_invalidate_unlock(inode->i_mapping); +out: + inode_unlock(inode); + free_xid(xid); return rc; } @@ -3763,7 +3468,7 @@ static int smb3_simple_fallocate_range(unsigned int xid, in_data.length = cpu_to_le64(len); rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, - FSCTL_QUERY_ALLOCATED_RANGES, true, + FSCTL_QUERY_ALLOCATED_RANGES, (char *)&in_data, sizeof(in_data), 1024 * sizeof(struct file_allocated_range_buffer), (char **)&out_data, &out_data_len); @@ -3964,39 +3669,50 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, { int rc; unsigned int xid; - struct inode *inode; + struct inode *inode = file_inode(file); struct cifsFileInfo *cfile = file->private_data; - struct cifsInodeInfo *cifsi; + struct cifsInodeInfo *cifsi = CIFS_I(inode); __le64 eof; + loff_t old_eof; xid = get_xid(); - inode = d_inode(cfile->dentry); - cifsi = CIFS_I(inode); + inode_lock(inode); - if (off >= i_size_read(inode) || - off + len >= i_size_read(inode)) { + old_eof = i_size_read(inode); + if ((off >= old_eof) || + off + len >= old_eof) { rc = -EINVAL; goto out; } + filemap_invalidate_lock(inode->i_mapping); + rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof - 1); + if (rc < 0) + goto out_2; + + truncate_pagecache_range(inode, off, old_eof); + rc = smb2_copychunk_range(xid, cfile, cfile, off + len, - i_size_read(inode) - off - len, off); + old_eof - off - len, off); if (rc < 0) - goto out; + goto out_2; - eof = cpu_to_le64(i_size_read(inode) - len); + eof = cpu_to_le64(old_eof - len); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, &eof); if (rc < 0) - goto out; + goto out_2; rc = 0; cifsi->server_eof = i_size_read(inode) - len; truncate_setsize(inode, cifsi->server_eof); fscache_resize_cookie(cifs_inode_cookie(inode), cifsi->server_eof); +out_2: + filemap_invalidate_unlock(inode->i_mapping); out: + inode_unlock(inode); free_xid(xid); return rc; } @@ -4007,34 +3723,47 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, int rc; unsigned int xid; struct cifsFileInfo *cfile = file->private_data; + struct inode *inode = file_inode(file); __le64 eof; - __u64 count; + __u64 count, old_eof; xid = get_xid(); - if (off >= i_size_read(file->f_inode)) { + inode_lock(inode); + + old_eof = i_size_read(inode); + if (off >= old_eof) { rc = -EINVAL; goto out; } - count = i_size_read(file->f_inode) - off; - eof = cpu_to_le64(i_size_read(file->f_inode) + len); + count = old_eof - off; + eof = cpu_to_le64(old_eof + len); + + filemap_invalidate_lock(inode->i_mapping); + rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof + len - 1); + if (rc < 0) + goto out_2; + truncate_pagecache_range(inode, off, old_eof); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, &eof); if (rc < 0) - goto out; + goto out_2; rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); if (rc < 0) - goto out; + goto out_2; - rc = smb3_zero_range(file, tcon, off, len, 1); + rc = smb3_zero_data(file, tcon, off, len, xid); if (rc < 0) - goto out; + goto out_2; rc = 0; +out_2: + filemap_invalidate_unlock(inode->i_mapping); out: + inode_unlock(inode); free_xid(xid); return rc; } @@ -4084,7 +3813,7 @@ static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offs rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, - FSCTL_QUERY_ALLOCATED_RANGES, true, + FSCTL_QUERY_ALLOCATED_RANGES, (char *)&in_data, sizeof(in_data), sizeof(struct file_allocated_range_buffer), (char **)&out_data, &out_data_len); @@ -4144,7 +3873,7 @@ static int smb3_fiemap(struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, - FSCTL_QUERY_ALLOCATED_RANGES, true, + FSCTL_QUERY_ALLOCATED_RANGES, (char *)&in_data, sizeof(in_data), 1024 * sizeof(struct file_allocated_range_buffer), (char **)&out_data, &out_data_len); @@ -4563,9 +4292,11 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key) list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { if (ses->Suid == ses_id) { + spin_lock(&ses->ses_lock); ses_enc_key = enc ? ses->smb3encryptionkey : ses->smb3decryptionkey; memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); + spin_unlock(&ses->ses_lock); spin_unlock(&cifs_tcp_ses_lock); return 0; } @@ -5080,23 +4811,24 @@ static void smb2_decrypt_offload(struct work_struct *work) mid->callback(mid); } else { - spin_lock(&cifs_tcp_ses_lock); - spin_lock(&GlobalMid_Lock); + spin_lock(&dw->server->srv_lock); if (dw->server->tcpStatus == CifsNeedReconnect) { + spin_lock(&dw->server->mid_lock); mid->mid_state = MID_RETRY_NEEDED; - spin_unlock(&GlobalMid_Lock); - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&dw->server->mid_lock); + spin_unlock(&dw->server->srv_lock); mid->callback(mid); } else { + spin_lock(&dw->server->mid_lock); mid->mid_state = MID_REQUEST_SUBMITTED; mid->mid_flags &= ~(MID_DELETED); list_add_tail(&mid->qhead, &dw->server->pending_mid_q); - spin_unlock(&GlobalMid_Lock); - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&dw->server->mid_lock); + spin_unlock(&dw->server->srv_lock); } } - cifs_mid_q_entry_release(mid); + release_mid(mid); } free_pages: diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index c705de32e225..6352ab32c7e7 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -39,6 +39,7 @@ #ifdef CONFIG_CIFS_DFS_UPCALL #include "dfs_cache.h" #endif +#include "cached_dir.h" /* * The following table defines the expected "StructureSize" of SMB2 requests @@ -162,7 +163,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL) return 0; - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->tc_lock); if (tcon->status == TID_EXITING) { /* * only tree disconnect, open, and write, @@ -172,13 +173,13 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, if ((smb2_command != SMB2_WRITE) && (smb2_command != SMB2_CREATE) && (smb2_command != SMB2_TREE_DISCONNECT)) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->tc_lock); cifs_dbg(FYI, "can not send cmd %d while umounting\n", smb2_command); return -ENODEV; } } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&tcon->tc_lock); if ((!tcon->ses) || (tcon->ses->ses_status == SES_EXITING) || (!tcon->ses->server) || !server) return -EIO; @@ -217,12 +218,12 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, } /* are we still trying to reconnect? */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus != CifsNeedReconnect) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); break; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); if (retries && --retries) continue; @@ -256,13 +257,13 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, * and the server never sends an answer the socket will be closed * and tcpStatus set to reconnect. */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsNeedReconnect) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); rc = -EHOSTDOWN; goto out; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); /* * need to prevent multiple threads trying to simultaneously @@ -354,7 +355,7 @@ fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon, void *buf, unsigned int *total_len) { - struct smb2_pdu *spdu = (struct smb2_pdu *)buf; + struct smb2_pdu *spdu = buf; /* lookup word count ie StructureSize from table */ __u16 parmsize = smb2_req_struct_sizes[le16_to_cpu(smb2_command)]; @@ -964,16 +965,17 @@ SMB2_negotiate(const unsigned int xid, } else if (rc != 0) goto neg_exit; + rc = -EIO; if (strcmp(server->vals->version_string, SMB3ANY_VERSION_STRING) == 0) { if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) { cifs_server_dbg(VFS, "SMB2 dialect returned but not requested\n"); - return -EIO; + goto neg_exit; } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { cifs_server_dbg(VFS, "SMB2.1 dialect returned but not requested\n"); - return -EIO; + goto neg_exit; } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) { /* ops set to 3.0 by default for default so update */ server->ops = &smb311_operations; @@ -984,7 +986,7 @@ SMB2_negotiate(const unsigned int xid, if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) { cifs_server_dbg(VFS, "SMB2 dialect returned but not requested\n"); - return -EIO; + goto neg_exit; } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { /* ops set to 3.0 by default for default so update */ server->ops = &smb21_operations; @@ -998,7 +1000,7 @@ SMB2_negotiate(const unsigned int xid, /* if requested single dialect ensure returned dialect matched */ cifs_server_dbg(VFS, "Invalid 0x%x dialect returned: not requested\n", le16_to_cpu(rsp->DialectRevision)); - return -EIO; + goto neg_exit; } cifs_dbg(FYI, "mode 0x%x\n", rsp->SecurityMode); @@ -1016,9 +1018,10 @@ SMB2_negotiate(const unsigned int xid, else { cifs_server_dbg(VFS, "Invalid dialect returned by server 0x%x\n", le16_to_cpu(rsp->DialectRevision)); - rc = -EIO; goto neg_exit; } + + rc = 0; server->dialect = le16_to_cpu(rsp->DialectRevision); /* @@ -1172,7 +1175,7 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) } rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, - FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */, + FSCTL_VALIDATE_NEGOTIATE_INFO, (char *)pneg_inbuf, inbuflen, CIFSMaxBufSize, (char **)&pneg_rsp, &rsplen); if (rc == -EOPNOTSUPP) { @@ -1927,7 +1930,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, tcon->capabilities = rsp->Capabilities; /* we keep caps little endian */ tcon->maximal_access = le32_to_cpu(rsp->MaximalAccess); tcon->tid = le32_to_cpu(rsp->hdr.Id.SyncId.TreeId); - strlcpy(tcon->treeName, tree, sizeof(tcon->treeName)); + strscpy(tcon->treeName, tree, sizeof(tcon->treeName)); if ((rsp->Capabilities & SMB2_SHARE_CAP_DFS) && ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0)) @@ -1978,7 +1981,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon) } spin_unlock(&ses->chan_lock); - close_cached_dir_lease(&tcon->crfid); + invalidate_all_cached_dirs(tcon); rc = smb2_plain_req_init(SMB2_TREE_DISCONNECT, tcon, ses->server, (void **) &req, @@ -2571,19 +2574,15 @@ alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len, path_len = UniStrnlen((wchar_t *)path, PATH_MAX); - /* - * make room for one path separator between the treename and - * path - */ - *out_len = treename_len + 1 + path_len; + /* make room for one path separator only if @path isn't empty */ + *out_len = treename_len + (path[0] ? 1 : 0) + path_len; /* - * final path needs to be null-terminated UTF16 with a - * size aligned to 8 + * final path needs to be 8-byte aligned as specified in + * MS-SMB2 2.2.13 SMB2 CREATE Request. */ - - *out_size = roundup((*out_len+1)*2, 8); - *out_path = kzalloc(*out_size, GFP_KERNEL); + *out_size = roundup(*out_len * sizeof(__le16), 8); + *out_path = kzalloc(*out_size + sizeof(__le16) /* null */, GFP_KERNEL); if (!*out_path) return -ENOMEM; @@ -3055,7 +3054,7 @@ int SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, + char *in_data, u32 indatalen, __u32 max_response_size) { struct smb2_ioctl_req *req; @@ -3130,10 +3129,8 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, req->hdr.CreditCharge = cpu_to_le16(DIV_ROUND_UP(max(indatalen, max_response_size), SMB2_MAX_BUFFER_SIZE)); - if (is_fsctl) - req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL); - else - req->Flags = 0; + /* always an FSCTL (for now) */ + req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL); /* validate negotiate request must be signed - see MS-SMB2 3.2.5.5 */ if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO) @@ -3160,9 +3157,9 @@ SMB2_ioctl_free(struct smb_rqst *rqst) */ int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, - u64 volatile_fid, u32 opcode, bool is_fsctl, - char *in_data, u32 indatalen, u32 max_out_data_len, - char **out_data, u32 *plen /* returned data len */) + u64 volatile_fid, u32 opcode, char *in_data, u32 indatalen, + u32 max_out_data_len, char **out_data, + u32 *plen /* returned data len */) { struct smb_rqst rqst; struct smb2_ioctl_rsp *rsp = NULL; @@ -3204,7 +3201,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, rc = SMB2_ioctl_init(tcon, server, &rqst, persistent_fid, volatile_fid, opcode, - is_fsctl, in_data, indatalen, max_out_data_len); + in_data, indatalen, max_out_data_len); if (rc) goto ioctl_exit; @@ -3296,7 +3293,7 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, cpu_to_le16(COMPRESSION_FORMAT_DEFAULT); rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, - FSCTL_SET_COMPRESSION, true /* is_fsctl */, + FSCTL_SET_COMPRESSION, (char *)&fsctl_input /* data input */, 2 /* in data len */, CIFSMaxBufSize /* max out data */, &ret_data /* out data */, NULL); @@ -3776,7 +3773,7 @@ smb2_echo_callback(struct mid_q_entry *mid) credits.instance = server->reconnect_instance; } - DeleteMidQEntry(mid); + release_mid(mid); add_credits(server, &credits, CIFS_ECHO_OP); } @@ -3911,15 +3908,15 @@ SMB2_echo(struct TCP_Server_Info *server) cifs_dbg(FYI, "In echo request for conn_id %lld\n", server->conn_id); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->ops->need_neg && server->ops->need_neg(server)) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); /* No need to send echo on newly established connections */ mod_delayed_work(cifsiod_wq, &server->reconnect, 0); return rc; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); rc = smb2_plain_req_init(SMB2_ECHO, NULL, server, (void **)&req, &total_len); @@ -4201,7 +4198,7 @@ smb2_readv_callback(struct mid_q_entry *mid) rdata->offset, rdata->got_bytes); queue_work(cifsiod_wq, &rdata->work); - DeleteMidQEntry(mid); + release_mid(mid); add_credits(server, &credits, 0); } @@ -4440,7 +4437,7 @@ smb2_writev_callback(struct mid_q_entry *mid) wdata->offset, wdata->bytes); queue_work(cifsiod_wq, &wdata->work); - DeleteMidQEntry(mid); + release_mid(mid); add_credits(server, &credits, 0); } diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index a69f1eed1cfe..3f740f24b96a 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -23,7 +23,7 @@ struct smb_rqst; extern int map_smb2_to_linux_error(char *buf, bool log_err); extern int smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *server); -extern unsigned int smb2_calc_size(void *buf, struct TCP_Server_Info *server); +extern unsigned int smb2_calc_size(void *buf); extern char *smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr); extern __le16 *cifs_convert_path_to_utf16(const char *from, @@ -54,16 +54,6 @@ extern bool smb2_is_valid_oplock_break(char *buffer, extern int smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid); -extern int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, - const char *path, - struct cifs_sb_info *cifs_sb, - struct cached_fid **cfid); -extern int open_cached_dir_by_dentry(struct cifs_tcon *tcon, - struct dentry *dentry, - struct cached_fid **cfid); -extern void close_cached_dir(struct cached_fid *cfid); -extern void close_cached_dir_lease(struct cached_fid *cfid); -extern void close_cached_dir_lease_locked(struct cached_fid *cfid); extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst, struct smb2_file_all_info *src); extern int smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon, @@ -147,13 +137,13 @@ extern int SMB2_open_init(struct cifs_tcon *tcon, extern void SMB2_open_free(struct smb_rqst *rqst); extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, u32 maxoutlen, + char *in_data, u32 indatalen, u32 maxoutlen, char **out_data, u32 *plen /* returned data len */); extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, + char *in_data, u32 indatalen, __u32 max_response_size); extern void SMB2_ioctl_free(struct smb_rqst *rqst); extern int SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 55e79f6ee78d..1a5fc3314dbf 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -640,13 +640,13 @@ smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) if (!is_signed) return 0; - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->ops->need_neg && server->ops->need_neg(server)) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return 0; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); if (!is_binding && !server->session_estab) { strncpy(shdr->Signature, "BSRSPYL", 8); return 0; @@ -750,7 +750,7 @@ smb2_mid_entry_alloc(const struct smb2_hdr *shdr, temp->callback = cifs_wake_up_task; temp->callback_data = current; - atomic_inc(&midCount); + atomic_inc(&mid_count); temp->mid_state = MID_REQUEST_ALLOCATED; trace_smb3_cmd_enter(le32_to_cpu(shdr->Id.SyncId.TreeId), le64_to_cpu(shdr->SessionId), @@ -762,28 +762,30 @@ static int smb2_get_mid_entry(struct cifs_ses *ses, struct TCP_Server_Info *server, struct smb2_hdr *shdr, struct mid_q_entry **mid) { - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsExiting) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return -ENOENT; } if (server->tcpStatus == CifsNeedReconnect) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); cifs_dbg(FYI, "tcp session dead - return to caller to retry\n"); return -EAGAIN; } if (server->tcpStatus == CifsNeedNegotiate && shdr->Command != SMB2_NEGOTIATE) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return -EAGAIN; } + spin_unlock(&server->srv_lock); + spin_lock(&ses->ses_lock); if (ses->ses_status == SES_NEW) { if ((shdr->Command != SMB2_SESSION_SETUP) && (shdr->Command != SMB2_NEGOTIATE)) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); return -EAGAIN; } /* else ok - we are setting up session */ @@ -791,19 +793,19 @@ smb2_get_mid_entry(struct cifs_ses *ses, struct TCP_Server_Info *server, if (ses->ses_status == SES_EXITING) { if (shdr->Command != SMB2_LOGOFF) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); return -EAGAIN; } /* else ok - we are shutting down the session */ } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); *mid = smb2_mid_entry_alloc(shdr, server); if (*mid == NULL) return -ENOMEM; - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); list_add_tail(&(*mid)->qhead, &server->pending_mid_q); - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); return 0; } @@ -854,7 +856,7 @@ smb2_setup_request(struct cifs_ses *ses, struct TCP_Server_Info *server, rc = smb2_sign_rqst(rqst, server); if (rc) { revert_current_mid_from_hdr(server, shdr); - cifs_delete_mid(mid); + delete_mid(mid); return ERR_PTR(rc); } @@ -869,13 +871,13 @@ smb2_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst) (struct smb2_hdr *)rqst->rq_iov[0].iov_base; struct mid_q_entry *mid; - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsNeedNegotiate && shdr->Command != SMB2_NEGOTIATE) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return ERR_PTR(-EAGAIN); } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); smb2_seq_num_into_buf(server, shdr); @@ -888,7 +890,7 @@ smb2_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst) rc = smb2_sign_rqst(rqst, server); if (rc) { revert_current_mid_from_hdr(server, shdr); - DeleteMidQEntry(mid); + release_mid(mid); return ERR_PTR(rc); } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index bfc9bd55870a..c2fe035e573b 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -21,6 +21,7 @@ #include <asm/processor.h> #include <linux/mempool.h> #include <linux/sched/signal.h> +#include <linux/task_io_accounting_ops.h> #include "cifspdu.h" #include "cifsglob.h" #include "cifsproto.h" @@ -37,13 +38,13 @@ cifs_wake_up_task(struct mid_q_entry *mid) wake_up_process(mid->callback_data); } -struct mid_q_entry * -AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) +static struct mid_q_entry * +alloc_mid(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) { struct mid_q_entry *temp; if (server == NULL) { - cifs_dbg(VFS, "Null TCP session in AllocMidQEntry\n"); + cifs_dbg(VFS, "%s: null TCP session\n", __func__); return NULL; } @@ -68,12 +69,12 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) temp->callback = cifs_wake_up_task; temp->callback_data = current; - atomic_inc(&midCount); + atomic_inc(&mid_count); temp->mid_state = MID_REQUEST_ALLOCATED; return temp; } -static void _cifs_mid_q_entry_release(struct kref *refcount) +static void __release_mid(struct kref *refcount) { struct mid_q_entry *midEntry = container_of(refcount, struct mid_q_entry, refcount); @@ -91,7 +92,7 @@ static void _cifs_mid_q_entry_release(struct kref *refcount) server->ops->handle_cancelled_mid(midEntry, server); midEntry->mid_state = MID_FREE; - atomic_dec(&midCount); + atomic_dec(&mid_count); if (midEntry->large_buf) cifs_buf_release(midEntry->resp_buf); else @@ -152,29 +153,26 @@ static void _cifs_mid_q_entry_release(struct kref *refcount) mempool_free(midEntry, cifs_mid_poolp); } -void cifs_mid_q_entry_release(struct mid_q_entry *midEntry) +void release_mid(struct mid_q_entry *mid) { - spin_lock(&GlobalMid_Lock); - kref_put(&midEntry->refcount, _cifs_mid_q_entry_release); - spin_unlock(&GlobalMid_Lock); -} + struct TCP_Server_Info *server = mid->server; -void DeleteMidQEntry(struct mid_q_entry *midEntry) -{ - cifs_mid_q_entry_release(midEntry); + spin_lock(&server->mid_lock); + kref_put(&mid->refcount, __release_mid); + spin_unlock(&server->mid_lock); } void -cifs_delete_mid(struct mid_q_entry *mid) +delete_mid(struct mid_q_entry *mid) { - spin_lock(&GlobalMid_Lock); + spin_lock(&mid->server->mid_lock); if (!(mid->mid_flags & MID_DELETED)) { list_del_init(&mid->qhead); mid->mid_flags |= MID_DELETED; } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&mid->server->mid_lock); - DeleteMidQEntry(mid); + release_mid(mid); } /* @@ -263,8 +261,8 @@ smb_rqst_len(struct TCP_Server_Info *server, struct smb_rqst *rqst) int nvec; unsigned long buflen = 0; - if (server->vals->header_preamble_size == 0 && - rqst->rq_nvec >= 2 && rqst->rq_iov[0].iov_len == 4) { + if (!is_smb1(server) && rqst->rq_nvec >= 2 && + rqst->rq_iov[0].iov_len == 4) { iov = &rqst->rq_iov[1]; nvec = rqst->rq_nvec - 1; } else { @@ -348,7 +346,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, sigprocmask(SIG_BLOCK, &mask, &oldmask); /* Generate a rfc1002 marker for SMB2+ */ - if (server->vals->header_preamble_size == 0) { + if (!is_smb1(server)) { struct kvec hiov = { .iov_base = &rfc1002_marker, .iov_len = 4 @@ -577,12 +575,12 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, } else { spin_unlock(&server->req_lock); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsExiting) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return -ENOENT; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); /* * For normal commands, reserve the last MAX_COMPOUND @@ -725,11 +723,11 @@ cifs_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, static int allocate_mid(struct cifs_ses *ses, struct smb_hdr *in_buf, struct mid_q_entry **ppmidQ) { - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&ses->ses_lock); if (ses->ses_status == SES_NEW) { if ((in_buf->Command != SMB_COM_SESSION_SETUP_ANDX) && (in_buf->Command != SMB_COM_NEGOTIATE)) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); return -EAGAIN; } /* else ok - we are setting up session */ @@ -738,19 +736,19 @@ static int allocate_mid(struct cifs_ses *ses, struct smb_hdr *in_buf, if (ses->ses_status == SES_EXITING) { /* check if SMB session is bad because we are setting it up */ if (in_buf->Command != SMB_COM_LOGOFF_ANDX) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); return -EAGAIN; } /* else ok - we are shutting down session */ } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); - *ppmidQ = AllocMidQEntry(in_buf, ses->server); + *ppmidQ = alloc_mid(in_buf, ses->server); if (*ppmidQ == NULL) return -ENOMEM; - spin_lock(&GlobalMid_Lock); + spin_lock(&ses->server->mid_lock); list_add_tail(&(*ppmidQ)->qhead, &ses->server->pending_mid_q); - spin_unlock(&GlobalMid_Lock); + spin_unlock(&ses->server->mid_lock); return 0; } @@ -782,13 +780,13 @@ cifs_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst) if (server->sign) hdr->Flags2 |= SMBFLG2_SECURITY_SIGNATURE; - mid = AllocMidQEntry(hdr, server); + mid = alloc_mid(hdr, server); if (mid == NULL) return ERR_PTR(-ENOMEM); rc = cifs_sign_rqst(rqst, server, &mid->sequence_number); if (rc) { - DeleteMidQEntry(mid); + release_mid(mid); return ERR_PTR(rc); } @@ -849,9 +847,9 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, mid->mid_state = MID_REQUEST_SUBMITTED; /* put it on the pending_mid_q */ - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); list_add_tail(&mid->qhead, &server->pending_mid_q); - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); /* * Need to store the time in mid before calling I/O. For call_async, @@ -865,7 +863,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, if (rc < 0) { revert_current_mid(server, mid->credits); server->sequence_number -= 2; - cifs_delete_mid(mid); + delete_mid(mid); } cifs_server_unlock(server); @@ -912,10 +910,10 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) cifs_dbg(FYI, "%s: cmd=%d mid=%llu state=%d\n", __func__, le16_to_cpu(mid->command), mid->mid, mid->mid_state); - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); switch (mid->mid_state) { case MID_RESPONSE_RECEIVED: - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); return rc; case MID_RETRY_NEEDED: rc = -EAGAIN; @@ -935,9 +933,9 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) __func__, mid->mid, mid->mid_state); rc = -EIO; } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); - DeleteMidQEntry(mid); + release_mid(mid); return rc; } @@ -997,7 +995,7 @@ cifs_setup_request(struct cifs_ses *ses, struct TCP_Server_Info *ignored, return ERR_PTR(rc); rc = cifs_sign_rqst(rqst, ses->server, &mid->sequence_number); if (rc) { - cifs_delete_mid(mid); + delete_mid(mid); return ERR_PTR(rc); } return mid; @@ -1026,7 +1024,7 @@ static void cifs_cancelled_callback(struct mid_q_entry *mid) { cifs_compound_callback(mid); - DeleteMidQEntry(mid); + release_mid(mid); } /* @@ -1078,12 +1076,12 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, return -EIO; } - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsExiting) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return -ENOENT; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); /* * Wait for all the requests to become available. @@ -1130,7 +1128,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, if (IS_ERR(midQ[i])) { revert_current_mid(server, i); for (j = 0; j < i; j++) - cifs_delete_mid(midQ[j]); + delete_mid(midQ[j]); cifs_server_unlock(server); /* Update # of requests on wire to server */ @@ -1186,17 +1184,17 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, /* * Compounding is never used during session establish. */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&ses->ses_lock); if ((ses->ses_status == SES_NEW) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP)) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); cifs_server_lock(server); smb311_update_preauth_hash(ses, server, rqst[0].rq_iov, rqst[0].rq_nvec); cifs_server_unlock(server); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&ses->ses_lock); } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); for (i = 0; i < num_rqst; i++) { rc = wait_for_response(server, midQ[i]); @@ -1208,14 +1206,14 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, cifs_server_dbg(FYI, "Cancelling wait for mid %llu cmd: %d\n", midQ[i]->mid, le16_to_cpu(midQ[i]->command)); send_cancel(server, &rqst[i], midQ[i]); - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); midQ[i]->mid_flags |= MID_WAIT_CANCELLED; if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) { midQ[i]->callback = cifs_cancelled_callback; cancelled_mid[i] = true; credits[i].value = 0; } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); } } @@ -1240,7 +1238,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, buf = (char *)midQ[i]->resp_buf; resp_iov[i].iov_base = buf; resp_iov[i].iov_len = midQ[i]->resp_buf_size + - server->vals->header_preamble_size; + HEADER_PREAMBLE_SIZE(server); if (midQ[i]->large_buf) resp_buf_type[i] = CIFS_LARGE_BUFFER; @@ -1250,7 +1248,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, rc = server->ops->check_receive(midQ[i], server, flags & CIFS_LOG_ERROR); - /* mark it so buf will not be freed by cifs_delete_mid */ + /* mark it so buf will not be freed by delete_mid */ if ((flags & CIFS_NO_RSP_BUF) == 0) midQ[i]->resp_buf = NULL; @@ -1259,19 +1257,19 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, /* * Compounding is never used during session establish. */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&ses->ses_lock); if ((ses->ses_status == SES_NEW) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP)) { struct kvec iov = { .iov_base = resp_iov[0].iov_base, .iov_len = resp_iov[0].iov_len }; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); cifs_server_lock(server); smb311_update_preauth_hash(ses, server, &iov, 1); cifs_server_unlock(server); - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&ses->ses_lock); } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->ses_lock); out: /* @@ -1282,7 +1280,7 @@ out: */ for (i = 0; i < num_rqst; i++) { if (!cancelled_mid[i]) - cifs_delete_mid(midQ[i]); + delete_mid(midQ[i]); } return rc; @@ -1360,12 +1358,12 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, return -EIO; } - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsExiting) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return -ENOENT; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); /* Ensure that we do not send more than 50 overlapping requests to the same server. We may make this configurable later or @@ -1419,15 +1417,15 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, rc = wait_for_response(server, midQ); if (rc != 0) { send_cancel(server, &rqst, midQ); - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); if (midQ->mid_state == MID_REQUEST_SUBMITTED) { /* no longer considered to be "in-flight" */ - midQ->callback = DeleteMidQEntry; - spin_unlock(&GlobalMid_Lock); + midQ->callback = release_mid; + spin_unlock(&server->mid_lock); add_credits(server, &credits, 0); return rc; } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); } rc = cifs_sync_mid_result(midQ, server); @@ -1447,7 +1445,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, memcpy(out_buf, midQ->resp_buf, *pbytes_returned + 4); rc = cifs_check_receive(midQ, server, 0); out: - cifs_delete_mid(midQ); + delete_mid(midQ); add_credits(server, &credits, 0); return rc; @@ -1505,12 +1503,12 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, return -EIO; } - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if (server->tcpStatus == CifsExiting) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); return -ENOENT; } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); /* Ensure that we do not send more than 50 overlapping requests to the same server. We may make this configurable later or @@ -1540,7 +1538,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_sign_smb(in_buf, server, &midQ->sequence_number); if (rc) { - cifs_delete_mid(midQ); + delete_mid(midQ); cifs_server_unlock(server); return rc; } @@ -1557,7 +1555,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, cifs_server_unlock(server); if (rc < 0) { - cifs_delete_mid(midQ); + delete_mid(midQ); return rc; } @@ -1568,19 +1566,19 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, (server->tcpStatus != CifsNew))); /* Were we interrupted by a signal ? */ - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); if ((rc == -ERESTARTSYS) && (midQ->mid_state == MID_REQUEST_SUBMITTED) && ((server->tcpStatus == CifsGood) || (server->tcpStatus == CifsNew))) { - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); if (in_buf->Command == SMB_COM_TRANSACTION2) { /* POSIX lock. We send a NT_CANCEL SMB to cause the blocking lock to return. */ rc = send_cancel(server, &rqst, midQ); if (rc) { - cifs_delete_mid(midQ); + delete_mid(midQ); return rc; } } else { @@ -1592,7 +1590,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, /* If we get -ENOLCK back the lock may have already been removed. Don't exit in this case. */ if (rc && rc != -ENOLCK) { - cifs_delete_mid(midQ); + delete_mid(midQ); return rc; } } @@ -1600,21 +1598,21 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, rc = wait_for_response(server, midQ); if (rc) { send_cancel(server, &rqst, midQ); - spin_lock(&GlobalMid_Lock); + spin_lock(&server->mid_lock); if (midQ->mid_state == MID_REQUEST_SUBMITTED) { /* no longer considered to be "in-flight" */ - midQ->callback = DeleteMidQEntry; - spin_unlock(&GlobalMid_Lock); + midQ->callback = release_mid; + spin_unlock(&server->mid_lock); return rc; } - spin_unlock(&GlobalMid_Lock); + spin_unlock(&server->mid_lock); } /* We got the response - restart system call. */ rstart = 1; - spin_lock(&cifs_tcp_ses_lock); + spin_lock(&server->srv_lock); } - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&server->srv_lock); rc = cifs_sync_mid_result(midQ, server); if (rc != 0) @@ -1631,8 +1629,185 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, memcpy(out_buf, midQ->resp_buf, *pbytes_returned + 4); rc = cifs_check_receive(midQ, server, 0); out: - cifs_delete_mid(midQ); + delete_mid(midQ); if (rstart && rc == -EACCES) return -ERESTARTSYS; return rc; } + +/* + * Discard any remaining data in the current SMB. To do this, we borrow the + * current bigbuf. + */ +int +cifs_discard_remaining_data(struct TCP_Server_Info *server) +{ + unsigned int rfclen = server->pdu_size; + int remaining = rfclen + HEADER_PREAMBLE_SIZE(server) - + server->total_read; + + while (remaining > 0) { + int length; + + length = cifs_discard_from_socket(server, + min_t(size_t, remaining, + CIFSMaxBufSize + MAX_HEADER_SIZE(server))); + if (length < 0) + return length; + server->total_read += length; + remaining -= length; + } + + return 0; +} + +static int +__cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid, + bool malformed) +{ + int length; + + length = cifs_discard_remaining_data(server); + dequeue_mid(mid, malformed); + mid->resp_buf = server->smallbuf; + server->smallbuf = NULL; + return length; +} + +static int +cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +{ + struct cifs_readdata *rdata = mid->callback_data; + + return __cifs_readv_discard(server, mid, rdata->result); +} + +int +cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) +{ + int length, len; + unsigned int data_offset, data_len; + struct cifs_readdata *rdata = mid->callback_data; + char *buf = server->smallbuf; + unsigned int buflen = server->pdu_size + HEADER_PREAMBLE_SIZE(server); + bool use_rdma_mr = false; + + cifs_dbg(FYI, "%s: mid=%llu offset=%llu bytes=%u\n", + __func__, mid->mid, rdata->offset, rdata->bytes); + + /* + * read the rest of READ_RSP header (sans Data array), or whatever we + * can if there's not enough data. At this point, we've read down to + * the Mid. + */ + len = min_t(unsigned int, buflen, server->vals->read_rsp_size) - + HEADER_SIZE(server) + 1; + + length = cifs_read_from_socket(server, + buf + HEADER_SIZE(server) - 1, len); + if (length < 0) + return length; + server->total_read += length; + + if (server->ops->is_session_expired && + server->ops->is_session_expired(buf)) { + cifs_reconnect(server, true); + return -1; + } + + if (server->ops->is_status_pending && + server->ops->is_status_pending(buf, server)) { + cifs_discard_remaining_data(server); + return -1; + } + + /* set up first two iov for signature check and to get credits */ + rdata->iov[0].iov_base = buf; + rdata->iov[0].iov_len = HEADER_PREAMBLE_SIZE(server); + rdata->iov[1].iov_base = buf + HEADER_PREAMBLE_SIZE(server); + rdata->iov[1].iov_len = + server->total_read - HEADER_PREAMBLE_SIZE(server); + cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n", + rdata->iov[0].iov_base, rdata->iov[0].iov_len); + cifs_dbg(FYI, "1: iov_base=%p iov_len=%zu\n", + rdata->iov[1].iov_base, rdata->iov[1].iov_len); + + /* Was the SMB read successful? */ + rdata->result = server->ops->map_error(buf, false); + if (rdata->result != 0) { + cifs_dbg(FYI, "%s: server returned error %d\n", + __func__, rdata->result); + /* normal error on read response */ + return __cifs_readv_discard(server, mid, false); + } + + /* Is there enough to get to the rest of the READ_RSP header? */ + if (server->total_read < server->vals->read_rsp_size) { + cifs_dbg(FYI, "%s: server returned short header. got=%u expected=%zu\n", + __func__, server->total_read, + server->vals->read_rsp_size); + rdata->result = -EIO; + return cifs_readv_discard(server, mid); + } + + data_offset = server->ops->read_data_offset(buf) + + HEADER_PREAMBLE_SIZE(server); + if (data_offset < server->total_read) { + /* + * win2k8 sometimes sends an offset of 0 when the read + * is beyond the EOF. Treat it as if the data starts just after + * the header. + */ + cifs_dbg(FYI, "%s: data offset (%u) inside read response header\n", + __func__, data_offset); + data_offset = server->total_read; + } else if (data_offset > MAX_CIFS_SMALL_BUFFER_SIZE) { + /* data_offset is beyond the end of smallbuf */ + cifs_dbg(FYI, "%s: data offset (%u) beyond end of smallbuf\n", + __func__, data_offset); + rdata->result = -EIO; + return cifs_readv_discard(server, mid); + } + + cifs_dbg(FYI, "%s: total_read=%u data_offset=%u\n", + __func__, server->total_read, data_offset); + + len = data_offset - server->total_read; + if (len > 0) { + /* read any junk before data into the rest of smallbuf */ + length = cifs_read_from_socket(server, + buf + server->total_read, len); + if (length < 0) + return length; + server->total_read += length; + } + + /* how much data is in the response? */ +#ifdef CONFIG_CIFS_SMB_DIRECT + use_rdma_mr = rdata->mr; +#endif + data_len = server->ops->read_data_length(buf, use_rdma_mr); + if (!use_rdma_mr && (data_offset + data_len > buflen)) { + /* data_len is corrupt -- discard frame */ + rdata->result = -EIO; + return cifs_readv_discard(server, mid); + } + + length = rdata->read_into_pages(server, rdata, data_len); + if (length < 0) + return length; + + server->total_read += length; + + cifs_dbg(FYI, "total_read=%u buflen=%u remaining=%u\n", + server->total_read, buflen, data_len); + + /* discard anything left over */ + if (server->total_read < buflen) + return cifs_readv_discard(server, mid); + + dequeue_mid(mid, false); + mid->resp_buf = server->smallbuf; + server->smallbuf = NULL; + return length; +} diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 9d486fbbfbbd..998fa51f9b68 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -201,6 +201,7 @@ static int cifs_xattr_set(const struct xattr_handler *handler, break; } +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY case XATTR_ACL_ACCESS: #ifdef CONFIG_CIFS_POSIX if (!value) @@ -224,6 +225,7 @@ static int cifs_xattr_set(const struct xattr_handler *handler, cifs_remap(cifs_sb)); #endif /* CONFIG_CIFS_POSIX */ break; +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ } out: @@ -364,7 +366,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler, } break; } - +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY case XATTR_ACL_ACCESS: #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & SB_POSIXACL) @@ -384,6 +386,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler, cifs_remap(cifs_sb)); #endif /* CONFIG_CIFS_POSIX */ break; +#endif /* ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ } /* We could add an additional check for streams ie diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 14e0ef5e9a20..12bd61d20f69 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -86,7 +86,8 @@ static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) /** * fscrypt_fname_encrypt() - encrypt a filename * @inode: inode of the parent directory (for regular filenames) - * or of the symlink (for symlink targets) + * or of the symlink (for symlink targets). Key must already be + * set up. * @iname: the filename to encrypt * @out: (output) the encrypted filename * @olen: size of the encrypted filename. It must be at least @iname->len. @@ -137,6 +138,7 @@ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname, return 0; } +EXPORT_SYMBOL_GPL(fscrypt_fname_encrypt); /** * fname_decrypt() - decrypt a filename @@ -264,9 +266,9 @@ static int fscrypt_base64url_decode(const char *src, int srclen, u8 *dst) return bp - dst; } -bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy, - u32 orig_len, u32 max_len, - u32 *encrypted_len_ret) +bool __fscrypt_fname_encrypted_size(const union fscrypt_policy *policy, + u32 orig_len, u32 max_len, + u32 *encrypted_len_ret) { int padding = 4 << (fscrypt_policy_flags(policy) & FSCRYPT_POLICY_FLAGS_PAD_MASK); @@ -281,6 +283,29 @@ bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy, } /** + * fscrypt_fname_encrypted_size() - calculate length of encrypted filename + * @inode: parent inode of dentry name being encrypted. Key must + * already be set up. + * @orig_len: length of the original filename + * @max_len: maximum length to return + * @encrypted_len_ret: where calculated length should be returned (on success) + * + * Filenames that are shorter than the maximum length may have their lengths + * increased slightly by encryption, due to padding that is applied. + * + * Return: false if the orig_len is greater than max_len. Otherwise, true and + * fill out encrypted_len_ret with the length (up to max_len). + */ +bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len, + u32 max_len, u32 *encrypted_len_ret) +{ + return __fscrypt_fname_encrypted_size(&inode->i_crypt_info->ci_policy, + orig_len, max_len, + encrypted_len_ret); +} +EXPORT_SYMBOL_GPL(fscrypt_fname_encrypted_size); + +/** * fscrypt_fname_alloc_buffer() - allocate a buffer for presented filenames * @max_encrypted_len: maximum length of encrypted filenames the buffer will be * used to present @@ -435,8 +460,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, return ret; if (fscrypt_has_encryption_key(dir)) { - if (!fscrypt_fname_encrypted_size(&dir->i_crypt_info->ci_policy, - iname->len, NAME_MAX, + if (!fscrypt_fname_encrypted_size(dir, iname->len, NAME_MAX, &fname->crypto_buf.len)) return -ENAMETOOLONG; fname->crypto_buf.name = kmalloc(fname->crypto_buf.len, diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index f5be777d8279..3afdaa084773 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -297,14 +297,11 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, const struct fscrypt_info *ci); /* fname.c */ -int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname, - u8 *out, unsigned int olen); -bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy, - u32 orig_len, u32 max_len, - u32 *encrypted_len_ret); +bool __fscrypt_fname_encrypted_size(const union fscrypt_policy *policy, + u32 orig_len, u32 max_len, + u32 *encrypted_len_ret); /* hkdf.c */ - struct fscrypt_hkdf { struct crypto_shash *hmac_tfm; }; diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index af74599ae1cf..7c01025879b3 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -228,9 +228,9 @@ int fscrypt_prepare_symlink(struct inode *dir, const char *target, * counting it (even though it is meaningless for ciphertext) is simpler * for now since filesystems will assume it is there and subtract it. */ - if (!fscrypt_fname_encrypted_size(policy, len, - max_len - sizeof(struct fscrypt_symlink_data), - &disk_link->len)) + if (!__fscrypt_fname_encrypted_size(policy, len, + max_len - sizeof(struct fscrypt_symlink_data), + &disk_link->len)) return -ENAMETOOLONG; disk_link->len += sizeof(struct fscrypt_symlink_data); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 8a054e6d1e68..80b8ca0f340b 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -694,6 +694,32 @@ const union fscrypt_policy *fscrypt_policy_to_inherit(struct inode *dir) } /** + * fscrypt_context_for_new_inode() - create an encryption context for a new inode + * @ctx: where context should be written + * @inode: inode from which to fetch policy and nonce + * + * Given an in-core "prepared" (via fscrypt_prepare_new_inode) inode, + * generate a new context and write it to ctx. ctx _must_ be at least + * FSCRYPT_SET_CONTEXT_MAX_SIZE bytes. + * + * Return: size of the resulting context or a negative error code. + */ +int fscrypt_context_for_new_inode(void *ctx, struct inode *inode) +{ + struct fscrypt_info *ci = inode->i_crypt_info; + + BUILD_BUG_ON(sizeof(union fscrypt_context) != + FSCRYPT_SET_CONTEXT_MAX_SIZE); + + /* fscrypt_prepare_new_inode() should have set up the key already. */ + if (WARN_ON_ONCE(!ci)) + return -ENOKEY; + + return fscrypt_new_context(ctx, &ci->ci_policy, ci->ci_nonce); +} +EXPORT_SYMBOL_GPL(fscrypt_context_for_new_inode); + +/** * fscrypt_set_context() - Set the fscrypt context of a new inode * @inode: a new inode * @fs_data: private data given by FS and passed to ->set_context() @@ -709,12 +735,9 @@ int fscrypt_set_context(struct inode *inode, void *fs_data) union fscrypt_context ctx; int ctxsize; - /* fscrypt_prepare_new_inode() should have set up the key already. */ - if (WARN_ON_ONCE(!ci)) - return -ENOKEY; - - BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE); - ctxsize = fscrypt_new_context(&ctx, &ci->ci_policy, ci->ci_nonce); + ctxsize = fscrypt_context_for_new_inode(&ctx, inode); + if (ctxsize < 0) + return ctxsize; /* * This may be the first time the inode number is available, so do any @@ -334,13 +334,35 @@ static unsigned long dax_end_pfn(void *entry) for (pfn = dax_to_pfn(entry); \ pfn < dax_end_pfn(entry); pfn++) +static inline bool dax_mapping_is_cow(struct address_space *mapping) +{ + return (unsigned long)mapping == PAGE_MAPPING_DAX_COW; +} + /* - * TODO: for reflink+dax we need a way to associate a single page with - * multiple address_space instances at different linear_page_index() - * offsets. + * Set the page->mapping with FS_DAX_MAPPING_COW flag, increase the refcount. + */ +static inline void dax_mapping_set_cow(struct page *page) +{ + if ((uintptr_t)page->mapping != PAGE_MAPPING_DAX_COW) { + /* + * Reset the index if the page was already mapped + * regularly before. + */ + if (page->mapping) + page->index = 1; + page->mapping = (void *)PAGE_MAPPING_DAX_COW; + } + page->index++; +} + +/* + * When it is called in dax_insert_entry(), the cow flag will indicate that + * whether this entry is shared by multiple files. If so, set the page->mapping + * FS_DAX_MAPPING_COW, and use page->index as refcount. */ static void dax_associate_entry(void *entry, struct address_space *mapping, - struct vm_area_struct *vma, unsigned long address) + struct vm_area_struct *vma, unsigned long address, bool cow) { unsigned long size = dax_entry_size(entry), pfn, index; int i = 0; @@ -352,9 +374,13 @@ static void dax_associate_entry(void *entry, struct address_space *mapping, for_each_mapped_pfn(entry, pfn) { struct page *page = pfn_to_page(pfn); - WARN_ON_ONCE(page->mapping); - page->mapping = mapping; - page->index = index + i++; + if (cow) { + dax_mapping_set_cow(page); + } else { + WARN_ON_ONCE(page->mapping); + page->mapping = mapping; + page->index = index + i++; + } } } @@ -370,7 +396,12 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping, struct page *page = pfn_to_page(pfn); WARN_ON_ONCE(trunc && page_ref_count(page) > 1); - WARN_ON_ONCE(page->mapping && page->mapping != mapping); + if (dax_mapping_is_cow(page->mapping)) { + /* keep the CoW flag if this page is still shared */ + if (page->index-- > 0) + continue; + } else + WARN_ON_ONCE(page->mapping && page->mapping != mapping); page->mapping = NULL; page->index = 0; } @@ -456,6 +487,69 @@ void dax_unlock_page(struct page *page, dax_entry_t cookie) } /* + * dax_lock_mapping_entry - Lock the DAX entry corresponding to a mapping + * @mapping: the file's mapping whose entry we want to lock + * @index: the offset within this file + * @page: output the dax page corresponding to this dax entry + * + * Return: A cookie to pass to dax_unlock_mapping_entry() or 0 if the entry + * could not be locked. + */ +dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, pgoff_t index, + struct page **page) +{ + XA_STATE(xas, NULL, 0); + void *entry; + + rcu_read_lock(); + for (;;) { + entry = NULL; + if (!dax_mapping(mapping)) + break; + + xas.xa = &mapping->i_pages; + xas_lock_irq(&xas); + xas_set(&xas, index); + entry = xas_load(&xas); + if (dax_is_locked(entry)) { + rcu_read_unlock(); + wait_entry_unlocked(&xas, entry); + rcu_read_lock(); + continue; + } + if (!entry || + dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { + /* + * Because we are looking for entry from file's mapping + * and index, so the entry may not be inserted for now, + * or even a zero/empty entry. We don't think this is + * an error case. So, return a special value and do + * not output @page. + */ + entry = (void *)~0UL; + } else { + *page = pfn_to_page(dax_to_pfn(entry)); + dax_lock_entry(&xas, entry); + } + xas_unlock_irq(&xas); + break; + } + rcu_read_unlock(); + return (dax_entry_t)entry; +} + +void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index, + dax_entry_t cookie) +{ + XA_STATE(xas, &mapping->i_pages, index); + + if (cookie == ~0UL) + return; + + dax_unlock_entry(&xas, (void *)cookie); +} + +/* * Find page cache entry at given index. If it is a DAX entry, return it * with the entry locked. If the page cache doesn't contain an entry at * that index, add a locked empty entry. @@ -736,22 +830,42 @@ static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter } /* + * MAP_SYNC on a dax mapping guarantees dirty metadata is + * flushed on write-faults (non-cow), but not read-faults. + */ +static bool dax_fault_is_synchronous(const struct iomap_iter *iter, + struct vm_area_struct *vma) +{ + return (iter->flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC) && + (iter->iomap.flags & IOMAP_F_DIRTY); +} + +static bool dax_fault_is_cow(const struct iomap_iter *iter) +{ + return (iter->flags & IOMAP_WRITE) && + (iter->iomap.flags & IOMAP_F_SHARED); +} + +/* * By this point grab_mapping_entry() has ensured that we have a locked entry * of the appropriate size so we don't have to worry about downgrading PMDs to * PTEs. If we happen to be trying to insert a PTE and there is a PMD * already in the tree, we will skip the insertion and just dirty the PMD as * appropriate. */ -static void *dax_insert_entry(struct xa_state *xas, - struct address_space *mapping, struct vm_fault *vmf, - void *entry, pfn_t pfn, unsigned long flags, bool dirty) +static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf, + const struct iomap_iter *iter, void *entry, pfn_t pfn, + unsigned long flags) { + struct address_space *mapping = vmf->vma->vm_file->f_mapping; void *new_entry = dax_make_entry(pfn, flags); + bool dirty = !dax_fault_is_synchronous(iter, vmf->vma); + bool cow = dax_fault_is_cow(iter); if (dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) { + if (cow || (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE))) { unsigned long index = xas->xa_index; /* we are replacing a zero page with block mapping */ if (dax_is_pmd_entry(entry)) @@ -763,11 +877,12 @@ static void *dax_insert_entry(struct xa_state *xas, xas_reset(xas); xas_lock_irq(xas); - if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { + if (cow || dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { void *old; dax_disassociate_entry(entry, mapping, false); - dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address); + dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address, + cow); /* * Only swap our new entry into the page cache if the current * entry is a zero page or an empty entry. If a normal PTE or @@ -787,6 +902,9 @@ static void *dax_insert_entry(struct xa_state *xas, if (dirty) xas_set_mark(xas, PAGECACHE_TAG_DIRTY); + if (cow) + xas_set_mark(xas, PAGECACHE_TAG_TOWRITE); + xas_unlock_irq(xas); return entry; } @@ -931,20 +1049,22 @@ int dax_writeback_mapping_range(struct address_space *mapping, } EXPORT_SYMBOL_GPL(dax_writeback_mapping_range); -static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size, - pfn_t *pfnp) +static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos, + size_t size, void **kaddr, pfn_t *pfnp) { pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); - int id, rc; + int id, rc = 0; long length; id = dax_read_lock(); length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size), - DAX_ACCESS, NULL, pfnp); + DAX_ACCESS, kaddr, pfnp); if (length < 0) { rc = length; goto out; } + if (!pfnp) + goto out_check_addr; rc = -EINVAL; if (PFN_PHYS(length) < size) goto out; @@ -954,11 +1074,71 @@ static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size, if (length > 1 && !pfn_t_devmap(*pfnp)) goto out; rc = 0; + +out_check_addr: + if (!kaddr) + goto out; + if (!*kaddr) + rc = -EFAULT; out: dax_read_unlock(id); return rc; } +/** + * dax_iomap_cow_copy - Copy the data from source to destination before write + * @pos: address to do copy from. + * @length: size of copy operation. + * @align_size: aligned w.r.t align_size (either PMD_SIZE or PAGE_SIZE) + * @srcmap: iomap srcmap + * @daddr: destination address to copy to. + * + * This can be called from two places. Either during DAX write fault (page + * aligned), to copy the length size data to daddr. Or, while doing normal DAX + * write operation, dax_iomap_actor() might call this to do the copy of either + * start or end unaligned address. In the latter case the rest of the copy of + * aligned ranges is taken care by dax_iomap_actor() itself. + */ +static int dax_iomap_cow_copy(loff_t pos, uint64_t length, size_t align_size, + const struct iomap *srcmap, void *daddr) +{ + loff_t head_off = pos & (align_size - 1); + size_t size = ALIGN(head_off + length, align_size); + loff_t end = pos + length; + loff_t pg_end = round_up(end, align_size); + bool copy_all = head_off == 0 && end == pg_end; + void *saddr = 0; + int ret = 0; + + ret = dax_iomap_direct_access(srcmap, pos, size, &saddr, NULL); + if (ret) + return ret; + + if (copy_all) { + ret = copy_mc_to_kernel(daddr, saddr, length); + return ret ? -EIO : 0; + } + + /* Copy the head part of the range */ + if (head_off) { + ret = copy_mc_to_kernel(daddr, saddr, head_off); + if (ret) + return -EIO; + } + + /* Copy the tail part of the range */ + if (end < pg_end) { + loff_t tail_off = head_off + length; + loff_t tail_len = pg_end - end; + + ret = copy_mc_to_kernel(daddr + tail_off, saddr + tail_off, + tail_len); + if (ret) + return -EIO; + } + return 0; +} + /* * The user has performed a load from a hole in the file. Allocating a new * page in the file would cause excessive storage usage for workloads with @@ -966,17 +1146,15 @@ out: * If this page is ever written to we will re-fault and change the mapping to * point to real DAX storage instead. */ -static vm_fault_t dax_load_hole(struct xa_state *xas, - struct address_space *mapping, void **entry, - struct vm_fault *vmf) +static vm_fault_t dax_load_hole(struct xa_state *xas, struct vm_fault *vmf, + const struct iomap_iter *iter, void **entry) { - struct inode *inode = mapping->host; + struct inode *inode = iter->inode; unsigned long vaddr = vmf->address; pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr)); vm_fault_t ret; - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, - DAX_ZERO_PAGE, false); + *entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, DAX_ZERO_PAGE); ret = vmf_insert_mixed(vmf->vma, vaddr, pfn); trace_dax_load_hole(inode, vmf, ret); @@ -985,7 +1163,7 @@ static vm_fault_t dax_load_hole(struct xa_state *xas, #ifdef CONFIG_FS_DAX_PMD static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, - const struct iomap *iomap, void **entry) + const struct iomap_iter *iter, void **entry) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; unsigned long pmd_addr = vmf->address & PMD_MASK; @@ -1003,8 +1181,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, goto fallback; pfn = page_to_pfn_t(zero_page); - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, - DAX_PMD | DAX_ZERO_PAGE, false); + *entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, + DAX_PMD | DAX_ZERO_PAGE); if (arch_needs_pgtable_deposit()) { pgtable = pte_alloc_one(vma->vm_mm); @@ -1037,23 +1215,34 @@ fallback: } #else static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, - const struct iomap *iomap, void **entry) + const struct iomap_iter *iter, void **entry) { return VM_FAULT_FALLBACK; } #endif /* CONFIG_FS_DAX_PMD */ -static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff, - unsigned int offset, size_t size) +static int dax_memzero(struct iomap_iter *iter, loff_t pos, size_t size) { + const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); + unsigned offset = offset_in_page(pos); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); void *kaddr; long ret; - ret = dax_direct_access(dax_dev, pgoff, 1, DAX_ACCESS, &kaddr, NULL); - if (ret > 0) { - memset(kaddr + offset, 0, size); - dax_flush(dax_dev, kaddr + offset, size); - } + ret = dax_direct_access(iomap->dax_dev, pgoff, 1, DAX_ACCESS, &kaddr, + NULL); + if (ret < 0) + return ret; + memset(kaddr + offset, 0, size); + if (srcmap->addr != iomap->addr) { + ret = dax_iomap_cow_copy(pos, size, PAGE_SIZE, srcmap, + kaddr); + if (ret < 0) + return ret; + dax_flush(iomap->dax_dev, kaddr, PAGE_SIZE); + } else + dax_flush(iomap->dax_dev, kaddr + offset, size); return ret; } @@ -1080,7 +1269,7 @@ static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero) if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); else - rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); + rc = dax_memzero(iter, pos, size); dax_read_unlock(id); if (rc < 0) @@ -1129,15 +1318,17 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, struct iov_iter *iter) { const struct iomap *iomap = &iomi->iomap; + const struct iomap *srcmap = &iomi->srcmap; loff_t length = iomap_length(iomi); loff_t pos = iomi->pos; struct dax_device *dax_dev = iomap->dax_dev; loff_t end = pos + length, done = 0; + bool write = iov_iter_rw(iter) == WRITE; ssize_t ret = 0; size_t xfer; int id; - if (iov_iter_rw(iter) == READ) { + if (!write) { end = min(end, i_size_read(iomi->inode)); if (pos >= end) return 0; @@ -1146,7 +1337,12 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, return iov_iter_zero(min(length, end - pos), iter); } - if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED)) + /* + * In DAX mode, enforce either pure overwrites of written extents, or + * writes to unwritten extents as part of a copy-on-write operation. + */ + if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED && + !(iomap->flags & IOMAP_F_SHARED))) return -EIO; /* @@ -1188,6 +1384,14 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, break; } + if (write && + srcmap->type != IOMAP_HOLE && srcmap->addr != iomap->addr) { + ret = dax_iomap_cow_copy(pos, length, PAGE_SIZE, srcmap, + kaddr); + if (ret) + break; + } + map_len = PFN_PHYS(map_len); kaddr += offset; map_len -= offset; @@ -1197,7 +1401,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, if (recovery) xfer = dax_recovery_write(dax_dev, pgoff, kaddr, map_len, iter); - else if (iov_iter_rw(iter) == WRITE) + else if (write) xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr, map_len, iter); else @@ -1268,17 +1472,6 @@ static vm_fault_t dax_fault_return(int error) } /* - * MAP_SYNC on a dax mapping guarantees dirty metadata is - * flushed on write-faults (non-cow), but not read-faults. - */ -static bool dax_fault_is_synchronous(unsigned long flags, - struct vm_area_struct *vma, const struct iomap *iomap) -{ - return (flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC) - && (iomap->flags & IOMAP_F_DIRTY); -} - -/* * When handling a synchronous page fault and the inode need a fsync, we can * insert the PTE/PMD into page tables only after that fsync happened. Skip * insertion for now and return the pfn so that caller can insert it after the @@ -1335,15 +1528,15 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, const struct iomap_iter *iter, pfn_t *pfnp, struct xa_state *xas, void **entry, bool pmd) { - struct address_space *mapping = vmf->vma->vm_file->f_mapping; const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = &iter->srcmap; size_t size = pmd ? PMD_SIZE : PAGE_SIZE; loff_t pos = (loff_t)xas->xa_index << PAGE_SHIFT; - bool write = vmf->flags & FAULT_FLAG_WRITE; - bool sync = dax_fault_is_synchronous(iter->flags, vmf->vma, iomap); + bool write = iter->flags & IOMAP_WRITE; unsigned long entry_flags = pmd ? DAX_PMD : 0; int err = 0; pfn_t pfn; + void *kaddr; if (!pmd && vmf->cow_page) return dax_fault_cow_page(vmf, iter); @@ -1352,23 +1545,29 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, if (!write && (iomap->type == IOMAP_UNWRITTEN || iomap->type == IOMAP_HOLE)) { if (!pmd) - return dax_load_hole(xas, mapping, entry, vmf); - return dax_pmd_load_hole(xas, vmf, iomap, entry); + return dax_load_hole(xas, vmf, iter, entry); + return dax_pmd_load_hole(xas, vmf, iter, entry); } - if (iomap->type != IOMAP_MAPPED) { + if (iomap->type != IOMAP_MAPPED && !(iomap->flags & IOMAP_F_SHARED)) { WARN_ON_ONCE(1); return pmd ? VM_FAULT_FALLBACK : VM_FAULT_SIGBUS; } - err = dax_iomap_pfn(&iter->iomap, pos, size, &pfn); + err = dax_iomap_direct_access(iomap, pos, size, &kaddr, &pfn); if (err) return pmd ? VM_FAULT_FALLBACK : dax_fault_return(err); - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, entry_flags, - write && !sync); + *entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, entry_flags); + + if (write && + srcmap->type != IOMAP_HOLE && srcmap->addr != iomap->addr) { + err = dax_iomap_cow_copy(pos, size, size, srcmap, kaddr); + if (err) + return dax_fault_return(err); + } - if (sync) + if (dax_fault_is_synchronous(iter, vmf->vma)) return dax_fault_synchronous_pfnp(pfnp, pfn); /* insert PMD pfn */ @@ -1674,3 +1873,85 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, return dax_insert_pfn_mkwrite(vmf, pfn, order); } EXPORT_SYMBOL_GPL(dax_finish_sync_fault); + +static loff_t dax_range_compare_iter(struct iomap_iter *it_src, + struct iomap_iter *it_dest, u64 len, bool *same) +{ + const struct iomap *smap = &it_src->iomap; + const struct iomap *dmap = &it_dest->iomap; + loff_t pos1 = it_src->pos, pos2 = it_dest->pos; + void *saddr, *daddr; + int id, ret; + + len = min(len, min(smap->length, dmap->length)); + + if (smap->type == IOMAP_HOLE && dmap->type == IOMAP_HOLE) { + *same = true; + return len; + } + + if (smap->type == IOMAP_HOLE || dmap->type == IOMAP_HOLE) { + *same = false; + return 0; + } + + id = dax_read_lock(); + ret = dax_iomap_direct_access(smap, pos1, ALIGN(pos1 + len, PAGE_SIZE), + &saddr, NULL); + if (ret < 0) + goto out_unlock; + + ret = dax_iomap_direct_access(dmap, pos2, ALIGN(pos2 + len, PAGE_SIZE), + &daddr, NULL); + if (ret < 0) + goto out_unlock; + + *same = !memcmp(saddr, daddr, len); + if (!*same) + len = 0; + dax_read_unlock(id); + return len; + +out_unlock: + dax_read_unlock(id); + return -EIO; +} + +int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dst, loff_t dstoff, loff_t len, bool *same, + const struct iomap_ops *ops) +{ + struct iomap_iter src_iter = { + .inode = src, + .pos = srcoff, + .len = len, + .flags = IOMAP_DAX, + }; + struct iomap_iter dst_iter = { + .inode = dst, + .pos = dstoff, + .len = len, + .flags = IOMAP_DAX, + }; + int ret; + + while ((ret = iomap_iter(&src_iter, ops)) > 0) { + while ((ret = iomap_iter(&dst_iter, ops)) > 0) { + dst_iter.processed = dax_range_compare_iter(&src_iter, + &dst_iter, len, same); + } + if (ret <= 0) + src_iter.processed = ret; + } + return ret; +} + +int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags, + const struct iomap_ops *ops) +{ + return __generic_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags, ops); +} +EXPORT_SYMBOL_GPL(dax_remap_file_range_prep); diff --git a/fs/dcache.c b/fs/dcache.c index ea5cdec24ea7..bb0c4d0038db 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2248,10 +2248,16 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, } EXPORT_SYMBOL(d_add_ci); - -static inline bool d_same_name(const struct dentry *dentry, - const struct dentry *parent, - const struct qstr *name) +/** + * d_same_name - compare dentry name with case-exact name + * @parent: parent dentry + * @dentry: the negative dentry that was passed to the parent's lookup func + * @name: the case-exact name to be associated with the returned dentry + * + * Return: true if names are same, or false + */ +bool d_same_name(const struct dentry *dentry, const struct dentry *parent, + const struct qstr *name) { if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { if (dentry->d_name.len != name->len) @@ -2262,6 +2268,49 @@ static inline bool d_same_name(const struct dentry *dentry, dentry->d_name.len, dentry->d_name.name, name) == 0; } +EXPORT_SYMBOL_GPL(d_same_name); + +/* + * This is __d_lookup_rcu() when the parent dentry has + * DCACHE_OP_COMPARE, which makes things much nastier. + */ +static noinline struct dentry *__d_lookup_rcu_op_compare( + const struct dentry *parent, + const struct qstr *name, + unsigned *seqp) +{ + u64 hashlen = name->hash_len; + struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen)); + struct hlist_bl_node *node; + struct dentry *dentry; + + hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { + int tlen; + const char *tname; + unsigned seq; + +seqretry: + seq = raw_seqcount_begin(&dentry->d_seq); + if (dentry->d_parent != parent) + continue; + if (d_unhashed(dentry)) + continue; + if (dentry->d_name.hash != hashlen_hash(hashlen)) + continue; + tlen = dentry->d_name.len; + tname = dentry->d_name.name; + /* we want a consistent (name,len) pair */ + if (read_seqcount_retry(&dentry->d_seq, seq)) { + cpu_relax(); + goto seqretry; + } + if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) + continue; + *seqp = seq; + return dentry; + } + return NULL; +} /** * __d_lookup_rcu - search for a dentry (racy, store-free) @@ -2309,6 +2358,9 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent, * Keep the two functions in sync. */ + if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) + return __d_lookup_rcu_op_compare(parent, name, seqp); + /* * The hash list is protected using RCU. * @@ -2325,7 +2377,6 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent, hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; -seqretry: /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. @@ -2348,28 +2399,10 @@ seqretry: continue; if (d_unhashed(dentry)) continue; - - if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) { - int tlen; - const char *tname; - if (dentry->d_name.hash != hashlen_hash(hashlen)) - continue; - tlen = dentry->d_name.len; - tname = dentry->d_name.name; - /* we want a consistent (name,len) pair */ - if (read_seqcount_retry(&dentry->d_seq, seq)) { - cpu_relax(); - goto seqretry; - } - if (parent->d_op->d_compare(dentry, - tlen, tname, name) != 0) - continue; - } else { - if (dentry->d_name.hash_len != hashlen) - continue; - if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) - continue; - } + if (dentry->d_name.hash_len != hashlen) + continue; + if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) + continue; *seqp = seq; return dentry; } diff --git a/fs/direct-io.c b/fs/direct-io.c index df5e2d048799..f669163d5860 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -169,7 +169,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) const enum req_op dio_op = dio->opf & REQ_OP_MASK; ssize_t ret; - ret = iov_iter_get_pages(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES, + ret = iov_iter_get_pages2(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES, &sdio->from); if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) { @@ -191,7 +191,6 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) } if (ret >= 0) { - iov_iter_advance(sdio->iter, ret); ret += sdio->from; sdio->head = 0; sdio->tail = (ret + PAGE_SIZE - 1) / PAGE_SIZE; @@ -1251,7 +1250,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, spin_lock_init(&dio->bio_lock); dio->refcount = 1; - dio->should_dirty = iter_is_iovec(iter) && iov_iter_rw(iter) == READ; + dio->should_dirty = user_backed_iter(iter) && iov_iter_rw(iter) == READ; sdio.iter = iter; sdio.final_block_in_request = end >> blkbits; diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 8e01d89c3319..b5fd9d71e67f 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -222,8 +222,10 @@ static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio) rreq = erofs_fscache_alloc_request(folio_mapping(folio), folio_pos(folio), folio_size(folio)); - if (IS_ERR(rreq)) + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); goto out; + } return erofs_fscache_read_folios_async(mdev.m_fscache->cookie, rreq, mdev.m_pa); @@ -301,8 +303,10 @@ static int erofs_fscache_read_folio(struct file *file, struct folio *folio) rreq = erofs_fscache_alloc_request(folio_mapping(folio), folio_pos(folio), folio_size(folio)); - if (IS_ERR(rreq)) + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); goto out_unlock; + } pstart = mdev.m_pa + (pos - map.m_la); return erofs_fscache_read_folios_async(mdev.m_fscache->cookie, diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index cfee49d33b95..a01cc82795a2 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -195,7 +195,6 @@ struct erofs_workgroup { atomic_t refcount; }; -#if defined(CONFIG_SMP) static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp, int val) { @@ -224,34 +223,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) return atomic_cond_read_relaxed(&grp->refcount, VAL != EROFS_LOCKED_MAGIC); } -#else -static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp, - int val) -{ - preempt_disable(); - /* no need to spin on UP platforms, let's just disable preemption. */ - if (val != atomic_read(&grp->refcount)) { - preempt_enable(); - return false; - } - return true; -} - -static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp, - int orig_val) -{ - preempt_enable(); -} - -static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) -{ - int v = atomic_read(&grp->refcount); - - /* workgroup is never freezed on uniprocessor systems */ - DBG_BUGON(v == EROFS_LOCKED_MAGIC); - return v; -} -#endif /* !CONFIG_SMP */ #endif /* !CONFIG_EROFS_FS_ZIP */ /* we strictly follow PAGE_SIZE and no buffer head yet */ diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 95addc5c9d34..3173debeaa5a 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -255,7 +255,8 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, if (IS_ERR(bdev)) return PTR_ERR(bdev); dif->bdev = bdev; - dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off); + dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off, + NULL, NULL); } dif->blocks = le32_to_cpu(dis->blocks); @@ -720,7 +721,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) } sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, - &sbi->dax_part_off); + &sbi->dax_part_off, + NULL, NULL); } err = erofs_read_superblock(sb); @@ -812,7 +814,7 @@ static int erofs_release_device_info(int id, void *ptr, void *data) { struct erofs_device_info *dif = ptr; - fs_put_dax(dif->dax_dev); + fs_put_dax(dif->dax_dev, NULL); if (dif->bdev) blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL); erofs_fscache_unregister_cookie(&dif->fscache); @@ -886,7 +888,7 @@ static void erofs_kill_sb(struct super_block *sb) return; erofs_free_dev_context(sbi->devs); - fs_put_dax(sbi->dax_dev); + fs_put_dax(sbi->dax_dev, NULL); erofs_fscache_unregister_cookie(&sbi->s_fscache); erofs_fscache_unregister_fs(sb); kfree(sbi->opt.fsid); diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c index ec9a1d780dc1..46627cb69abe 100644 --- a/fs/erofs/utils.c +++ b/fs/erofs/utils.c @@ -282,7 +282,7 @@ static struct shrinker erofs_shrinker_info = { int __init erofs_init_shrinker(void) { - return register_shrinker(&erofs_shrinker_info); + return register_shrinker(&erofs_shrinker_info, "erofs-shrinker"); } void erofs_exit_shrinker(void) diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 572f0b8151ba..d58549ca1df9 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -141,7 +141,7 @@ struct z_erofs_maprecorder { u8 type, headtype; u16 clusterofs; u16 delta[2]; - erofs_blk_t pblk, compressedlcs; + erofs_blk_t pblk, compressedblks; erofs_off_t nextpackoff; }; @@ -192,7 +192,7 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, DBG_BUGON(1); return -EFSCORRUPTED; } - m->compressedlcs = m->delta[0] & + m->compressedblks = m->delta[0] & ~Z_EROFS_VLE_DI_D0_CBLKCNT; m->delta[0] = 1; } @@ -293,7 +293,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, DBG_BUGON(1); return -EFSCORRUPTED; } - m->compressedlcs = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; + m->compressedblks = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; m->delta[0] = 1; return 0; } else if (i + 1 != (int)vcnt) { @@ -497,7 +497,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, return 0; } lcn = m->lcn + 1; - if (m->compressedlcs) + if (m->compressedblks) goto out; err = z_erofs_load_cluster_from_disk(m, lcn, false); @@ -506,7 +506,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, /* * If the 1st NONHEAD lcluster has already been handled initially w/o - * valid compressedlcs, which means at least it mustn't be CBLKCNT, or + * valid compressedblks, which means at least it mustn't be CBLKCNT, or * an internal implemenatation error is detected. * * The following code can also handle it properly anyway, but let's @@ -523,12 +523,12 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type * rather than CBLKCNT, it's a 1 lcluster-sized pcluster. */ - m->compressedlcs = 1; + m->compressedblks = 1 << (lclusterbits - LOG_BLOCK_SIZE); break; case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: if (m->delta[0] != 1) goto err_bonus_cblkcnt; - if (m->compressedlcs) + if (m->compressedblks) break; fallthrough; default: @@ -539,7 +539,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, return -EFSCORRUPTED; } out: - map->m_plen = (u64)m->compressedlcs << lclusterbits; + map->m_plen = (u64)m->compressedblks << LOG_BLOCK_SIZE; return 0; err_bonus_cblkcnt: erofs_err(m->inode->i_sb, diff --git a/fs/eventpoll.c b/fs/eventpoll.c index e2daa940ebce..8b56b94e2f56 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1747,6 +1747,21 @@ static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms) return to; } +/* + * autoremove_wake_function, but remove even on failure to wake up, because we + * know that default_wake_function/ttwu will only fail if the thread is already + * woken, and in that case the ep_poll loop will remove the entry anyways, not + * try to reuse it. + */ +static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry, + unsigned int mode, int sync, void *key) +{ + int ret = default_wake_function(wq_entry, mode, sync, key); + + list_del_init(&wq_entry->entry); + return ret; +} + /** * ep_poll - Retrieves ready events, and delivers them to the caller-supplied * event buffer. @@ -1828,8 +1843,15 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, * normal wakeup path no need to call __remove_wait_queue() * explicitly, thus ep->lock is not taken, which halts the * event delivery. + * + * In fact, we now use an even more aggressive function that + * unconditionally removes, because we don't reuse the wait + * entry between loop iterations. This lets us also avoid the + * performance issue if a process is killed, causing all of its + * threads to wake up without being removed normally. */ init_wait(&wait); + wait.func = ep_autoremove_wake_function; write_lock_irq(&ep->lock); /* diff --git a/fs/exec.c b/fs/exec.c index 5fd73915c62c..9a5ca7b82bfc 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -584,11 +584,11 @@ static int copy_strings(int argc, struct user_arg_ptr argv, if (kmapped_page) { flush_dcache_page(kmapped_page); - kunmap(kmapped_page); + kunmap_local(kaddr); put_arg_page(kmapped_page); } kmapped_page = page; - kaddr = kmap(kmapped_page); + kaddr = kmap_local_page(kmapped_page); kpos = pos & PAGE_MASK; flush_arg_page(bprm, kpos, kmapped_page); } @@ -602,7 +602,7 @@ static int copy_strings(int argc, struct user_arg_ptr argv, out: if (kmapped_page) { flush_dcache_page(kmapped_page); - kunmap(kmapped_page); + kunmap_local(kaddr); put_arg_page(kmapped_page); } return ret; @@ -880,11 +880,11 @@ int transfer_args_to_stack(struct linux_binprm *bprm, for (index = MAX_ARG_PAGES - 1; index >= stop; index--) { unsigned int offset = index == stop ? bprm->p & ~PAGE_MASK : 0; - char *src = kmap(bprm->page[index]) + offset; + char *src = kmap_local_page(bprm->page[index]) + offset; sp -= PAGE_SIZE - offset; if (copy_to_user((void *) sp, src, PAGE_SIZE - offset) != 0) ret = -EFAULT; - kunmap(bprm->page[index]); + kunmap_local(src); if (ret) goto out; } @@ -1304,6 +1304,9 @@ int begin_new_exec(struct linux_binprm * bprm) bprm->mm = NULL; #ifdef CONFIG_POSIX_TIMERS + spin_lock_irq(&me->sighand->siglock); + posix_cpu_timers_exit(me); + spin_unlock_irq(&me->sighand->siglock); exit_itimers(me); flush_itimer_signals(); #endif @@ -1683,13 +1686,13 @@ int remove_arg_zero(struct linux_binprm *bprm) ret = -EFAULT; goto out; } - kaddr = kmap_atomic(page); + kaddr = kmap_local_page(page); for (; offset < PAGE_SIZE && kaddr[offset]; offset++, bprm->p++) ; - kunmap_atomic(kaddr); + kunmap_local(kaddr); put_arg_page(page); } while (offset == PAGE_SIZE); diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index 4a7a2308eb72..a8f8eee4937c 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -27,9 +27,9 @@ enum exfat_error_mode { * exfat nls lossy flag */ enum { - NLS_NAME_NO_LOSSY, /* no lossy */ - NLS_NAME_LOSSY, /* just detected incorrect filename(s) */ - NLS_NAME_OVERLEN, /* the length is over than its limit */ + NLS_NAME_NO_LOSSY = 0, /* no lossy */ + NLS_NAME_LOSSY = 1 << 0, /* just detected incorrect filename(s) */ + NLS_NAME_OVERLEN = 1 << 1, /* the length is over than its limit */ }; #define EXFAT_HASH_BITS 8 @@ -483,6 +483,7 @@ struct inode *exfat_build_inode(struct super_block *sb, void exfat_hash_inode(struct inode *inode, loff_t i_pos); void exfat_unhash_inode(struct inode *inode); struct inode *exfat_iget(struct super_block *sb, loff_t i_pos); +int __exfat_write_inode(struct inode *inode, int sync); int exfat_write_inode(struct inode *inode, struct writeback_control *wbc); void exfat_evict_inode(struct inode *inode); int exfat_block_truncate_page(struct inode *inode, loff_t from); @@ -508,14 +509,16 @@ void __exfat_fs_error(struct super_block *sb, int report, const char *fmt, ...) #define exfat_fs_error_ratelimit(sb, fmt, args...) \ __exfat_fs_error(sb, __ratelimit(&EXFAT_SB(sb)->ratelimit), \ fmt, ## args) -void exfat_msg(struct super_block *sb, const char *lv, const char *fmt, ...) - __printf(3, 4) __cold; + +/* expand to pr_*() with prefix */ #define exfat_err(sb, fmt, ...) \ - exfat_msg(sb, KERN_ERR, fmt, ##__VA_ARGS__) + pr_err("exFAT-fs (%s): " fmt "\n", (sb)->s_id, ##__VA_ARGS__) #define exfat_warn(sb, fmt, ...) \ - exfat_msg(sb, KERN_WARNING, fmt, ##__VA_ARGS__) + pr_warn("exFAT-fs (%s): " fmt "\n", (sb)->s_id, ##__VA_ARGS__) #define exfat_info(sb, fmt, ...) \ - exfat_msg(sb, KERN_INFO, fmt, ##__VA_ARGS__) + pr_info("exFAT-fs (%s): " fmt "\n", (sb)->s_id, ##__VA_ARGS__) +#define exfat_debug(sb, fmt, ...) \ + pr_debug("exFAT-fs (%s): " fmt "\n", (sb)->s_id, ##__VA_ARGS__) void exfat_get_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, u8 tz, __le16 time, __le16 date, u8 time_cs); diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index 9de6a6b844c9..ee0b7cf51157 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -331,7 +331,7 @@ int exfat_alloc_cluster(struct inode *inode, unsigned int num_alloc, /* find new cluster */ if (hint_clu == EXFAT_EOF_CLUSTER) { if (sbi->clu_srch_ptr < EXFAT_FIRST_CLUSTER) { - exfat_err(sb, "sbi->clu_srch_ptr is invalid (%u)\n", + exfat_err(sb, "sbi->clu_srch_ptr is invalid (%u)", sbi->clu_srch_ptr); sbi->clu_srch_ptr = EXFAT_FIRST_CLUSTER; } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index 20d4e47f57ab..4e0793f35e8f 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -101,7 +101,6 @@ int __exfat_truncate(struct inode *inode, loff_t new_size) struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); - int evict = (ei->dir.dir == DIR_DELETED) ? 1 : 0; /* check if the given file ID is opened */ if (ei->type != TYPE_FILE && ei->type != TYPE_DIR) @@ -149,50 +148,19 @@ int __exfat_truncate(struct inode *inode, loff_t new_size) if (ei->type == TYPE_FILE) ei->attr |= ATTR_ARCHIVE; - /* update the directory entry */ - if (!evict) { - struct timespec64 ts; - struct exfat_dentry *ep, *ep2; - struct exfat_entry_set_cache *es; - int err; - - es = exfat_get_dentry_set(sb, &(ei->dir), ei->entry, - ES_ALL_ENTRIES); - if (!es) - return -EIO; - ep = exfat_get_dentry_cached(es, 0); - ep2 = exfat_get_dentry_cached(es, 1); - - ts = current_time(inode); - exfat_set_entry_time(sbi, &ts, - &ep->dentry.file.modify_tz, - &ep->dentry.file.modify_time, - &ep->dentry.file.modify_date, - &ep->dentry.file.modify_time_cs); - ep->dentry.file.attr = cpu_to_le16(ei->attr); - - /* File size should be zero if there is no cluster allocated */ - if (ei->start_clu == EXFAT_EOF_CLUSTER) { - ep2->dentry.stream.valid_size = 0; - ep2->dentry.stream.size = 0; - } else { - ep2->dentry.stream.valid_size = cpu_to_le64(new_size); - ep2->dentry.stream.size = ep2->dentry.stream.valid_size; - } - - if (new_size == 0) { - /* Any directory can not be truncated to zero */ - WARN_ON(ei->type != TYPE_FILE); - - ep2->dentry.stream.flags = ALLOC_FAT_CHAIN; - ep2->dentry.stream.start_clu = EXFAT_FREE_CLUSTER; - } - - exfat_update_dir_chksum_with_entry_set(es); - err = exfat_free_dentry_set(es, inode_needs_sync(inode)); - if (err) - return err; - } + /* + * update the directory entry + * + * If the directory entry is updated by mark_inode_dirty(), the + * directory entry will be written after a writeback cycle of + * updating the bitmap/FAT, which may result in clusters being + * freed but referenced by the directory entry in the event of a + * sudden power failure. + * __exfat_write_inode() is called for directory entry, bitmap + * and FAT to be written in a same writeback. + */ + if (__exfat_write_inode(inode, inode_needs_sync(inode))) + return -EIO; /* cut off from the FAT chain */ if (ei->flags == ALLOC_FAT_CHAIN && last_clu != EXFAT_FREE_CLUSTER && @@ -243,12 +211,6 @@ void exfat_truncate(struct inode *inode, loff_t size) if (err) goto write_size; - inode->i_ctime = inode->i_mtime = current_time(inode); - if (IS_DIRSYNC(inode)) - exfat_sync_inode(inode); - else - mark_inode_dirty(inode); - inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> inode->i_blkbits; write_size: @@ -330,6 +292,12 @@ int exfat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, attr->ia_valid &= ~ATTR_MODE; } + if (attr->ia_valid & ATTR_SIZE) + inode->i_mtime = inode->i_ctime = current_time(inode); + + setattr_copy(&init_user_ns, inode, attr); + exfat_truncate_atime(&inode->i_atime); + if (attr->ia_valid & ATTR_SIZE) { error = exfat_block_truncate_page(inode, attr->ia_size); if (error) @@ -337,13 +305,15 @@ int exfat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, down_write(&EXFAT_I(inode)->truncate_lock); truncate_setsize(inode, attr->ia_size); + + /* + * __exfat_write_inode() is called from exfat_truncate(), inode + * is already written by it, so mark_inode_dirty() is unneeded. + */ exfat_truncate(inode, attr->ia_size); up_write(&EXFAT_I(inode)->truncate_lock); - } - - setattr_copy(&init_user_ns, inode, attr); - exfat_truncate_atime(&inode->i_atime); - mark_inode_dirty(inode); + } else + mark_inode_dirty(inode); out: return error; diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index 0133d385d8e8..a795437b86d0 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -17,7 +17,7 @@ #include "exfat_raw.h" #include "exfat_fs.h" -static int __exfat_write_inode(struct inode *inode, int sync) +int __exfat_write_inode(struct inode *inode, int sync) { unsigned long long on_disk_size; struct exfat_dentry *ep, *ep2; @@ -75,6 +75,13 @@ static int __exfat_write_inode(struct inode *inode, int sync) ep2->dentry.stream.valid_size = cpu_to_le64(on_disk_size); ep2->dentry.stream.size = ep2->dentry.stream.valid_size; + if (on_disk_size) { + ep2->dentry.stream.flags = ei->flags; + ep2->dentry.stream.start_clu = cpu_to_le32(ei->start_clu); + } else { + ep2->dentry.stream.flags = ALLOC_FAT_CHAIN; + ep2->dentry.stream.start_clu = EXFAT_FREE_CLUSTER; + } exfat_update_dir_chksum_with_entry_set(es); return exfat_free_dentry_set(es, sync); @@ -105,7 +112,7 @@ void exfat_sync_inode(struct inode *inode) static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, unsigned int *clu, int create) { - int ret, modified = false; + int ret; unsigned int last_clu; struct exfat_chain new_clu; struct super_block *sb = inode->i_sb; @@ -196,7 +203,6 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, if (new_clu.flags == ALLOC_FAT_CHAIN) ei->flags = ALLOC_FAT_CHAIN; ei->start_clu = new_clu.dir; - modified = true; } else { if (new_clu.flags != ei->flags) { /* no-fat-chain bit is disabled, @@ -206,7 +212,6 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters); ei->flags = ALLOC_FAT_CHAIN; - modified = true; } if (new_clu.flags == ALLOC_FAT_CHAIN) if (exfat_ent_set(sb, last_clu, new_clu.dir)) @@ -216,33 +221,6 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, num_clusters += num_to_be_allocated; *clu = new_clu.dir; - if (ei->dir.dir != DIR_DELETED && modified) { - struct exfat_dentry *ep; - struct exfat_entry_set_cache *es; - int err; - - es = exfat_get_dentry_set(sb, &(ei->dir), ei->entry, - ES_ALL_ENTRIES); - if (!es) - return -EIO; - /* get stream entry */ - ep = exfat_get_dentry_cached(es, 1); - - /* update directory entry */ - ep->dentry.stream.flags = ei->flags; - ep->dentry.stream.start_clu = - cpu_to_le32(ei->start_clu); - ep->dentry.stream.valid_size = - cpu_to_le64(i_size_read(inode)); - ep->dentry.stream.size = - ep->dentry.stream.valid_size; - - exfat_update_dir_chksum_with_entry_set(es); - err = exfat_free_dentry_set(es, inode_needs_sync(inode)); - if (err) - return err; - } /* end of if != DIR_DELETED */ - inode->i_blocks += num_to_be_allocated << sbi->sect_per_clus_bits; @@ -384,6 +362,7 @@ static void exfat_write_failed(struct address_space *mapping, loff_t to) if (to > i_size_read(inode)) { truncate_pagecache(inode, i_size_read(inode)); + inode->i_mtime = inode->i_ctime = current_time(inode); exfat_truncate(inode, EXFAT_I(inode)->i_size_aligned); } } diff --git a/fs/exfat/misc.c b/fs/exfat/misc.c index 9380e0188b55..2e1a1a6b1021 100644 --- a/fs/exfat/misc.c +++ b/fs/exfat/misc.c @@ -46,23 +46,6 @@ void __exfat_fs_error(struct super_block *sb, int report, const char *fmt, ...) } } -/* - * exfat_msg() - print preformated EXFAT specific messages. - * All logs except what uses exfat_fs_error() should be written by exfat_msg() - */ -void exfat_msg(struct super_block *sb, const char *level, const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - va_start(args, fmt); - vaf.fmt = fmt; - vaf.va = &args; - /* level means KERN_ pacility level */ - printk("%sexFAT-fs (%s): %pV\n", level, sb->s_id, &vaf); - va_end(args); -} - #define SECS_PER_MIN (60) #define TIMEZONE_SEC(x) ((x) * 15 * SECS_PER_MIN) diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index c6eaf7e9ea74..b617bebc3d0f 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -318,7 +318,6 @@ static int exfat_find_empty_entry(struct inode *inode, unsigned int ret, last_clu; loff_t size = 0; struct exfat_chain clu; - struct exfat_dentry *ep = NULL; struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); @@ -383,25 +382,6 @@ static int exfat_find_empty_entry(struct inode *inode, p_dir->size++; size = EXFAT_CLU_TO_B(p_dir->size, sbi); - /* update the directory entry */ - if (p_dir->dir != sbi->root_dir) { - struct buffer_head *bh; - - ep = exfat_get_dentry(sb, - &(ei->dir), ei->entry + 1, &bh); - if (!ep) - return -EIO; - - ep->dentry.stream.valid_size = cpu_to_le64(size); - ep->dentry.stream.size = ep->dentry.stream.valid_size; - ep->dentry.stream.flags = p_dir->flags; - exfat_update_bh(bh, IS_DIRSYNC(inode)); - brelse(bh); - if (exfat_update_dir_chksum(inode, &(ei->dir), - ei->entry)) - return -EIO; - } - /* directory inode should be updated in here */ i_size_write(inode, size); ei->i_size_ondisk += sbi->cluster_size; @@ -462,7 +442,7 @@ static int __exfat_resolve_path(struct inode *inode, const unsigned char *path, return namelen; /* return error value */ if ((lossy && !lookup) || !namelen) - return -EINVAL; + return (lossy & NLS_NAME_OVERLEN) ? -ENAMETOOLONG : -EINVAL; exfat_chain_set(p_dir, ei->start_clu, EXFAT_B_TO_CLU(i_size_read(inode), sbi), ei->flags); diff --git a/fs/exfat/nls.c b/fs/exfat/nls.c index ef115e673406..705710f93e2d 100644 --- a/fs/exfat/nls.c +++ b/fs/exfat/nls.c @@ -509,7 +509,7 @@ static int exfat_utf8_to_utf16(struct super_block *sb, } if (unilen > MAX_NAME_LENGTH) { - exfat_err(sb, "failed to %s (estr:ENAMETOOLONG) nls len : %d, unilen : %d > %d", + exfat_debug(sb, "failed to %s (estr:ENAMETOOLONG) nls len : %d, unilen : %d > %d", __func__, len, unilen, MAX_NAME_LENGTH); return -ENAMETOOLONG; } @@ -671,7 +671,7 @@ static int exfat_load_upcase_table(struct super_block *sb, bh = sb_bread(sb, sector); if (!bh) { - exfat_err(sb, "failed to read sector(0x%llx)\n", + exfat_err(sb, "failed to read sector(0x%llx)", (unsigned long long)sector); ret = -EIO; goto free_table; diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 6a4dfe9f31ee..35f0305cd493 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -464,7 +464,7 @@ static int exfat_read_boot_sector(struct super_block *sb) */ if (p_boot->sect_size_bits < EXFAT_MIN_SECT_SIZE_BITS || p_boot->sect_size_bits > EXFAT_MAX_SECT_SIZE_BITS) { - exfat_err(sb, "bogus sector size bits : %u\n", + exfat_err(sb, "bogus sector size bits : %u", p_boot->sect_size_bits); return -EINVAL; } @@ -473,7 +473,7 @@ static int exfat_read_boot_sector(struct super_block *sb) * sect_per_clus_bits could be at least 0 and at most 25 - sect_size_bits. */ if (p_boot->sect_per_clus_bits > EXFAT_MAX_SECT_PER_CLUS_BITS(p_boot)) { - exfat_err(sb, "bogus sectors bits per cluster : %u\n", + exfat_err(sb, "bogus sectors bits per cluster : %u", p_boot->sect_per_clus_bits); return -EINVAL; } diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 27a0a8c74f7a..252c742379cf 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -171,7 +171,7 @@ static void ext2_put_super (struct super_block * sb) brelse (sbi->s_sbh); sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); - fs_put_dax(sbi->s_daxdev); + fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); } @@ -833,7 +833,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } sb->s_fs_info = sbi; sbi->s_sb_block = sb_block; - sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off); + sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off, + NULL, NULL); spin_lock_init(&sbi->s_lock); ret = -EINVAL; @@ -1210,7 +1211,7 @@ failed_mount_group_desc: failed_mount: brelse(bh); failed_sbi: - fs_put_dax(sbi->s_daxdev); + fs_put_dax(sbi->s_daxdev, NULL); sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); kfree(sbi); diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 841fa6d9d744..641abfa4b718 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -517,36 +517,36 @@ bad_block: /* Here we know that we can set the new attribute. */ if (header) { - /* assert(header == HDR(bh)); */ + int offset; + lock_buffer(bh); if (header->h_refcount == cpu_to_le32(1)) { __u32 hash = le32_to_cpu(header->h_hash); + struct mb_cache_entry *oe; - ea_bdebug(bh, "modifying in-place"); + oe = mb_cache_entry_delete_or_get(EA_BLOCK_CACHE(inode), + hash, bh->b_blocknr); + if (!oe) { + ea_bdebug(bh, "modifying in-place"); + goto update_block; + } /* - * This must happen under buffer lock for - * ext2_xattr_set2() to reliably detect modified block + * Someone is trying to reuse the block, leave it alone */ - mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash, - bh->b_blocknr); - - /* keep the buffer locked while modifying it. */ - } else { - int offset; - - unlock_buffer(bh); - ea_bdebug(bh, "cloning"); - header = kmemdup(HDR(bh), bh->b_size, GFP_KERNEL); - error = -ENOMEM; - if (header == NULL) - goto cleanup; - header->h_refcount = cpu_to_le32(1); - - offset = (char *)here - bh->b_data; - here = ENTRY((char *)header + offset); - offset = (char *)last - bh->b_data; - last = ENTRY((char *)header + offset); + mb_cache_entry_put(EA_BLOCK_CACHE(inode), oe); } + unlock_buffer(bh); + ea_bdebug(bh, "cloning"); + header = kmemdup(HDR(bh), bh->b_size, GFP_KERNEL); + error = -ENOMEM; + if (header == NULL) + goto cleanup; + header->h_refcount = cpu_to_le32(1); + + offset = (char *)here - bh->b_data; + here = ENTRY((char *)header + offset); + offset = (char *)last - bh->b_data; + last = ENTRY((char *)header + offset); } else { /* Allocate a buffer where we construct the new block. */ header = kzalloc(sb->s_blocksize, GFP_KERNEL); @@ -559,6 +559,7 @@ bad_block: last = here = ENTRY(header+1); } +update_block: /* Iff we are modifying the block in-place, bh is locked here. */ if (not_found) { @@ -651,6 +652,55 @@ cleanup: return error; } +static void ext2_xattr_release_block(struct inode *inode, + struct buffer_head *bh) +{ + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); + +retry_ref: + lock_buffer(bh); + if (HDR(bh)->h_refcount == cpu_to_le32(1)) { + __u32 hash = le32_to_cpu(HDR(bh)->h_hash); + struct mb_cache_entry *oe; + + /* + * This must happen under buffer lock to properly + * serialize with ext2_xattr_set() reusing the block. + */ + oe = mb_cache_entry_delete_or_get(ea_block_cache, hash, + bh->b_blocknr); + if (oe) { + /* + * Someone is trying to reuse the block. Wait + * and retry. + */ + unlock_buffer(bh); + mb_cache_entry_wait_unused(oe); + mb_cache_entry_put(ea_block_cache, oe); + goto retry_ref; + } + + /* Free the old block. */ + ea_bdebug(bh, "freeing"); + ext2_free_blocks(inode, bh->b_blocknr, 1); + /* We let our caller release bh, so we + * need to duplicate the buffer before. */ + get_bh(bh); + bforget(bh); + unlock_buffer(bh); + } else { + /* Decrement the refcount only. */ + le32_add_cpu(&HDR(bh)->h_refcount, -1); + dquot_free_block(inode, 1); + mark_buffer_dirty(bh); + unlock_buffer(bh); + ea_bdebug(bh, "refcount now=%d", + le32_to_cpu(HDR(bh)->h_refcount)); + if (IS_SYNC(inode)) + sync_dirty_buffer(bh); + } +} + /* * Second half of ext2_xattr_set(): Update the file system. */ @@ -747,34 +797,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, * If there was an old block and we are no longer using it, * release the old block. */ - lock_buffer(old_bh); - if (HDR(old_bh)->h_refcount == cpu_to_le32(1)) { - __u32 hash = le32_to_cpu(HDR(old_bh)->h_hash); - - /* - * This must happen under buffer lock for - * ext2_xattr_set2() to reliably detect freed block - */ - mb_cache_entry_delete(ea_block_cache, hash, - old_bh->b_blocknr); - /* Free the old block. */ - ea_bdebug(old_bh, "freeing"); - ext2_free_blocks(inode, old_bh->b_blocknr, 1); - mark_inode_dirty(inode); - /* We let our caller release old_bh, so we - * need to duplicate the buffer before. */ - get_bh(old_bh); - bforget(old_bh); - } else { - /* Decrement the refcount only. */ - le32_add_cpu(&HDR(old_bh)->h_refcount, -1); - dquot_free_block_nodirty(inode, 1); - mark_inode_dirty(inode); - mark_buffer_dirty(old_bh); - ea_bdebug(old_bh, "refcount now=%d", - le32_to_cpu(HDR(old_bh)->h_refcount)); - } - unlock_buffer(old_bh); + ext2_xattr_release_block(inode, old_bh); } cleanup: @@ -828,30 +851,7 @@ ext2_xattr_delete_inode(struct inode *inode) EXT2_I(inode)->i_file_acl); goto cleanup; } - lock_buffer(bh); - if (HDR(bh)->h_refcount == cpu_to_le32(1)) { - __u32 hash = le32_to_cpu(HDR(bh)->h_hash); - - /* - * This must happen under buffer lock for ext2_xattr_set2() to - * reliably detect freed block - */ - mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash, - bh->b_blocknr); - ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1); - get_bh(bh); - bforget(bh); - unlock_buffer(bh); - } else { - le32_add_cpu(&HDR(bh)->h_refcount, -1); - ea_bdebug(bh, "refcount now=%d", - le32_to_cpu(HDR(bh)->h_refcount)); - unlock_buffer(bh); - mark_buffer_dirty(bh); - if (IS_SYNC(inode)) - sync_dirty_buffer(bh); - dquot_free_block_nodirty(inode, 1); - } + ext2_xattr_release_block(inode, bh); EXT2_I(inode)->i_file_acl = 0; cleanup: @@ -943,7 +943,7 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header) if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); -again: + ce = mb_cache_entry_find_first(ea_block_cache, hash); while (ce) { struct buffer_head *bh; @@ -955,22 +955,8 @@ again: inode->i_ino, (unsigned long) ce->e_value); } else { lock_buffer(bh); - /* - * We have to be careful about races with freeing or - * rehashing of xattr block. Once we hold buffer lock - * xattr block's state is stable so we can check - * whether the block got freed / rehashed or not. - * Since we unhash mbcache entry under buffer lock when - * freeing / rehashing xattr block, checking whether - * entry is still hashed is reliable. - */ - if (hlist_bl_unhashed(&ce->e_hash_list)) { - mb_cache_entry_put(ea_block_cache, ce); - unlock_buffer(bh); - brelse(bh); - goto again; - } else if (le32_to_cpu(HDR(bh)->h_refcount) > - EXT2_XATTR_REFCOUNT_MAX) { + if (le32_to_cpu(HDR(bh)->h_refcount) > + EXT2_XATTR_REFCOUNT_MAX) { ea_idebug(inode, "block %ld refcount %d>%d", (unsigned long) ce->e_value, le32_to_cpu(HDR(bh)->h_refcount), diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 78ee3ef795ae..8ff4b9192a9f 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -666,7 +666,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries) * it's possible we've just missed a transaction commit here, * so ignore the returned status */ - jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id); + ext4_debug("%s: retrying operation after ENOSPC\n", sb->s_id); (void) jbd2_journal_force_commit_nested(sbi->s_journal); return 1; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 29fc575a4eb6..9bca5565547b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -724,6 +724,8 @@ enum { #define EXT4_IOC_GETSTATE _IOW('f', 41, __u32) #define EXT4_IOC_GET_ES_CACHE _IOWR('f', 42, struct fiemap) #define EXT4_IOC_CHECKPOINT _IOW('f', 43, __u32) +#define EXT4_IOC_GETFSUUID _IOR('f', 44, struct fsuuid) +#define EXT4_IOC_SETFSUUID _IOW('f', 44, struct fsuuid) #define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32) @@ -753,6 +755,15 @@ enum { EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT | \ EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN) +/* + * Structure for EXT4_IOC_GETFSUUID/EXT4_IOC_SETFSUUID + */ +struct fsuuid { + __u32 fsu_len; + __u32 fsu_flags; + __u8 fsu_uuid[]; +}; + #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* * ioctl commands in 32 bit emulation @@ -3016,7 +3027,7 @@ int ext4_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, struct fileattr *fa); int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa); extern void ext4_reset_inode_seed(struct inode *inode); -int ext4_update_overhead(struct super_block *sb); +int ext4_update_overhead(struct super_block *sb, bool force); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); @@ -3583,6 +3594,7 @@ extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode, extern int ext4_inline_data_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, int *has_inline, __u64 start, __u64 len); +extern void *ext4_read_inline_link(struct inode *inode); struct iomap; extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap); @@ -3799,7 +3811,7 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh) extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; extern int ext4_resize_begin(struct super_block *sb); -extern void ext4_resize_end(struct super_block *sb); +extern int ext4_resize_end(struct super_block *sb, bool update_backups); static inline void ext4_set_io_unwritten_flag(struct inode *inode, struct ext4_io_end *io_end) diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 3477a16d08ae..8e1fb18f465e 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -267,8 +267,7 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle, trace_ext4_forget(inode, is_metadata, blocknr); BUFFER_TRACE(bh, "enter"); - jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, " - "data mode %x\n", + ext4_debug("forgetting bh %p: is_metadata=%d, mode %o, data mode %x\n", bh, is_metadata, inode->i_mode, test_opt(inode->i_sb, DATA_FLAGS)); diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 9a3a8996aacf..23167efda95e 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -1654,7 +1654,8 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi) sbi->s_es_shrinker.scan_objects = ext4_es_scan; sbi->s_es_shrinker.count_objects = ext4_es_count; sbi->s_es_shrinker.seeks = DEFAULT_SEEKS; - err = register_shrinker(&sbi->s_es_shrinker); + err = register_shrinker(&sbi->s_es_shrinker, "ext4-es:%s", + sbi->s_sb->s_id); if (err) goto err4; diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index eb4c8ad1bb61..2af962cbb835 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -917,8 +917,8 @@ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc) mutex_unlock(&ei->i_fc_lock); cur_lblk_off = old_blk_size; - jbd_debug(1, "%s: will try writing %d to %d for inode %ld\n", - __func__, cur_lblk_off, new_blk_size, inode->i_ino); + ext4_debug("will try writing %d to %d for inode %ld\n", + cur_lblk_off, new_blk_size, inode->i_ino); while (cur_lblk_off <= new_blk_size) { map.m_lblk = cur_lblk_off; @@ -1168,7 +1168,7 @@ static void ext4_fc_update_stats(struct super_block *sb, int status, { struct ext4_fc_stats *stats = &EXT4_SB(sb)->s_fc_stats; - jbd_debug(1, "Fast commit ended with status = %d for tid %u", + ext4_debug("Fast commit ended with status = %d for tid %u", status, commit_tid); if (status == EXT4_FC_STATUS_OK) { stats->fc_num_commits++; @@ -1375,14 +1375,14 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl, inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode %d not found", darg.ino); + ext4_debug("Inode %d not found", darg.ino); return 0; } old_parent = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(old_parent)) { - jbd_debug(1, "Dir with inode %d not found", darg.parent_ino); + ext4_debug("Dir with inode %d not found", darg.parent_ino); iput(inode); return 0; } @@ -1407,21 +1407,21 @@ static int ext4_fc_replay_link_internal(struct super_block *sb, dir = ext4_iget(sb, darg->parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(dir)) { - jbd_debug(1, "Dir with inode %d not found.", darg->parent_ino); + ext4_debug("Dir with inode %d not found.", darg->parent_ino); dir = NULL; goto out; } dentry_dir = d_obtain_alias(dir); if (IS_ERR(dentry_dir)) { - jbd_debug(1, "Failed to obtain dentry"); + ext4_debug("Failed to obtain dentry"); dentry_dir = NULL; goto out; } dentry_inode = d_alloc(dentry_dir, &qstr_dname); if (!dentry_inode) { - jbd_debug(1, "Inode dentry not created."); + ext4_debug("Inode dentry not created."); ret = -ENOMEM; goto out; } @@ -1434,7 +1434,7 @@ static int ext4_fc_replay_link_internal(struct super_block *sb, * could complete. */ if (ret && ret != -EEXIST) { - jbd_debug(1, "Failed to link\n"); + ext4_debug("Failed to link\n"); goto out; } @@ -1468,7 +1468,7 @@ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl, inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode not found."); + ext4_debug("Inode not found."); return 0; } @@ -1576,7 +1576,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, /* Given that we just wrote the inode on disk, this SHOULD succeed. */ inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode not found."); + ext4_debug("Inode not found."); return -EFSCORRUPTED; } @@ -1630,7 +1630,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl, inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "inode %d not found.", darg.ino); + ext4_debug("inode %d not found.", darg.ino); inode = NULL; ret = -EINVAL; goto out; @@ -1643,7 +1643,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl, */ dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(dir)) { - jbd_debug(1, "Dir %d not found.", darg.ino); + ext4_debug("Dir %d not found.", darg.ino); goto out; } ret = ext4_init_new_dir(NULL, dir, inode); @@ -1727,7 +1727,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb, inode = ext4_iget(sb, le32_to_cpu(fc_add_ex.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode not found."); + ext4_debug("Inode not found."); return 0; } @@ -1741,7 +1741,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb, cur = start; remaining = len; - jbd_debug(1, "ADD_RANGE, lblk %d, pblk %lld, len %d, unwritten %d, inode %ld\n", + ext4_debug("ADD_RANGE, lblk %d, pblk %lld, len %d, unwritten %d, inode %ld\n", start, start_pblk, len, ext4_ext_is_unwritten(ex), inode->i_ino); @@ -1802,7 +1802,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb, } /* Range is mapped and needs a state change */ - jbd_debug(1, "Converting from %ld to %d %lld", + ext4_debug("Converting from %ld to %d %lld", map.m_flags & EXT4_MAP_UNWRITTEN, ext4_ext_is_unwritten(ex), map.m_pblk); ret = ext4_ext_replay_update_ex(inode, cur, map.m_len, @@ -1845,7 +1845,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl, inode = ext4_iget(sb, le32_to_cpu(lrange.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange.fc_ino)); + ext4_debug("Inode %d not found", le32_to_cpu(lrange.fc_ino)); return 0; } @@ -1853,7 +1853,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl, if (ret) goto out; - jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n", + ext4_debug("DEL_RANGE, inode %ld, lblk %d, len %d\n", inode->i_ino, le32_to_cpu(lrange.fc_lblk), le32_to_cpu(lrange.fc_len)); while (remaining > 0) { @@ -1902,7 +1902,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) inode = ext4_iget(sb, state->fc_modified_inodes[i], EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode %d not found.", + ext4_debug("Inode %d not found.", state->fc_modified_inodes[i]); continue; } @@ -2031,7 +2031,7 @@ static int ext4_fc_replay_scan(journal_t *journal, for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) { memcpy(&tl, cur, sizeof(tl)); val = cur + sizeof(tl); - jbd_debug(3, "Scan phase, tag:%s, blk %lld\n", + ext4_debug("Scan phase, tag:%s, blk %lld\n", tag2str(le16_to_cpu(tl.fc_tag)), bh->b_blocknr); switch (le16_to_cpu(tl.fc_tag)) { case EXT4_FC_TAG_ADD_RANGE: @@ -2126,7 +2126,7 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, sbi->s_mount_state |= EXT4_FC_REPLAY; } if (!sbi->s_fc_replay_state.fc_replay_num_tags) { - jbd_debug(1, "Replay stops\n"); + ext4_debug("Replay stops\n"); ext4_fc_set_bitmaps_and_counters(sb); return 0; } @@ -2150,7 +2150,7 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, ext4_fc_set_bitmaps_and_counters(sb); break; } - jbd_debug(3, "Replay phase, tag:%s\n", + ext4_debug("Replay phase, tag:%s\n", tag2str(le16_to_cpu(tl.fc_tag))); state->fc_replay_num_tags--; switch (le16_to_cpu(tl.fc_tag)) { diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 07a8c75b65ed..860fc5119009 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -460,7 +460,7 @@ static int ext4_splice_branch(handle_t *handle, * the new i_size. But that is not done here - it is done in * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode. */ - jbd_debug(5, "splicing indirect only\n"); + ext4_debug("splicing indirect only\n"); BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, ar->inode, where->bh); if (err) @@ -472,7 +472,7 @@ static int ext4_splice_branch(handle_t *handle, err = ext4_mark_inode_dirty(handle, ar->inode); if (unlikely(err)) goto err_out; - jbd_debug(5, "splicing direct\n"); + ext4_debug("splicing direct\n"); } return err; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index cff52ff6549d..a4fbe825694b 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -6,6 +6,7 @@ #include <linux/iomap.h> #include <linux/fiemap.h> +#include <linux/namei.h> #include <linux/iversion.h> #include <linux/sched/mm.h> @@ -35,6 +36,9 @@ static int get_max_inline_xattr_value_size(struct inode *inode, struct ext4_inode *raw_inode; int free, min_offs; + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) + return 0; + min_offs = EXT4_SB(inode->i_sb)->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE - EXT4_I(inode)->i_extra_isize - @@ -1588,6 +1592,35 @@ out: return ret; } +void *ext4_read_inline_link(struct inode *inode) +{ + struct ext4_iloc iloc; + int ret, inline_size; + void *link; + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + return ERR_PTR(ret); + + ret = -ENOMEM; + inline_size = ext4_get_inline_size(inode); + link = kmalloc(inline_size + 1, GFP_NOFS); + if (!link) + goto out; + + ret = ext4_read_inline_data(inode, link, inline_size, &iloc); + if (ret < 0) { + kfree(link); + goto out; + } + nd_terminate_link(link, inode->i_size, ret); +out: + if (ret < 0) + link = ERR_PTR(ret); + brelse(iloc.bh); + return link; +} + struct buffer_head *ext4_get_first_inline_block(struct inode *inode, struct ext4_dir_entry_2 **parent_de, int *retval) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9fd60fc8ba4c..601214453c3a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -177,6 +177,8 @@ void ext4_evict_inode(struct inode *inode) trace_ext4_evict_inode(inode); + if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL) + ext4_evict_ea_inode(inode); if (inode->i_nlink) { /* * When journalling data dirty buffers are tracked only in the @@ -1571,7 +1573,14 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd, ext4_lblk_t start, last; start = index << (PAGE_SHIFT - inode->i_blkbits); last = end << (PAGE_SHIFT - inode->i_blkbits); + + /* + * avoid racing with extent status tree scans made by + * ext4_insert_delayed_block() + */ + down_write(&EXT4_I(inode)->i_data_sem); ext4_es_remove_extent(inode, start, last - start + 1); + up_write(&EXT4_I(inode)->i_data_sem); } folio_batch_init(&fbatch); @@ -3142,13 +3151,15 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; journal_t *journal; + sector_t ret = 0; int err; + inode_lock_shared(inode); /* * We can get here for an inline file via the FIBMAP ioctl */ if (ext4_has_inline_data(inode)) - return 0; + goto out; if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && test_opt(inode->i_sb, DELALLOC)) { @@ -3187,10 +3198,14 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) jbd2_journal_unlock_updates(journal); if (err) - return 0; + goto out; } - return iomap_bmap(mapping, block, &ext4_iomap_ops); + ret = iomap_bmap(mapping, block, &ext4_iomap_ops); + +out: + inode_unlock_shared(inode); + return ret; } static int ext4_read_folio(struct file *file, struct folio *folio) @@ -4687,8 +4702,7 @@ static inline int ext4_iget_extra_inode(struct inode *inode, __le32 *magic = (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize; - if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <= - EXT4_INODE_SIZE(inode->i_sb) && + if (EXT4_INODE_HAS_XATTR_SPACE(inode) && *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { ext4_set_inode_state(inode, EXT4_STATE_XATTR); return ext4_find_inline_data_nolock(inode); @@ -5215,7 +5229,7 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) if (EXT4_SB(inode->i_sb)->s_journal) { if (ext4_journal_current_handle()) { - jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n"); + ext4_debug("called recursively, non-PF_MEMALLOC!\n"); dump_stack(); return -EIO; } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index cb01c1da0f9d..3cf3ec4b1c21 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -20,6 +20,7 @@ #include <linux/delay.h> #include <linux/iversion.h> #include <linux/fileattr.h> +#include <linux/uuid.h> #include "ext4_jbd2.h" #include "ext4.h" #include <linux/fsmap.h> @@ -41,6 +42,15 @@ static void ext4_sb_setlabel(struct ext4_super_block *es, const void *arg) memcpy(es->s_volume_name, (char *)arg, EXT4_LABEL_MAX); } +/* + * Superblock modification callback function for changing file system + * UUID. + */ +static void ext4_sb_setuuid(struct ext4_super_block *es, const void *arg) +{ + memcpy(es->s_uuid, (__u8 *)arg, UUID_SIZE); +} + static int ext4_update_primary_sb(struct super_block *sb, handle_t *handle, ext4_update_sb_callback func, @@ -944,7 +954,9 @@ static long ext4_ioctl_group_add(struct file *file, test_opt(sb, INIT_INODE_TABLE)) err = ext4_register_li_request(sb, input->group); group_add_out: - ext4_resize_end(sb); + err2 = ext4_resize_end(sb, false); + if (err == 0) + err = err2; return err; } @@ -1131,6 +1143,73 @@ static int ext4_ioctl_getlabel(struct ext4_sb_info *sbi, char __user *user_label return 0; } +static int ext4_ioctl_getuuid(struct ext4_sb_info *sbi, + struct fsuuid __user *ufsuuid) +{ + struct fsuuid fsuuid; + __u8 uuid[UUID_SIZE]; + + if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid))) + return -EFAULT; + + if (fsuuid.fsu_len == 0) { + fsuuid.fsu_len = UUID_SIZE; + if (copy_to_user(ufsuuid, &fsuuid, sizeof(fsuuid.fsu_len))) + return -EFAULT; + return -EINVAL; + } + + if (fsuuid.fsu_len != UUID_SIZE || fsuuid.fsu_flags != 0) + return -EINVAL; + + lock_buffer(sbi->s_sbh); + memcpy(uuid, sbi->s_es->s_uuid, UUID_SIZE); + unlock_buffer(sbi->s_sbh); + + if (copy_to_user(&ufsuuid->fsu_uuid[0], uuid, UUID_SIZE)) + return -EFAULT; + return 0; +} + +static int ext4_ioctl_setuuid(struct file *filp, + const struct fsuuid __user *ufsuuid) +{ + int ret = 0; + struct super_block *sb = file_inode(filp)->i_sb; + struct fsuuid fsuuid; + __u8 uuid[UUID_SIZE]; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* + * If any checksums (group descriptors or metadata) are being used + * then the checksum seed feature is required to change the UUID. + */ + if (((ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb)) + && !ext4_has_feature_csum_seed(sb)) + || ext4_has_feature_stable_inodes(sb)) + return -EOPNOTSUPP; + + if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid))) + return -EFAULT; + + if (fsuuid.fsu_len != UUID_SIZE || fsuuid.fsu_flags != 0) + return -EINVAL; + + if (copy_from_user(uuid, &ufsuuid->fsu_uuid[0], UUID_SIZE)) + return -EFAULT; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + ret = ext4_update_superblocks_fn(sb, ext4_sb_setuuid, &uuid); + mnt_drop_write_file(filp); + + return ret; +} + static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -1223,7 +1302,9 @@ setversion_out: err = err2; mnt_drop_write_file(filp); group_extend_out: - ext4_resize_end(sb); + err2 = ext4_resize_end(sb, false); + if (err == 0) + err = err2; return err; } @@ -1371,7 +1452,9 @@ mext_out: err = ext4_register_li_request(sb, o_group); resizefs_out: - ext4_resize_end(sb); + err2 = ext4_resize_end(sb, true); + if (err == 0) + err = err2; return err; } @@ -1509,6 +1592,10 @@ resizefs_out: return ext4_ioctl_setlabel(filp, (const void __user *)arg); + case EXT4_IOC_GETFSUUID: + return ext4_ioctl_getuuid(EXT4_SB(sb), (void __user *)arg); + case EXT4_IOC_SETFSUUID: + return ext4_ioctl_setuuid(filp, (const void __user *)arg); default: return -ENOTTY; } @@ -1586,6 +1673,8 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case EXT4_IOC_CHECKPOINT: case FS_IOC_GETFSLABEL: case FS_IOC_SETFSLABEL: + case EXT4_IOC_GETFSUUID: + case EXT4_IOC_SETFSUUID: break; default: return -ENOIOCTLCMD; @@ -1599,13 +1688,15 @@ static void set_overhead(struct ext4_super_block *es, const void *arg) es->s_overhead_clusters = cpu_to_le32(*((unsigned long *) arg)); } -int ext4_update_overhead(struct super_block *sb) +int ext4_update_overhead(struct super_block *sb, bool force) { struct ext4_sb_info *sbi = EXT4_SB(sb); - if (sb_rdonly(sb) || sbi->s_overhead == 0 || - sbi->s_overhead == le32_to_cpu(sbi->s_es->s_overhead_clusters)) + if (sb_rdonly(sb)) + return 0; + if (!force && + (sbi->s_overhead == 0 || + sbi->s_overhead == le32_to_cpu(sbi->s_es->s_overhead_clusters))) return 0; - return ext4_update_superblocks_fn(sb, set_overhead, &sbi->s_overhead); } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 9e06334771a3..bd8f8b5c3d30 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1933,6 +1933,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) unsigned ret = 0; int len0 = len; void *buddy; + bool split = false; BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3)); BUG_ON(e4b->bd_group != ex->fe_group); @@ -1957,12 +1958,16 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) /* let's maintain buddy itself */ while (len) { - ord = mb_find_order_for_block(e4b, start); + if (!split) + ord = mb_find_order_for_block(e4b, start); if (((start >> ord) << ord) == start && len >= (1 << ord)) { /* the whole chunk may be allocated at once! */ mlen = 1 << ord; - buddy = mb_find_buddy(e4b, ord, &max); + if (!split) + buddy = mb_find_buddy(e4b, ord, &max); + else + split = false; BUG_ON((start >> ord) >= max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; @@ -1989,6 +1994,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) mb_clear_bit(cur + 1, buddy); e4b->bd_info->bb_counters[ord]++; e4b->bd_info->bb_counters[ord]++; + split = true; } mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info); @@ -5928,6 +5934,15 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { + ext4_error(sb, "Freeing blocks in system zone - " + "Block = %llu, count = %lu", block, count); + /* err = 0. ext4_std_error should be a no op */ + goto error_return; + } + flags |= EXT4_FREE_BLOCKS_VALIDATED; + do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); @@ -5944,6 +5959,8 @@ do_more: overflow = EXT4_C2B(sbi, bit) + count - EXT4_BLOCKS_PER_GROUP(sb); count -= overflow; + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } count_clusters = EXT4_NUM_B2C(sbi, count); bitmap_bh = ext4_read_block_bitmap(sb, block_group); @@ -5958,7 +5975,8 @@ do_more: goto error_return; } - if (!ext4_inode_block_valid(inode, block, count)) { + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ @@ -6081,6 +6099,8 @@ do_more: block += count; count = overflow; put_bh(bitmap_bh); + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; goto do_more; } error_return: @@ -6127,6 +6147,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, "block = %llu, count = %lu", block, count); return; } + flags |= EXT4_FREE_BLOCKS_VALIDATED; ext4_debug("freeing block %llu\n", block); trace_ext4_free_blocks(inode, block, count, flags); @@ -6158,6 +6179,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, block -= overflow; count += overflow; } + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } overflow = EXT4_LBLK_COFF(sbi, count); if (overflow) { @@ -6168,6 +6191,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, return; } else count += sbi->s_cluster_ratio - overflow; + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 42f590518b4c..54e7d3c95fd7 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -417,7 +417,7 @@ int ext4_ext_migrate(struct inode *inode) struct inode *tmp_inode = NULL; struct migrate_struct lb; unsigned long max_entries; - __u32 goal; + __u32 goal, tmp_csum_seed; uid_t owner[2]; /* @@ -465,6 +465,7 @@ int ext4_ext_migrate(struct inode *inode) * the migration. */ ei = EXT4_I(inode); + tmp_csum_seed = EXT4_I(tmp_inode)->i_csum_seed; EXT4_I(tmp_inode)->i_csum_seed = ei->i_csum_seed; i_size_write(tmp_inode, i_size_read(inode)); /* @@ -575,6 +576,7 @@ err_out: * the inode is not visible to user space. */ tmp_inode->i_blocks = 0; + EXT4_I(tmp_inode)->i_csum_seed = tmp_csum_seed; /* Reset the extent details */ ext4_ext_tree_init(handle, tmp_inode); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index db4ba99d1ceb..3a31b662f661 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -54,6 +54,7 @@ static struct buffer_head *ext4_append(handle_t *handle, struct inode *inode, ext4_lblk_t *block) { + struct ext4_map_blocks map; struct buffer_head *bh; int err; @@ -63,6 +64,21 @@ static struct buffer_head *ext4_append(handle_t *handle, return ERR_PTR(-ENOSPC); *block = inode->i_size >> inode->i_sb->s_blocksize_bits; + map.m_lblk = *block; + map.m_len = 1; + + /* + * We're appending new directory block. Make sure the block is not + * allocated yet, otherwise we will end up corrupting the + * directory. + */ + err = ext4_map_blocks(NULL, inode, &map, 0); + if (err < 0) + return ERR_PTR(err); + if (err) { + EXT4_ERROR_INODE(inode, "Logical block already allocated"); + return ERR_PTR(-EFSCORRUPTED); + } bh = ext4_bread(handle, inode, *block, EXT4_GET_BLOCKS_CREATE); if (IS_ERR(bh)) @@ -110,6 +126,13 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, struct ext4_dir_entry *dirent; int is_dx_block = 0; + if (block >= inode->i_size) { + ext4_error_inode(inode, func, line, block, + "Attempting to read directory block (%u) that is past i_size (%llu)", + block, inode->i_size); + return ERR_PTR(-EFSCORRUPTED); + } + if (ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_EIO)) bh = ERR_PTR(-EIO); else @@ -3067,11 +3090,8 @@ bool ext4_empty_dir(struct inode *inode) de = (struct ext4_dir_entry_2 *) (bh->b_data + (offset & (sb->s_blocksize - 1))); if (ext4_check_dir_entry(inode, NULL, de, bh, - bh->b_data, bh->b_size, offset)) { - offset = (offset | (sb->s_blocksize - 1)) + 1; - continue; - } - if (le32_to_cpu(de->inode)) { + bh->b_data, bh->b_size, offset) || + le32_to_cpu(de->inode)) { brelse(bh); return false; } diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c index 7de0612eb42d..69a9cf9137a6 100644 --- a/fs/ext4/orphan.c +++ b/fs/ext4/orphan.c @@ -181,8 +181,8 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) } else brelse(iloc.bh); - jbd_debug(4, "superblock will point to %lu\n", inode->i_ino); - jbd_debug(4, "orphan inode %lu will point to %d\n", + ext4_debug("superblock will point to %lu\n", inode->i_ino); + ext4_debug("orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); out: ext4_std_error(sb, err); @@ -251,7 +251,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) } mutex_lock(&sbi->s_orphan_lock); - jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino); + ext4_debug("remove inode %lu from orphan list\n", inode->i_ino); prev = ei->i_orphan.prev; list_del_init(&ei->i_orphan); @@ -267,7 +267,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) ino_next = NEXT_ORPHAN(inode); if (prev == &sbi->s_orphan) { - jbd_debug(4, "superblock will point to %u\n", ino_next); + ext4_debug("superblock will point to %u\n", ino_next); BUFFER_TRACE(sbi->s_sbh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode->i_sb, sbi->s_sbh, EXT4_JTR_NONE); @@ -286,7 +286,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) struct inode *i_prev = &list_entry(prev, struct ext4_inode_info, i_orphan)->vfs_inode; - jbd_debug(4, "orphan inode %lu will point to %u\n", + ext4_debug("orphan inode %lu will point to %u\n", i_prev->i_ino, ino_next); err = ext4_reserve_inode_write(handle, i_prev, &iloc2); if (err) { @@ -332,8 +332,8 @@ static void ext4_process_orphan(struct inode *inode, ext4_msg(sb, KERN_DEBUG, "%s: truncating inode %lu to %lld bytes", __func__, inode->i_ino, inode->i_size); - jbd_debug(2, "truncating inode %lu to %lld bytes\n", - inode->i_ino, inode->i_size); + ext4_debug("truncating inode %lu to %lld bytes\n", + inode->i_ino, inode->i_size); inode_lock(inode); truncate_inode_pages(inode->i_mapping, inode->i_size); ret = ext4_truncate(inode); @@ -353,8 +353,8 @@ static void ext4_process_orphan(struct inode *inode, ext4_msg(sb, KERN_DEBUG, "%s: deleting unreferenced inode %lu", __func__, inode->i_ino); - jbd_debug(2, "deleting unreferenced inode %lu\n", - inode->i_ino); + ext4_debug("deleting unreferenced inode %lu\n", + inode->i_ino); (*nr_orphans)++; } iput(inode); /* The delete magic happens here! */ @@ -391,7 +391,7 @@ void ext4_orphan_cleanup(struct super_block *sb, struct ext4_super_block *es) int inodes_per_ob = ext4_inodes_per_orphan_block(sb); if (!es->s_last_orphan && !oi->of_blocks) { - jbd_debug(4, "no orphan inodes to clean up\n"); + ext4_debug("no orphan inodes to clean up\n"); return; } @@ -415,7 +415,7 @@ void ext4_orphan_cleanup(struct super_block *sb, struct ext4_super_block *es) "clearing orphan list.\n"); es->s_last_orphan = 0; } - jbd_debug(1, "Skipping orphan recovery on fs with errors.\n"); + ext4_debug("Skipping orphan recovery on fs with errors.\n"); return; } @@ -459,7 +459,7 @@ void ext4_orphan_cleanup(struct super_block *sb, struct ext4_super_block *es) * so, skip the rest. */ if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { - jbd_debug(1, "Skipping orphan recovery on fs with errors.\n"); + ext4_debug("Skipping orphan recovery on fs with errors.\n"); es->s_last_orphan = 0; break; } diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 8b70a4701293..fea2a68d067b 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -97,10 +97,13 @@ int ext4_resize_begin(struct super_block *sb) return ret; } -void ext4_resize_end(struct super_block *sb) +int ext4_resize_end(struct super_block *sb, bool update_backups) { clear_bit_unlock(EXT4_FLAGS_RESIZING, &EXT4_SB(sb)->s_ext4_flags); smp_mb__after_atomic(); + if (update_backups) + return ext4_update_overhead(sb, true); + return 0; } static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb, @@ -1380,6 +1383,17 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb, return err; } +static void ext4_add_overhead(struct super_block *sb, + const ext4_fsblk_t overhead) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + + sbi->s_overhead += overhead; + es->s_overhead_clusters = cpu_to_le32(sbi->s_overhead); + smp_wmb(); +} + /* * ext4_update_super() updates the super block so that the newly added * groups can be seen by the filesystem. @@ -1481,9 +1495,18 @@ static void ext4_update_super(struct super_block *sb, } /* - * Update the fs overhead information + * Update the fs overhead information. + * + * For bigalloc, if the superblock already has a properly calculated + * overhead, update it with a value based on numbers already computed + * above for the newly allocated capacity. */ - ext4_calculate_overhead(sb); + if (ext4_has_feature_bigalloc(sb) && (sbi->s_overhead != 0)) + ext4_add_overhead(sb, + EXT4_NUM_B2C(sbi, blocks_count - free_blocks)); + else + ext4_calculate_overhead(sb); + es->s_overhead_clusters = cpu_to_le32(sbi->s_overhead); if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: added group %u:" @@ -1988,6 +2011,16 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) } brelse(bh); + /* + * For bigalloc, trim the requested size to the nearest cluster + * boundary to avoid creating an unusable filesystem. We do this + * silently, instead of returning an error, to avoid breaking + * callers that blindly resize the filesystem to the full size of + * the underlying block device. + */ + if (ext4_has_feature_bigalloc(sb)) + n_blocks_count &= ~((1 << EXT4_CLUSTER_BITS(sb)) - 1); + retry: o_blocks_count = ext4_blocks_count(es); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2c68dec63e54..9a66abcca1a8 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1307,7 +1307,7 @@ static void ext4_put_super(struct super_block *sb) if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->s_blockgroup_lock); - fs_put_dax(sbi->s_daxdev); + fs_put_dax(sbi->s_daxdev, NULL); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); @@ -3011,6 +3011,15 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, } else if (test_opt2(sb, DAX_INODE)) { SEQ_OPTS_PUTS("dax=inode"); } + + if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD && + !test_opt2(sb, MB_OPTIMIZE_SCAN)) { + SEQ_OPTS_PUTS("mb_optimize_scan=0"); + } else if (sbi->s_groups_count < MB_DEFAULT_LINEAR_SCAN_THRESHOLD && + test_opt2(sb, MB_OPTIMIZE_SCAN)) { + SEQ_OPTS_PUTS("mb_optimize_scan=1"); + } + ext4_show_quota_options(seq, sb); return 0; } @@ -4272,7 +4281,7 @@ static void ext4_free_sbi(struct ext4_sb_info *sbi) return; kfree(sbi->s_blockgroup_lock); - fs_put_dax(sbi->s_daxdev); + fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); } @@ -4284,7 +4293,8 @@ static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb) if (!sbi) return NULL; - sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off); + sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off, + NULL, NULL); sbi->s_blockgroup_lock = kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); @@ -4296,7 +4306,7 @@ static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb) sbi->s_sb = sb; return sbi; err_out: - fs_put_dax(sbi->s_daxdev); + fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); return NULL; } @@ -5523,7 +5533,7 @@ static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) "Quota mode: %s.", descr, ext4_quota_mode(sb)); /* Update the s_overhead_clusters if necessary */ - ext4_update_overhead(sb); + ext4_update_overhead(sb, false); return 0; free_sbi: @@ -5585,7 +5595,7 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb, return NULL; } - jbd_debug(2, "Journal inode found at %p: %lld bytes\n", + ext4_debug("Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); if (!S_ISREG(journal_inode->i_mode)) { ext4_msg(sb, KERN_ERR, "invalid journal inode"); diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index d281f5bcc526..3d3ed3c38f56 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -74,6 +74,21 @@ static const char *ext4_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { struct buffer_head *bh; + char *inline_link; + + /* + * Create a new inlined symlink is not supported, just provide a + * method to read the leftovers. + */ + if (ext4_has_inline_data(inode)) { + if (!dentry) + return ERR_PTR(-ECHILD); + + inline_link = ext4_read_inline_link(inode); + if (!IS_ERR(inline_link)) + set_delayed_call(callback, kfree_link, inline_link); + return inline_link; + } if (!dentry) { bh = ext4_getblk(NULL, inode, 0, EXT4_GET_BLOCKS_CACHED_NOWAIT); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 564e28a1aa94..533216e80fa2 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -436,6 +436,21 @@ error: return err; } +/* Remove entry from mbcache when EA inode is getting evicted */ +void ext4_evict_ea_inode(struct inode *inode) +{ + struct mb_cache_entry *oe; + + if (!EA_INODE_CACHE(inode)) + return; + /* Wait for entry to get unused so that we can remove it */ + while ((oe = mb_cache_entry_delete_or_get(EA_INODE_CACHE(inode), + ext4_xattr_inode_get_hash(inode), inode->i_ino))) { + mb_cache_entry_wait_unused(oe); + mb_cache_entry_put(EA_INODE_CACHE(inode), oe); + } +} + static int ext4_xattr_inode_verify_hashes(struct inode *ea_inode, struct ext4_xattr_entry *entry, void *buffer, @@ -976,10 +991,8 @@ int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, int ref_change) { - struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode); struct ext4_iloc iloc; s64 ref_count; - u32 hash; int ret; inode_lock(ea_inode); @@ -1002,14 +1015,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, set_nlink(ea_inode, 1); ext4_orphan_del(handle, ea_inode); - - if (ea_inode_cache) { - hash = ext4_xattr_inode_get_hash(ea_inode); - mb_cache_entry_create(ea_inode_cache, - GFP_NOFS, hash, - ea_inode->i_ino, - true /* reusable */); - } } } else { WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld", @@ -1022,12 +1027,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, clear_nlink(ea_inode); ext4_orphan_add(handle, ea_inode); - - if (ea_inode_cache) { - hash = ext4_xattr_inode_get_hash(ea_inode); - mb_cache_entry_delete(ea_inode_cache, hash, - ea_inode->i_ino); - } } } @@ -1237,6 +1236,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, if (error) goto out; +retry_ref: lock_buffer(bh); hash = le32_to_cpu(BHDR(bh)->h_hash); ref = le32_to_cpu(BHDR(bh)->h_refcount); @@ -1246,9 +1246,18 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect freed block */ - if (ea_block_cache) - mb_cache_entry_delete(ea_block_cache, hash, - bh->b_blocknr); + if (ea_block_cache) { + struct mb_cache_entry *oe; + + oe = mb_cache_entry_delete_or_get(ea_block_cache, hash, + bh->b_blocknr); + if (oe) { + unlock_buffer(bh); + mb_cache_entry_wait_unused(oe); + mb_cache_entry_put(ea_block_cache, oe); + goto retry_ref; + } + } get_bh(bh); unlock_buffer(bh); @@ -1858,6 +1867,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, #define header(x) ((struct ext4_xattr_header *)(x)) if (s->base) { + int offset = (char *)s->here - bs->bh->b_data; + BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, sb, bs->bh, EXT4_JTR_NONE); @@ -1873,9 +1884,20 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, * ext4_xattr_block_set() to reliably detect modified * block */ - if (ea_block_cache) - mb_cache_entry_delete(ea_block_cache, hash, - bs->bh->b_blocknr); + if (ea_block_cache) { + struct mb_cache_entry *oe; + + oe = mb_cache_entry_delete_or_get(ea_block_cache, + hash, bs->bh->b_blocknr); + if (oe) { + /* + * Xattr block is getting reused. Leave + * it alone. + */ + mb_cache_entry_put(ea_block_cache, oe); + goto clone_block; + } + } ea_bdebug(bs->bh, "modifying in-place"); error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */); @@ -1890,49 +1912,47 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, if (error) goto cleanup; goto inserted; - } else { - int offset = (char *)s->here - bs->bh->b_data; + } +clone_block: + unlock_buffer(bs->bh); + ea_bdebug(bs->bh, "cloning"); + s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS); + error = -ENOMEM; + if (s->base == NULL) + goto cleanup; + s->first = ENTRY(header(s->base)+1); + header(s->base)->h_refcount = cpu_to_le32(1); + s->here = ENTRY(s->base + offset); + s->end = s->base + bs->bh->b_size; - unlock_buffer(bs->bh); - ea_bdebug(bs->bh, "cloning"); - s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS); - error = -ENOMEM; - if (s->base == NULL) + /* + * If existing entry points to an xattr inode, we need + * to prevent ext4_xattr_set_entry() from decrementing + * ref count on it because the reference belongs to the + * original block. In this case, make the entry look + * like it has an empty value. + */ + if (!s->not_found && s->here->e_value_inum) { + ea_ino = le32_to_cpu(s->here->e_value_inum); + error = ext4_xattr_inode_iget(inode, ea_ino, + le32_to_cpu(s->here->e_hash), + &tmp_inode); + if (error) goto cleanup; - s->first = ENTRY(header(s->base)+1); - header(s->base)->h_refcount = cpu_to_le32(1); - s->here = ENTRY(s->base + offset); - s->end = s->base + bs->bh->b_size; - - /* - * If existing entry points to an xattr inode, we need - * to prevent ext4_xattr_set_entry() from decrementing - * ref count on it because the reference belongs to the - * original block. In this case, make the entry look - * like it has an empty value. - */ - if (!s->not_found && s->here->e_value_inum) { - ea_ino = le32_to_cpu(s->here->e_value_inum); - error = ext4_xattr_inode_iget(inode, ea_ino, - le32_to_cpu(s->here->e_hash), - &tmp_inode); - if (error) - goto cleanup; - - if (!ext4_test_inode_state(tmp_inode, - EXT4_STATE_LUSTRE_EA_INODE)) { - /* - * Defer quota free call for previous - * inode until success is guaranteed. - */ - old_ea_inode_quota = le32_to_cpu( - s->here->e_value_size); - } - iput(tmp_inode); - s->here->e_value_inum = 0; - s->here->e_value_size = 0; + if (!ext4_test_inode_state(tmp_inode, + EXT4_STATE_LUSTRE_EA_INODE)) { + /* + * Defer quota free call for previous + * inode until success is guaranteed. + */ + old_ea_inode_quota = le32_to_cpu( + s->here->e_value_size); } + iput(tmp_inode); + + s->here->e_value_inum = 0; + s->here->e_value_size = 0; } } else { /* Allocate a buffer where we construct the new block. */ @@ -1999,18 +2019,13 @@ inserted: lock_buffer(new_bh); /* * We have to be careful about races with - * freeing, rehashing or adding references to - * xattr block. Once we hold buffer lock xattr - * block's state is stable so we can check - * whether the block got freed / rehashed or - * not. Since we unhash mbcache entry under - * buffer lock when freeing / rehashing xattr - * block, checking whether entry is still - * hashed is reliable. Same rules hold for - * e_reusable handling. + * adding references to xattr block. Once we + * hold buffer lock xattr block's state is + * stable so we can check the additional + * reference fits. */ - if (hlist_bl_unhashed(&ce->e_hash_list) || - !ce->e_reusable) { + ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; + if (ref > EXT4_XATTR_REFCOUNT_MAX) { /* * Undo everything and check mbcache * again. @@ -2025,9 +2040,8 @@ inserted: new_bh = NULL; goto inserted; } - ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; BHDR(new_bh)->h_refcount = cpu_to_le32(ref); - if (ref >= EXT4_XATTR_REFCOUNT_MAX) + if (ref == EXT4_XATTR_REFCOUNT_MAX) ce->e_reusable = 0; ea_bdebug(new_bh, "reusing; refcount now=%d", ref); @@ -2175,8 +2189,9 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_inode *raw_inode; int error; - if (EXT4_I(inode)->i_extra_isize == 0) + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return 0; + raw_inode = ext4_raw_inode(&is->iloc); header = IHDR(inode, raw_inode); is->s.base = is->s.first = IFIRST(header); @@ -2204,8 +2219,9 @@ int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_search *s = &is->s; int error; - if (EXT4_I(inode)->i_extra_isize == 0) + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return -ENOSPC; + error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) return error; diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 77efb9a627ad..824faf0b15a8 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -84,7 +84,7 @@ struct ext4_xattr_entry { /* * The minimum size of EA value when you start storing it in an external inode * size of block - size of header - size of 1 entry - 4 null bytes -*/ + */ #define EXT4_XATTR_MIN_LARGE_EA_SIZE(b) \ ((b) - EXT4_XATTR_LEN(3) - sizeof(struct ext4_xattr_header) - 4) @@ -95,6 +95,19 @@ struct ext4_xattr_entry { #define EXT4_ZERO_XATTR_VALUE ((void *)-1) +/* + * If we want to add an xattr to the inode, we should make sure that + * i_extra_isize is not 0 and that the inode size is not less than + * EXT4_GOOD_OLD_INODE_SIZE + extra_isize + pad. + * EXT4_GOOD_OLD_INODE_SIZE extra_isize header entry pad data + * |--------------------------|------------|------|---------|---|-------| + */ +#define EXT4_INODE_HAS_XATTR_SPACE(inode) \ + ((EXT4_I(inode)->i_extra_isize != 0) && \ + (EXT4_GOOD_OLD_INODE_SIZE + EXT4_I(inode)->i_extra_isize + \ + sizeof(struct ext4_xattr_ibody_header) + EXT4_XATTR_PAD <= \ + EXT4_INODE_SIZE((inode)->i_sb))) + struct ext4_xattr_info { const char *name; const void *value; @@ -178,6 +191,7 @@ extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array); extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); +extern void ext4_evict_ea_inode(struct inode *inode); extern const struct xattr_handler *ext4_xattr_handlers[]; diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 009e6c519e98..70e97075e535 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -729,14 +729,19 @@ out: return ret; } -void f2fs_decompress_cluster(struct decompress_io_ctx *dic) +static int f2fs_prepare_decomp_mem(struct decompress_io_ctx *dic, + bool pre_alloc); +static void f2fs_release_decomp_mem(struct decompress_io_ctx *dic, + bool bypass_destroy_callback, bool pre_alloc); + +void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task) { struct f2fs_sb_info *sbi = F2FS_I_SB(dic->inode); struct f2fs_inode_info *fi = F2FS_I(dic->inode); const struct f2fs_compress_ops *cops = f2fs_cops[fi->i_compress_algorithm]; + bool bypass_callback = false; int ret; - int i; trace_f2fs_decompress_pages_start(dic->inode, dic->cluster_idx, dic->cluster_size, fi->i_compress_algorithm); @@ -746,41 +751,10 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic) goto out_end_io; } - dic->tpages = page_array_alloc(dic->inode, dic->cluster_size); - if (!dic->tpages) { - ret = -ENOMEM; - goto out_end_io; - } - - for (i = 0; i < dic->cluster_size; i++) { - if (dic->rpages[i]) { - dic->tpages[i] = dic->rpages[i]; - continue; - } - - dic->tpages[i] = f2fs_compress_alloc_page(); - if (!dic->tpages[i]) { - ret = -ENOMEM; - goto out_end_io; - } - } - - if (cops->init_decompress_ctx) { - ret = cops->init_decompress_ctx(dic); - if (ret) - goto out_end_io; - } - - dic->rbuf = f2fs_vmap(dic->tpages, dic->cluster_size); - if (!dic->rbuf) { - ret = -ENOMEM; - goto out_destroy_decompress_ctx; - } - - dic->cbuf = f2fs_vmap(dic->cpages, dic->nr_cpages); - if (!dic->cbuf) { - ret = -ENOMEM; - goto out_vunmap_rbuf; + ret = f2fs_prepare_decomp_mem(dic, false); + if (ret) { + bypass_callback = true; + goto out_release; } dic->clen = le32_to_cpu(dic->cbuf->clen); @@ -788,7 +762,7 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic) if (dic->clen > PAGE_SIZE * dic->nr_cpages - COMPRESS_HEADER_SIZE) { ret = -EFSCORRUPTED; - goto out_vunmap_cbuf; + goto out_release; } ret = cops->decompress_pages(dic); @@ -809,17 +783,13 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic) } } -out_vunmap_cbuf: - vm_unmap_ram(dic->cbuf, dic->nr_cpages); -out_vunmap_rbuf: - vm_unmap_ram(dic->rbuf, dic->cluster_size); -out_destroy_decompress_ctx: - if (cops->destroy_decompress_ctx) - cops->destroy_decompress_ctx(dic); +out_release: + f2fs_release_decomp_mem(dic, bypass_callback, false); + out_end_io: trace_f2fs_decompress_pages_end(dic->inode, dic->cluster_idx, dic->clen, ret); - f2fs_decompress_end_io(dic, ret); + f2fs_decompress_end_io(dic, ret, in_task); } /* @@ -829,7 +799,7 @@ out_end_io: * (or in the case of a failure, cleans up without actually decompressing). */ void f2fs_end_read_compressed_page(struct page *page, bool failed, - block_t blkaddr) + block_t blkaddr, bool in_task) { struct decompress_io_ctx *dic = (struct decompress_io_ctx *)page_private(page); @@ -839,12 +809,12 @@ void f2fs_end_read_compressed_page(struct page *page, bool failed, if (failed) WRITE_ONCE(dic->failed, true); - else if (blkaddr) + else if (blkaddr && in_task) f2fs_cache_compressed_page(sbi, page, dic->inode->i_ino, blkaddr); if (atomic_dec_and_test(&dic->remaining_pages)) - f2fs_decompress_cluster(dic); + f2fs_decompress_cluster(dic, in_task); } static bool is_page_in_cluster(struct compress_ctx *cc, pgoff_t index) @@ -871,19 +841,26 @@ bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index) return is_page_in_cluster(cc, index); } -bool f2fs_all_cluster_page_loaded(struct compress_ctx *cc, struct pagevec *pvec, - int index, int nr_pages) +bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages, + int index, int nr_pages, bool uptodate) { - unsigned long pgidx; - int i; + unsigned long pgidx = pages[index]->index; + int i = uptodate ? 0 : 1; - if (nr_pages - index < cc->cluster_size) + /* + * when uptodate set to true, try to check all pages in cluster is + * uptodate or not. + */ + if (uptodate && (pgidx % cc->cluster_size)) return false; - pgidx = pvec->pages[index]->index; + if (nr_pages - index < cc->cluster_size) + return false; - for (i = 1; i < cc->cluster_size; i++) { - if (pvec->pages[index + i]->index != pgidx + i) + for (; i < cc->cluster_size; i++) { + if (pages[index + i]->index != pgidx + i) + return false; + if (uptodate && !PageUptodate(pages[index + i])) return false; } @@ -1552,16 +1529,85 @@ destroy_out: return err; } -static void f2fs_free_dic(struct decompress_io_ctx *dic); +static inline bool allow_memalloc_for_decomp(struct f2fs_sb_info *sbi, + bool pre_alloc) +{ + return pre_alloc ^ f2fs_low_mem_mode(sbi); +} + +static int f2fs_prepare_decomp_mem(struct decompress_io_ctx *dic, + bool pre_alloc) +{ + const struct f2fs_compress_ops *cops = + f2fs_cops[F2FS_I(dic->inode)->i_compress_algorithm]; + int i; + + if (!allow_memalloc_for_decomp(F2FS_I_SB(dic->inode), pre_alloc)) + return 0; + + dic->tpages = page_array_alloc(dic->inode, dic->cluster_size); + if (!dic->tpages) + return -ENOMEM; + + for (i = 0; i < dic->cluster_size; i++) { + if (dic->rpages[i]) { + dic->tpages[i] = dic->rpages[i]; + continue; + } + + dic->tpages[i] = f2fs_compress_alloc_page(); + if (!dic->tpages[i]) + return -ENOMEM; + } + + dic->rbuf = f2fs_vmap(dic->tpages, dic->cluster_size); + if (!dic->rbuf) + return -ENOMEM; + + dic->cbuf = f2fs_vmap(dic->cpages, dic->nr_cpages); + if (!dic->cbuf) + return -ENOMEM; + + if (cops->init_decompress_ctx) { + int ret = cops->init_decompress_ctx(dic); + + if (ret) + return ret; + } + + return 0; +} + +static void f2fs_release_decomp_mem(struct decompress_io_ctx *dic, + bool bypass_destroy_callback, bool pre_alloc) +{ + const struct f2fs_compress_ops *cops = + f2fs_cops[F2FS_I(dic->inode)->i_compress_algorithm]; + + if (!allow_memalloc_for_decomp(F2FS_I_SB(dic->inode), pre_alloc)) + return; + + if (!bypass_destroy_callback && cops->destroy_decompress_ctx) + cops->destroy_decompress_ctx(dic); + + if (dic->cbuf) + vm_unmap_ram(dic->cbuf, dic->nr_cpages); + + if (dic->rbuf) + vm_unmap_ram(dic->rbuf, dic->cluster_size); +} + +static void f2fs_free_dic(struct decompress_io_ctx *dic, + bool bypass_destroy_callback); struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc) { struct decompress_io_ctx *dic; pgoff_t start_idx = start_idx_of_cluster(cc); - int i; + struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode); + int i, ret; - dic = f2fs_kmem_cache_alloc(dic_entry_slab, GFP_F2FS_ZERO, - false, F2FS_I_SB(cc->inode)); + dic = f2fs_kmem_cache_alloc(dic_entry_slab, GFP_F2FS_ZERO, false, sbi); if (!dic) return ERR_PTR(-ENOMEM); @@ -1587,32 +1633,43 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc) dic->nr_rpages = cc->cluster_size; dic->cpages = page_array_alloc(dic->inode, dic->nr_cpages); - if (!dic->cpages) + if (!dic->cpages) { + ret = -ENOMEM; goto out_free; + } for (i = 0; i < dic->nr_cpages; i++) { struct page *page; page = f2fs_compress_alloc_page(); - if (!page) + if (!page) { + ret = -ENOMEM; goto out_free; + } f2fs_set_compressed_page(page, cc->inode, start_idx + i + 1, dic); dic->cpages[i] = page; } + ret = f2fs_prepare_decomp_mem(dic, true); + if (ret) + goto out_free; + return dic; out_free: - f2fs_free_dic(dic); - return ERR_PTR(-ENOMEM); + f2fs_free_dic(dic, true); + return ERR_PTR(ret); } -static void f2fs_free_dic(struct decompress_io_ctx *dic) +static void f2fs_free_dic(struct decompress_io_ctx *dic, + bool bypass_destroy_callback) { int i; + f2fs_release_decomp_mem(dic, bypass_destroy_callback, true); + if (dic->tpages) { for (i = 0; i < dic->cluster_size; i++) { if (dic->rpages[i]) @@ -1637,17 +1694,33 @@ static void f2fs_free_dic(struct decompress_io_ctx *dic) kmem_cache_free(dic_entry_slab, dic); } -static void f2fs_put_dic(struct decompress_io_ctx *dic) +static void f2fs_late_free_dic(struct work_struct *work) { - if (refcount_dec_and_test(&dic->refcnt)) - f2fs_free_dic(dic); + struct decompress_io_ctx *dic = + container_of(work, struct decompress_io_ctx, free_work); + + f2fs_free_dic(dic, false); +} + +static void f2fs_put_dic(struct decompress_io_ctx *dic, bool in_task) +{ + if (refcount_dec_and_test(&dic->refcnt)) { + if (in_task) { + f2fs_free_dic(dic, false); + } else { + INIT_WORK(&dic->free_work, f2fs_late_free_dic); + queue_work(F2FS_I_SB(dic->inode)->post_read_wq, + &dic->free_work); + } + } } /* * Update and unlock the cluster's pagecache pages, and release the reference to * the decompress_io_ctx that was being held for I/O completion. */ -static void __f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed) +static void __f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed, + bool in_task) { int i; @@ -1668,7 +1741,7 @@ static void __f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed) unlock_page(rpage); } - f2fs_put_dic(dic); + f2fs_put_dic(dic, in_task); } static void f2fs_verify_cluster(struct work_struct *work) @@ -1685,14 +1758,15 @@ static void f2fs_verify_cluster(struct work_struct *work) SetPageError(rpage); } - __f2fs_decompress_end_io(dic, false); + __f2fs_decompress_end_io(dic, false, true); } /* * This is called when a compressed cluster has been decompressed * (or failed to be read and/or decompressed). */ -void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed) +void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed, + bool in_task) { if (!failed && dic->need_verity) { /* @@ -1704,7 +1778,7 @@ void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed) INIT_WORK(&dic->verity_work, f2fs_verify_cluster); fsverity_enqueue_verify_work(&dic->verity_work); } else { - __f2fs_decompress_end_io(dic, failed); + __f2fs_decompress_end_io(dic, failed, in_task); } } @@ -1713,12 +1787,12 @@ void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed) * * This is called when the page is no longer needed and can be freed. */ -void f2fs_put_page_dic(struct page *page) +void f2fs_put_page_dic(struct page *page, bool in_task) { struct decompress_io_ctx *dic = (struct decompress_io_ctx *)page_private(page); - f2fs_put_dic(dic); + f2fs_put_dic(dic, in_task); } /* @@ -1903,6 +1977,9 @@ int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) dev_t dev = sbi->sb->s_bdev->bd_dev; char slab_name[32]; + if (!f2fs_sb_has_compression(sbi)) + return 0; + sprintf(slab_name, "f2fs_page_array_entry-%u:%u", MAJOR(dev), MINOR(dev)); sbi->page_array_slab_size = sizeof(struct page *) << diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index ed503d50f95f..aa3ccddfa037 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -119,7 +119,7 @@ struct bio_post_read_ctx { block_t fs_blkaddr; }; -static void f2fs_finish_read_bio(struct bio *bio) +static void f2fs_finish_read_bio(struct bio *bio, bool in_task) { struct bio_vec *bv; struct bvec_iter_all iter_all; @@ -133,8 +133,9 @@ static void f2fs_finish_read_bio(struct bio *bio) if (f2fs_is_compressed_page(page)) { if (bio->bi_status) - f2fs_end_read_compressed_page(page, true, 0); - f2fs_put_page_dic(page); + f2fs_end_read_compressed_page(page, true, 0, + in_task); + f2fs_put_page_dic(page, in_task); continue; } @@ -191,7 +192,7 @@ static void f2fs_verify_bio(struct work_struct *work) fsverity_verify_bio(bio); } - f2fs_finish_read_bio(bio); + f2fs_finish_read_bio(bio, true); } /* @@ -203,7 +204,7 @@ static void f2fs_verify_bio(struct work_struct *work) * can involve reading verity metadata pages from the file, and these verity * metadata pages may be encrypted and/or compressed. */ -static void f2fs_verify_and_finish_bio(struct bio *bio) +static void f2fs_verify_and_finish_bio(struct bio *bio, bool in_task) { struct bio_post_read_ctx *ctx = bio->bi_private; @@ -211,7 +212,7 @@ static void f2fs_verify_and_finish_bio(struct bio *bio) INIT_WORK(&ctx->work, f2fs_verify_bio); fsverity_enqueue_verify_work(&ctx->work); } else { - f2fs_finish_read_bio(bio); + f2fs_finish_read_bio(bio, in_task); } } @@ -224,7 +225,8 @@ static void f2fs_verify_and_finish_bio(struct bio *bio) * that the bio includes at least one compressed page. The actual decompression * is done on a per-cluster basis, not a per-bio basis. */ -static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx) +static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx, + bool in_task) { struct bio_vec *bv; struct bvec_iter_all iter_all; @@ -237,7 +239,7 @@ static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx) /* PG_error was set if decryption failed. */ if (f2fs_is_compressed_page(page)) f2fs_end_read_compressed_page(page, PageError(page), - blkaddr); + blkaddr, in_task); else all_compressed = false; @@ -262,15 +264,16 @@ static void f2fs_post_read_work(struct work_struct *work) fscrypt_decrypt_bio(ctx->bio); if (ctx->enabled_steps & STEP_DECOMPRESS) - f2fs_handle_step_decompress(ctx); + f2fs_handle_step_decompress(ctx, true); - f2fs_verify_and_finish_bio(ctx->bio); + f2fs_verify_and_finish_bio(ctx->bio, true); } static void f2fs_read_end_io(struct bio *bio) { struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio)); struct bio_post_read_ctx *ctx; + bool intask = in_task(); iostat_update_and_unbind_ctx(bio, 0); ctx = bio->bi_private; @@ -281,16 +284,29 @@ static void f2fs_read_end_io(struct bio *bio) } if (bio->bi_status) { - f2fs_finish_read_bio(bio); + f2fs_finish_read_bio(bio, intask); return; } - if (ctx && (ctx->enabled_steps & (STEP_DECRYPT | STEP_DECOMPRESS))) { - INIT_WORK(&ctx->work, f2fs_post_read_work); - queue_work(ctx->sbi->post_read_wq, &ctx->work); - } else { - f2fs_verify_and_finish_bio(bio); + if (ctx) { + unsigned int enabled_steps = ctx->enabled_steps & + (STEP_DECRYPT | STEP_DECOMPRESS); + + /* + * If we have only decompression step between decompression and + * decrypt, we don't need post processing for this. + */ + if (enabled_steps == STEP_DECOMPRESS && + !f2fs_low_mem_mode(sbi)) { + f2fs_handle_step_decompress(ctx, intask); + } else if (enabled_steps) { + INIT_WORK(&ctx->work, f2fs_post_read_work); + queue_work(ctx->sbi->post_read_wq, &ctx->work); + return; + } } + + f2fs_verify_and_finish_bio(bio, intask); } static void f2fs_write_end_io(struct bio *bio) @@ -1682,8 +1698,6 @@ sync_out: */ f2fs_wait_on_block_writeback_range(inode, map->m_pblk, map->m_len); - invalidate_mapping_pages(META_MAPPING(sbi), - map->m_pblk, map->m_pblk); if (map->m_multidev_dio) { block_t blk_addr = map->m_pblk; @@ -2223,7 +2237,7 @@ skip_reading_dnode: if (f2fs_load_compressed_page(sbi, page, blkaddr)) { if (atomic_dec_and_test(&dic->remaining_pages)) - f2fs_decompress_cluster(dic); + f2fs_decompress_cluster(dic, true); continue; } @@ -2241,7 +2255,7 @@ submit_and_realloc: page->index, for_write); if (IS_ERR(bio)) { ret = PTR_ERR(bio); - f2fs_decompress_end_io(dic, ret); + f2fs_decompress_end_io(dic, ret, true); f2fs_put_dnode(&dn); *bio_ret = NULL; return ret; @@ -2731,6 +2745,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, .submitted = false, .compr_blocks = compr_blocks, .need_lock = LOCK_RETRY, + .post_read = f2fs_post_read_required(inode), .io_type = io_type, .io_wbc = wbc, .bio = bio, @@ -2902,7 +2917,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping, { int ret = 0; int done = 0, retry = 0; - struct pagevec pvec; + struct page *pages[F2FS_ONSTACK_PAGES]; struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); struct bio *bio = NULL; sector_t last_block; @@ -2933,8 +2948,6 @@ static int f2fs_write_cache_pages(struct address_space *mapping, int submitted = 0; int i; - pagevec_init(&pvec); - if (get_dirty_pages(mapping->host) <= SM_I(F2FS_M_SB(mapping))->min_hot_blocks) set_inode_flag(mapping->host, FI_HOT_DATA); @@ -2960,13 +2973,13 @@ retry: tag_pages_for_writeback(mapping, index, end); done_index = index; while (!done && !retry && (index <= end)) { - nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, - tag); + nr_pages = find_get_pages_range_tag(mapping, &index, end, + tag, F2FS_ONSTACK_PAGES, pages); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; + struct page *page = pages[i]; bool need_readd; readd: need_readd = false; @@ -2997,6 +3010,10 @@ readd: if (!f2fs_cluster_is_empty(&cc)) goto lock_page; + if (f2fs_all_cluster_page_ready(&cc, + pages, i, nr_pages, true)) + goto lock_page; + ret2 = f2fs_prepare_compress_overwrite( inode, &pagep, page->index, &fsdata); @@ -3007,8 +3024,8 @@ readd: } else if (ret2 && (!f2fs_compress_write_end(inode, fsdata, page->index, 1) || - !f2fs_all_cluster_page_loaded(&cc, - &pvec, i, nr_pages))) { + !f2fs_all_cluster_page_ready(&cc, + pages, i, nr_pages, false))) { retry = 1; break; } @@ -3098,7 +3115,7 @@ next: if (need_readd) goto readd; } - pagevec_release(&pvec); + release_pages(pages, nr_pages); cond_resched(); } #ifdef CONFIG_F2FS_FS_COMPRESSION @@ -3408,12 +3425,11 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, struct inode *cow_inode = F2FS_I(inode)->cow_inode; pgoff_t index = page->index; int err = 0; - block_t ori_blk_addr; + block_t ori_blk_addr = NULL_ADDR; /* If pos is beyond the end of file, reserve a new block in COW inode */ if ((pos & PAGE_MASK) >= i_size_read(inode)) - return __reserve_data_block(cow_inode, index, blk_addr, - node_changed); + goto reserve_block; /* Look for the block in COW inode first */ err = __find_data_block(cow_inode, index, blk_addr); @@ -3427,10 +3443,12 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, if (err) return err; +reserve_block: /* Finally, we should reserve a new block in COW inode for the update */ err = __reserve_data_block(cow_inode, index, blk_addr, node_changed); if (err) return err; + inc_atomic_write_cnt(inode); if (ori_blk_addr != NULL_ADDR) *blk_addr = ori_blk_addr; diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index c92625ef16d0..c01471573977 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -39,7 +39,7 @@ void f2fs_update_sit_info(struct f2fs_sb_info *sbi) bimodal = 0; total_vblocks = 0; - blks_per_sec = BLKS_PER_SEC(sbi); + blks_per_sec = CAP_BLKS_PER_SEC(sbi); hblks_per_sec = blks_per_sec / 2; for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { vblocks = get_valid_blocks(sbi, segno, true); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 85921a1f2db8..3c7cdb70fe2e 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -159,6 +159,7 @@ struct f2fs_mount_info { int fsync_mode; /* fsync policy */ int fs_mode; /* fs mode: LFS or ADAPTIVE */ int bggc_mode; /* bggc mode: off, on or sync */ + int memory_mode; /* memory mode */ int discard_unit; /* * discard command's offset/size should * be aligned to this unit: block, @@ -229,7 +230,6 @@ enum { #define CP_PAUSE 0x00000040 #define CP_RESIZE 0x00000080 -#define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi) #define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */ #define DEF_MIN_DISCARD_ISSUE_TIME 50 /* 50 ms, if exists */ #define DEF_MID_DISCARD_ISSUE_TIME 500 /* 500 ms, if device busy */ @@ -598,6 +598,8 @@ enum { #define RECOVERY_MAX_RA_BLOCKS BIO_MAX_VECS #define RECOVERY_MIN_RA_BLOCKS 1 +#define F2FS_ONSTACK_PAGES 16 /* nr of onstack pages */ + struct rb_entry { struct rb_node rb_node; /* rb node located in rb-tree */ union { @@ -757,6 +759,7 @@ enum { FI_ENABLE_COMPRESS, /* enable compression in "user" compression mode */ FI_COMPRESS_RELEASED, /* compressed blocks were released */ FI_ALIGNED_WRITE, /* enable aligned write */ + FI_COW_FILE, /* indicate COW file */ FI_MAX, /* max flag, never be used */ }; @@ -812,6 +815,8 @@ struct f2fs_inode_info { unsigned char i_compress_level; /* compress level (lz4hc,zstd) */ unsigned short i_compress_flag; /* compress flag */ unsigned int i_cluster_size; /* cluster size */ + + unsigned int atomic_write_cnt; }; static inline void get_extent_info(struct extent_info *ext, @@ -1198,6 +1203,7 @@ struct f2fs_io_info { bool retry; /* need to reallocate block address */ int compr_blocks; /* # of compressed block addresses */ bool encrypted; /* indicate file is encrypted */ + bool post_read; /* require post read */ enum iostat_type io_type; /* io type */ struct writeback_control *io_wbc; /* writeback control */ struct bio **bio; /* bio for ipu */ @@ -1234,7 +1240,6 @@ struct f2fs_dev_info { #ifdef CONFIG_BLK_DEV_ZONED unsigned int nr_blkz; /* Total number of zones */ unsigned long *blkz_seq; /* Bitmap indicating sequential zones */ - block_t *zone_capacity_blocks; /* Array of zone capacity in blks */ #endif }; @@ -1360,6 +1365,13 @@ enum { DISCARD_UNIT_SECTION, /* basic discard unit is section */ }; +enum { + MEMORY_MODE_NORMAL, /* memory mode for normal devices */ + MEMORY_MODE_LOW, /* memory mode for low memry devices */ +}; + + + static inline int f2fs_test_bit(unsigned int nr, char *addr); static inline void f2fs_set_bit(unsigned int nr, char *addr); static inline void f2fs_clear_bit(unsigned int nr, char *addr); @@ -1580,6 +1592,7 @@ struct decompress_io_ctx { void *private; /* payload buffer for specified decompression algorithm */ void *private2; /* extra payload buffer */ struct work_struct verity_work; /* work to verify the decompressed pages */ + struct work_struct free_work; /* work for late free this structure itself */ }; #define NULL_CLUSTER ((unsigned int)(~0)) @@ -1664,6 +1677,7 @@ struct f2fs_sb_info { unsigned int meta_ino_num; /* meta inode number*/ unsigned int log_blocks_per_seg; /* log2 blocks per segment */ unsigned int blocks_per_seg; /* blocks per segment */ + unsigned int unusable_blocks_per_sec; /* unusable blocks per section */ unsigned int segs_per_sec; /* segments per section */ unsigned int secs_per_zone; /* sections per zone */ unsigned int total_sections; /* total section count */ @@ -1804,6 +1818,12 @@ struct f2fs_sb_info { int max_fragment_chunk; /* max chunk size for block fragmentation mode */ int max_fragment_hole; /* max hole size for block fragmentation mode */ + /* For atomic write statistics */ + atomic64_t current_atomic_write; + s64 peak_atomic_write; + u64 committed_atomic_block; + u64 revoked_atomic_block; + #ifdef CONFIG_F2FS_FS_COMPRESSION struct kmem_cache *page_array_slab; /* page array entry */ unsigned int page_array_slab_size; /* default page array slab size */ @@ -2418,6 +2438,28 @@ static inline void inode_dec_dirty_pages(struct inode *inode) dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA); } +static inline void inc_atomic_write_cnt(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + u64 current_write; + + fi->atomic_write_cnt++; + atomic64_inc(&sbi->current_atomic_write); + current_write = atomic64_read(&sbi->current_atomic_write); + if (current_write > sbi->peak_atomic_write) + sbi->peak_atomic_write = current_write; +} + +static inline void release_atomic_write_cnt(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + + atomic64_sub(fi->atomic_write_cnt, &sbi->current_atomic_write); + fi->atomic_write_cnt = 0; +} + static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type) { return atomic_read(&sbi->nr_pages[count_type]); @@ -2696,16 +2738,6 @@ static inline struct page *f2fs_pagecache_get_page( return pagecache_get_page(mapping, index, fgp_flags, gfp_mask); } -static inline void f2fs_copy_page(struct page *src, struct page *dst) -{ - char *src_kaddr = kmap(src); - char *dst_kaddr = kmap(dst); - - memcpy(dst_kaddr, src_kaddr, PAGE_SIZE); - kunmap(dst); - kunmap(src); -} - static inline void f2fs_put_page(struct page *page, int unlock) { if (!page) @@ -3208,6 +3240,11 @@ static inline bool f2fs_is_atomic_file(struct inode *inode) return is_inode_flag_set(inode, FI_ATOMIC_FILE); } +static inline bool f2fs_is_cow_file(struct inode *inode) +{ + return is_inode_flag_set(inode, FI_COW_FILE); +} + static inline bool f2fs_is_first_block_written(struct inode *inode) { return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN); @@ -4154,13 +4191,13 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page); bool f2fs_is_compress_backend_ready(struct inode *inode); int f2fs_init_compress_mempool(void); void f2fs_destroy_compress_mempool(void); -void f2fs_decompress_cluster(struct decompress_io_ctx *dic); +void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task); void f2fs_end_read_compressed_page(struct page *page, bool failed, - block_t blkaddr); + block_t blkaddr, bool in_task); bool f2fs_cluster_is_empty(struct compress_ctx *cc); bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index); -bool f2fs_all_cluster_page_loaded(struct compress_ctx *cc, struct pagevec *pvec, - int index, int nr_pages); +bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages, + int index, int nr_pages, bool uptodate); bool f2fs_sanity_check_cluster(struct dnode_of_data *dn); void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page); int f2fs_write_multi_pages(struct compress_ctx *cc, @@ -4175,8 +4212,9 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, unsigned nr_pages, sector_t *last_block_in_bio, bool is_readahead, bool for_write); struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); -void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed); -void f2fs_put_page_dic(struct page *page); +void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed, + bool in_task); +void f2fs_put_page_dic(struct page *page, bool in_task); unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn); int f2fs_init_compress_ctx(struct compress_ctx *cc); void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse); @@ -4222,13 +4260,14 @@ static inline struct page *f2fs_compress_control_page(struct page *page) } static inline int f2fs_init_compress_mempool(void) { return 0; } static inline void f2fs_destroy_compress_mempool(void) { } -static inline void f2fs_decompress_cluster(struct decompress_io_ctx *dic) { } +static inline void f2fs_decompress_cluster(struct decompress_io_ctx *dic, + bool in_task) { } static inline void f2fs_end_read_compressed_page(struct page *page, - bool failed, block_t blkaddr) + bool failed, block_t blkaddr, bool in_task) { WARN_ON_ONCE(1); } -static inline void f2fs_put_page_dic(struct page *page) +static inline void f2fs_put_page_dic(struct page *page, bool in_task) { WARN_ON_ONCE(1); } @@ -4254,8 +4293,9 @@ static inline void f2fs_update_extent_tree_range_compressed(struct inode *inode, unsigned int c_len) { } #endif -static inline void set_compress_context(struct inode *inode) +static inline int set_compress_context(struct inode *inode) { +#ifdef CONFIG_F2FS_FS_COMPRESSION struct f2fs_sb_info *sbi = F2FS_I_SB(inode); F2FS_I(inode)->i_compress_algorithm = @@ -4278,6 +4318,10 @@ static inline void set_compress_context(struct inode *inode) stat_inc_compr_inode(inode); inc_compr_inode_stat(inode); f2fs_mark_inode_dirty_sync(inode, true); + return 0; +#else + return -EOPNOTSUPP; +#endif } static inline bool f2fs_disable_compressed_file(struct inode *inode) @@ -4394,10 +4438,15 @@ static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi) return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS; } +static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi) +{ + return F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_LOW; +} + static inline bool f2fs_may_compress(struct inode *inode) { if (IS_SWAPFILE(inode) || f2fs_is_pinned_file(inode) || - f2fs_is_atomic_file(inode)) + f2fs_is_atomic_file(inode) || f2fs_has_inline_data(inode)) return false; return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode); } @@ -4459,12 +4508,7 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, /* disallow direct IO if any of devices has unaligned blksize */ if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize) return true; - /* - * for blkzoned device, fallback direct IO to buffered IO, so - * all IOs can be serialized by log-structured write. - */ - if (f2fs_sb_has_blkzoned(sbi)) - return true; + if (f2fs_lfs_mode(sbi) && (rw == WRITE)) { if (block_unaligned_IO(inode, iocb, iter)) return true; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index d66e37d80a2d..ce4905a073b3 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1272,7 +1272,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, f2fs_put_page(psrc, 1); return PTR_ERR(pdst); } - f2fs_copy_page(psrc, pdst); + memcpy_page(pdst, 0, psrc, 0, PAGE_SIZE); set_page_dirty(pdst); f2fs_put_page(pdst, 1); f2fs_put_page(psrc, 1); @@ -1675,7 +1675,7 @@ static int expand_inode_data(struct inode *inode, loff_t offset, return 0; if (f2fs_is_pinned_file(inode)) { - block_t sec_blks = BLKS_PER_SEC(sbi); + block_t sec_blks = CAP_BLKS_PER_SEC(sbi); block_t sec_len = roundup(map.m_len, sec_blks); map.m_len = sec_blks; @@ -1816,8 +1816,7 @@ static int f2fs_release_file(struct inode *inode, struct file *filp) atomic_read(&inode->i_writecount) != 1) return 0; - if (f2fs_is_atomic_file(inode)) - f2fs_abort_atomic_write(inode, true); + f2fs_abort_atomic_write(inode, true); return 0; } @@ -1831,8 +1830,7 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id) * until all the writers close its file. Since this should be done * before dropping file lock, it needs to do in ->flush. */ - if (f2fs_is_atomic_file(inode) && - F2FS_I(inode)->atomic_write_task == current) + if (F2FS_I(inode)->atomic_write_task == current) f2fs_abort_atomic_write(inode, true); return 0; } @@ -1867,22 +1865,15 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) if (masked_flags & F2FS_COMPR_FL) { if (!f2fs_disable_compressed_file(inode)) return -EINVAL; - } - if (iflags & F2FS_NOCOMP_FL) - return -EINVAL; - if (iflags & F2FS_COMPR_FL) { + } else { if (!f2fs_may_compress(inode)) return -EINVAL; - if (S_ISREG(inode->i_mode) && inode->i_size) + if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode)) return -EINVAL; - - set_compress_context(inode); + if (set_compress_context(inode)) + return -EOPNOTSUPP; } } - if ((iflags ^ masked_flags) & F2FS_NOCOMP_FL) { - if (masked_flags & F2FS_COMPR_FL) - return -EINVAL; - } fi->i_flags = iflags | (fi->i_flags & ~mask); f2fs_bug_on(F2FS_I_SB(inode), (fi->i_flags & F2FS_COMPR_FL) && @@ -2062,13 +2053,14 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); set_inode_flag(inode, FI_ATOMIC_FILE); - set_inode_flag(fi->cow_inode, FI_ATOMIC_FILE); + set_inode_flag(fi->cow_inode, FI_COW_FILE); clear_inode_flag(fi->cow_inode, FI_INLINE_DATA); f2fs_up_write(&fi->i_gc_rwsem[WRITE]); f2fs_update_time(sbi, REQ_TIME); fi->atomic_write_task = current; stat_update_max_atomic_write(inode); + fi->atomic_write_cnt = 0; out: inode_unlock(inode); mnt_drop_write_file(filp); @@ -2109,6 +2101,30 @@ unlock_out: return ret; } +static int f2fs_ioc_abort_atomic_write(struct file *filp) +{ + struct inode *inode = file_inode(filp); + struct user_namespace *mnt_userns = file_mnt_user_ns(filp); + int ret; + + if (!inode_owner_or_capable(mnt_userns, inode)) + return -EACCES; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + inode_lock(inode); + + f2fs_abort_atomic_write(inode, true); + + inode_unlock(inode); + + mnt_drop_write_file(filp); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + return ret; +} + static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -2426,7 +2442,7 @@ do_more: ret = -EAGAIN; goto out; } - range->start += BLKS_PER_SEC(sbi); + range->start += CAP_BLKS_PER_SEC(sbi); if (range->start <= end) goto do_more; out: @@ -2551,7 +2567,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, goto out; } - sec_num = DIV_ROUND_UP(total, BLKS_PER_SEC(sbi)); + sec_num = DIV_ROUND_UP(total, CAP_BLKS_PER_SEC(sbi)); /* * make sure there are enough free section for LFS allocation, this can @@ -3897,10 +3913,10 @@ static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len) for (i = 0; i < page_len; i++, redirty_idx++) { page = find_lock_page(mapping, redirty_idx); - if (!page) { - ret = -ENOMEM; - break; - } + + /* It will never fail, when page has pinned above */ + f2fs_bug_on(F2FS_I_SB(inode), !page); + set_page_dirty(page); f2fs_put_page(page, 1); f2fs_put_page(page, 0); @@ -3939,6 +3955,11 @@ static int f2fs_ioc_decompress_file(struct file *filp, unsigned long arg) goto out; } + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + ret = -EINVAL; + goto out; + } + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); if (ret) goto out; @@ -4006,6 +4027,11 @@ static int f2fs_ioc_compress_file(struct file *filp, unsigned long arg) goto out; } + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + ret = -EINVAL; + goto out; + } + ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); if (ret) goto out; @@ -4054,9 +4080,10 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_start_atomic_write(filp); case F2FS_IOC_COMMIT_ATOMIC_WRITE: return f2fs_ioc_commit_atomic_write(filp); + case F2FS_IOC_ABORT_ATOMIC_WRITE: + return f2fs_ioc_abort_atomic_write(filp); case F2FS_IOC_START_VOLATILE_WRITE: case F2FS_IOC_RELEASE_VOLATILE_WRITE: - case F2FS_IOC_ABORT_VOLATILE_WRITE: return -EOPNOTSUPP; case F2FS_IOC_SHUTDOWN: return f2fs_ioc_shutdown(filp, arg); @@ -4725,7 +4752,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_COMMIT_ATOMIC_WRITE: case F2FS_IOC_START_VOLATILE_WRITE: case F2FS_IOC_RELEASE_VOLATILE_WRITE: - case F2FS_IOC_ABORT_VOLATILE_WRITE: + case F2FS_IOC_ABORT_ATOMIC_WRITE: case F2FS_IOC_SHUTDOWN: case FITRIM: case FS_IOC_SET_ENCRYPTION_POLICY: diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index d5fb426e0747..6da21d405ce1 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -150,8 +150,11 @@ do_gc: gc_control.nr_free_secs = foreground ? 1 : 0; /* if return value is not zero, no victim was selected */ - if (f2fs_gc(sbi, &gc_control)) - wait_ms = gc_th->no_gc_sleep_time; + if (f2fs_gc(sbi, &gc_control)) { + /* don't bother wait_ms by foreground gc */ + if (!foreground) + wait_ms = gc_th->no_gc_sleep_time; + } if (foreground) wake_up_all(&gc_th->fggc_wq); @@ -487,7 +490,7 @@ static void atgc_lookup_victim(struct f2fs_sb_info *sbi, unsigned long long age, u, accu; unsigned long long max_mtime = sit_i->dirty_max_mtime; unsigned long long min_mtime = sit_i->dirty_min_mtime; - unsigned int sec_blocks = BLKS_PER_SEC(sbi); + unsigned int sec_blocks = CAP_BLKS_PER_SEC(sbi); unsigned int vblocks; unsigned int dirty_threshold = max(am->max_candidate_count, am->candidate_ratio * @@ -1487,7 +1490,7 @@ next_step: */ if ((gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) || (!force_migrate && get_valid_blocks(sbi, segno, true) == - BLKS_PER_SEC(sbi))) + CAP_BLKS_PER_SEC(sbi))) return submitted; if (check_valid_map(sbi, segno, off) == 0) diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index 3fe145e8e594..19b956c2d697 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -120,15 +120,13 @@ static inline block_t free_user_blocks(struct f2fs_sb_info *sbi) return free_blks - ovp_blks; } -static inline block_t limit_invalid_user_blocks(struct f2fs_sb_info *sbi) +static inline block_t limit_invalid_user_blocks(block_t user_block_count) { - return (long)(sbi->user_block_count * LIMIT_INVALID_BLOCK) / 100; + return (long)(user_block_count * LIMIT_INVALID_BLOCK) / 100; } -static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi) +static inline block_t limit_free_user_blocks(block_t reclaimable_user_blocks) { - block_t reclaimable_user_blocks = sbi->user_block_count - - written_block_count(sbi); return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100; } @@ -163,15 +161,16 @@ static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th, static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi) { - block_t invalid_user_blocks = sbi->user_block_count - - written_block_count(sbi); + block_t user_block_count = sbi->user_block_count; + block_t invalid_user_blocks = user_block_count - + written_block_count(sbi); /* * Background GC is triggered with the following conditions. * 1. There are a number of invalid blocks. * 2. There is not enough free space. */ - if (invalid_user_blocks > limit_invalid_user_blocks(sbi) && - free_user_blocks(sbi) < limit_free_user_blocks(sbi)) - return true; - return false; + return (invalid_user_blocks > + limit_invalid_user_blocks(user_block_count) && + free_user_blocks(sbi) < + limit_free_user_blocks(invalid_user_blocks)); } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index fc55f5bd1fcc..6d11c365d7b4 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -744,8 +744,7 @@ void f2fs_evict_inode(struct inode *inode) nid_t xnid = F2FS_I(inode)->i_xattr_nid; int err = 0; - if (f2fs_is_atomic_file(inode)) - f2fs_abort_atomic_write(inode, true); + f2fs_abort_atomic_write(inode, true); trace_f2fs_evict_inode(inode); truncate_inode_pages_final(&inode->i_data); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 740c72d088f3..e06a0c478b39 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1292,7 +1292,11 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs) dec_valid_node_count(sbi, dn->inode, !ofs); goto fail; } - f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR); + if (unlikely(new_ni.blk_addr != NULL_ADDR)) { + err = -EFSCORRUPTED; + set_sbi_flag(sbi, SBI_NEED_FSCK); + goto fail; + } #endif new_ni.nid = dn->nid; new_ni.ino = dn->inode->i_ino; @@ -1945,7 +1949,6 @@ next_step: for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; bool submitted = false; - bool may_dirty = true; /* give a priority to WB_SYNC threads */ if (atomic_read(&sbi->wb_sync_req[NODE]) && @@ -1998,11 +2001,8 @@ continue_unlock: } /* flush dirty inode */ - if (IS_INODE(page) && may_dirty) { - may_dirty = false; - if (flush_dirty_inode(page)) - goto lock_node; - } + if (IS_INODE(page) && flush_dirty_inode(page)) + goto lock_node; write_node: f2fs_wait_on_page_writeback(page, NODE, true, true); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index c7afc588cf26..0de21f82d7bc 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -190,18 +190,20 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); - if (f2fs_is_atomic_file(inode)) { - if (clean) - truncate_inode_pages_final(inode->i_mapping); - clear_inode_flag(fi->cow_inode, FI_ATOMIC_FILE); - iput(fi->cow_inode); - fi->cow_inode = NULL; - clear_inode_flag(inode, FI_ATOMIC_FILE); + if (!f2fs_is_atomic_file(inode)) + return; - spin_lock(&sbi->inode_lock[ATOMIC_FILE]); - sbi->atomic_files--; - spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); - } + if (clean) + truncate_inode_pages_final(inode->i_mapping); + clear_inode_flag(fi->cow_inode, FI_COW_FILE); + iput(fi->cow_inode); + fi->cow_inode = NULL; + release_atomic_write_cnt(inode); + clear_inode_flag(inode, FI_ATOMIC_FILE); + + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + sbi->atomic_files--; + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); } static int __replace_atomic_write_block(struct inode *inode, pgoff_t index, @@ -335,6 +337,11 @@ next: } out: + if (ret) + sbi->revoked_atomic_block += fi->atomic_write_cnt; + else + sbi->committed_atomic_block += fi->atomic_write_cnt; + __complete_revoke_list(inode, &revoke_list, ret ? true : false); return ret; @@ -728,7 +735,7 @@ static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, get_valid_blocks(sbi, segno, true); f2fs_bug_on(sbi, unlikely(!valid_blocks || - valid_blocks == BLKS_PER_SEC(sbi))); + valid_blocks == CAP_BLKS_PER_SEC(sbi))); if (!IS_CURSEC(sbi, secno)) set_bit(secno, dirty_i->dirty_secmap); @@ -764,7 +771,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); if (!valid_blocks || - valid_blocks == BLKS_PER_SEC(sbi)) { + valid_blocks == CAP_BLKS_PER_SEC(sbi)) { clear_bit(secno, dirty_i->dirty_secmap); return; } @@ -3166,7 +3173,7 @@ static int __get_segment_type_6(struct f2fs_io_info *fio) return CURSEG_COLD_DATA; if (file_is_hot(inode) || is_inode_flag_set(inode, FI_HOT_DATA) || - f2fs_is_atomic_file(inode)) + f2fs_is_cow_file(inode)) return CURSEG_HOT_DATA; return f2fs_rw_hint_to_seg_type(inode->i_write_hint); } else { @@ -3433,7 +3440,8 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) goto drop_bio; } - invalidate_mapping_pages(META_MAPPING(sbi), + if (fio->post_read) + invalidate_mapping_pages(META_MAPPING(sbi), fio->new_blkaddr, fio->new_blkaddr); stat_inc_inplace_blocks(fio->sbi); @@ -3616,10 +3624,16 @@ void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr) void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, block_t len) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); block_t i; + if (!f2fs_post_read_required(inode)) + return; + for (i = 0; i < len; i++) f2fs_wait_on_block_writeback(inode, blkaddr + i); + + invalidate_mapping_pages(META_MAPPING(sbi), blkaddr, blkaddr + len - 1); } static int read_compacted_summaries(struct f2fs_sb_info *sbi) @@ -4362,6 +4376,12 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) return err; seg_info_from_raw_sit(se, &sit); + if (se->type >= NR_PERSISTENT_LOG) { + f2fs_err(sbi, "Invalid segment type: %u, segno: %u", + se->type, start); + return -EFSCORRUPTED; + } + sit_valid_blocks[SE_PAGETYPE(se)] += se->valid_blocks; if (f2fs_block_unit_discard(sbi)) { @@ -4410,6 +4430,13 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) break; seg_info_from_raw_sit(se, &sit); + if (se->type >= NR_PERSISTENT_LOG) { + f2fs_err(sbi, "Invalid segment type: %u, segno: %u", + se->type, start); + err = -EFSCORRUPTED; + break; + } + sit_valid_blocks[SE_PAGETYPE(se)] += se->valid_blocks; if (f2fs_block_unit_discard(sbi)) { @@ -4483,7 +4510,6 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi) struct free_segmap_info *free_i = FREE_I(sbi); unsigned int segno = 0, offset = 0, secno; block_t valid_blocks, usable_blks_in_seg; - block_t blks_per_sec = BLKS_PER_SEC(sbi); while (1) { /* find dirty segment based on free segmap */ @@ -4512,7 +4538,7 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi) valid_blocks = get_valid_blocks(sbi, segno, true); secno = GET_SEC_FROM_SEG(sbi, segno); - if (!valid_blocks || valid_blocks == blks_per_sec) + if (!valid_blocks || valid_blocks == CAP_BLKS_PER_SEC(sbi)) continue; if (IS_CURSEC(sbi, secno)) continue; @@ -4895,7 +4921,7 @@ static unsigned int get_zone_idx(struct f2fs_sb_info *sbi, unsigned int secno, static inline unsigned int f2fs_usable_zone_segs_in_sec( struct f2fs_sb_info *sbi, unsigned int segno) { - unsigned int dev_idx, zone_idx, unusable_segs_in_sec; + unsigned int dev_idx, zone_idx; dev_idx = f2fs_target_device_index(sbi, START_BLOCK(sbi, segno)); zone_idx = get_zone_idx(sbi, GET_SEC_FROM_SEG(sbi, segno), dev_idx); @@ -4904,18 +4930,12 @@ static inline unsigned int f2fs_usable_zone_segs_in_sec( if (is_conv_zone(sbi, zone_idx, dev_idx)) return sbi->segs_per_sec; - /* - * If the zone_capacity_blocks array is NULL, then zone capacity - * is equal to the zone size for all zones - */ - if (!FDEV(dev_idx).zone_capacity_blocks) + if (!sbi->unusable_blocks_per_sec) return sbi->segs_per_sec; /* Get the segment count beyond zone capacity block */ - unusable_segs_in_sec = (sbi->blocks_per_blkz - - FDEV(dev_idx).zone_capacity_blocks[zone_idx]) >> - sbi->log_blocks_per_seg; - return sbi->segs_per_sec - unusable_segs_in_sec; + return sbi->segs_per_sec - (sbi->unusable_blocks_per_sec >> + sbi->log_blocks_per_seg); } /* @@ -4944,12 +4964,11 @@ static inline unsigned int f2fs_usable_zone_blks_in_seg( if (is_conv_zone(sbi, zone_idx, dev_idx)) return sbi->blocks_per_seg; - if (!FDEV(dev_idx).zone_capacity_blocks) + if (!sbi->unusable_blocks_per_sec) return sbi->blocks_per_seg; sec_start_blkaddr = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno)); - sec_cap_blkaddr = sec_start_blkaddr + - FDEV(dev_idx).zone_capacity_blocks[zone_idx]; + sec_cap_blkaddr = sec_start_blkaddr + CAP_BLKS_PER_SEC(sbi); /* * If segment starts before zone capacity and spans beyond diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 3f277dfcb131..d1d63766f2c7 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -101,6 +101,9 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi, GET_SEGNO_FROM_SEG0(sbi, blk_addr))) #define BLKS_PER_SEC(sbi) \ ((sbi)->segs_per_sec * (sbi)->blocks_per_seg) +#define CAP_BLKS_PER_SEC(sbi) \ + ((sbi)->segs_per_sec * (sbi)->blocks_per_seg - \ + (sbi)->unusable_blocks_per_sec) #define GET_SEC_FROM_SEG(sbi, segno) \ (((segno) == -1) ? -1: (segno) / (sbi)->segs_per_sec) #define GET_SEG_FROM_SEC(sbi, secno) \ @@ -609,10 +612,10 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, get_pages(sbi, F2FS_DIRTY_DENTS) + get_pages(sbi, F2FS_DIRTY_IMETA); unsigned int total_dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS); - unsigned int node_secs = total_node_blocks / BLKS_PER_SEC(sbi); - unsigned int dent_secs = total_dent_blocks / BLKS_PER_SEC(sbi); - unsigned int node_blocks = total_node_blocks % BLKS_PER_SEC(sbi); - unsigned int dent_blocks = total_dent_blocks % BLKS_PER_SEC(sbi); + unsigned int node_secs = total_node_blocks / CAP_BLKS_PER_SEC(sbi); + unsigned int dent_secs = total_dent_blocks / CAP_BLKS_PER_SEC(sbi); + unsigned int node_blocks = total_node_blocks % CAP_BLKS_PER_SEC(sbi); + unsigned int dent_blocks = total_dent_blocks % CAP_BLKS_PER_SEC(sbi); unsigned int free, need_lower, need_upper; if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 37221e94e5ef..2451623c05a7 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> +#include <linux/fs_context.h> #include <linux/sched/mm.h> #include <linux/statfs.h> #include <linux/buffer_head.h> @@ -159,6 +160,7 @@ enum { Opt_gc_merge, Opt_nogc_merge, Opt_discard_unit, + Opt_memory_mode, Opt_err, }; @@ -235,6 +237,7 @@ static match_table_t f2fs_tokens = { {Opt_gc_merge, "gc_merge"}, {Opt_nogc_merge, "nogc_merge"}, {Opt_discard_unit, "discard_unit=%s"}, + {Opt_memory_mode, "memory=%s"}, {Opt_err, NULL}, }; @@ -492,9 +495,19 @@ static int f2fs_set_test_dummy_encryption(struct super_block *sb, bool is_remount) { struct f2fs_sb_info *sbi = F2FS_SB(sb); -#ifdef CONFIG_FS_ENCRYPTION + struct fs_parameter param = { + .type = fs_value_is_string, + .string = arg->from ? arg->from : "", + }; + struct fscrypt_dummy_policy *policy = + &F2FS_OPTION(sbi).dummy_enc_policy; int err; + if (!IS_ENABLED(CONFIG_FS_ENCRYPTION)) { + f2fs_warn(sbi, "test_dummy_encryption option not supported"); + return -EINVAL; + } + if (!f2fs_sb_has_encrypt(sbi)) { f2fs_err(sbi, "Encrypt feature is off"); return -EINVAL; @@ -506,12 +519,12 @@ static int f2fs_set_test_dummy_encryption(struct super_block *sb, * needed to allow it to be set or changed during remount. We do allow * it to be specified during remount, but only if there is no change. */ - if (is_remount && !F2FS_OPTION(sbi).dummy_enc_policy.policy) { + if (is_remount && !fscrypt_is_dummy_policy_set(policy)) { f2fs_warn(sbi, "Can't set test_dummy_encryption on remount"); return -EINVAL; } - err = fscrypt_set_test_dummy_encryption( - sb, arg->from, &F2FS_OPTION(sbi).dummy_enc_policy); + + err = fscrypt_parse_test_dummy_encryption(¶m, policy); if (err) { if (err == -EEXIST) f2fs_warn(sbi, @@ -524,12 +537,14 @@ static int f2fs_set_test_dummy_encryption(struct super_block *sb, opt, err); return -EINVAL; } + err = fscrypt_add_test_dummy_key(sb, policy); + if (err) { + f2fs_warn(sbi, "Error adding test dummy encryption key [%d]", + err); + return err; + } f2fs_warn(sbi, "Test dummy encryption mode enabled"); return 0; -#else - f2fs_warn(sbi, "test_dummy_encryption option not supported"); - return -EINVAL; -#endif } #ifdef CONFIG_F2FS_FS_COMPRESSION @@ -1222,6 +1237,22 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) } kfree(name); break; + case Opt_memory_mode: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + if (!strcmp(name, "normal")) { + F2FS_OPTION(sbi).memory_mode = + MEMORY_MODE_NORMAL; + } else if (!strcmp(name, "low")) { + F2FS_OPTION(sbi).memory_mode = + MEMORY_MODE_LOW; + } else { + kfree(name); + return -EINVAL; + } + kfree(name); + break; default: f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value", p); @@ -1380,8 +1411,7 @@ static int f2fs_drop_inode(struct inode *inode) atomic_inc(&inode->i_count); spin_unlock(&inode->i_lock); - if (f2fs_is_atomic_file(inode)) - f2fs_abort_atomic_write(inode, true); + f2fs_abort_atomic_write(inode, true); /* should remain fi->extent_tree for writepage */ f2fs_destroy_extent_node(inode); @@ -1491,7 +1521,6 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) blkdev_put(FDEV(i).bdev, FMODE_EXCL); #ifdef CONFIG_BLK_DEV_ZONED kvfree(FDEV(i).blkz_seq); - kfree(FDEV(i).zone_capacity_blocks); #endif } kvfree(sbi->devs); @@ -1993,6 +2022,11 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION) seq_printf(seq, ",discard_unit=%s", "section"); + if (F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_NORMAL) + seq_printf(seq, ",memory=%s", "normal"); + else if (F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_LOW) + seq_printf(seq, ",memory=%s", "low"); + return 0; } @@ -2014,6 +2048,7 @@ static void default_options(struct f2fs_sb_info *sbi) F2FS_OPTION(sbi).compress_ext_cnt = 0; F2FS_OPTION(sbi).compress_mode = COMPR_MODE_FS; F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON; + F2FS_OPTION(sbi).memory_mode = MEMORY_MODE_NORMAL; sbi->sb->s_flags &= ~SB_INLINECRYPT; @@ -3579,6 +3614,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE; sbi->max_fragment_hole = DEF_FRAGMENT_SIZE; spin_lock_init(&sbi->gc_urgent_high_lock); + atomic64_set(&sbi->current_atomic_write, 0); sbi->dir_level = DEF_DIR_LEVEL; sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL; @@ -3636,24 +3672,29 @@ err_valid_block: #ifdef CONFIG_BLK_DEV_ZONED struct f2fs_report_zones_args { + struct f2fs_sb_info *sbi; struct f2fs_dev_info *dev; - bool zone_cap_mismatch; }; static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx, void *data) { struct f2fs_report_zones_args *rz_args = data; + block_t unusable_blocks = (zone->len - zone->capacity) >> + F2FS_LOG_SECTORS_PER_BLOCK; if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) return 0; set_bit(idx, rz_args->dev->blkz_seq); - rz_args->dev->zone_capacity_blocks[idx] = zone->capacity >> - F2FS_LOG_SECTORS_PER_BLOCK; - if (zone->len != zone->capacity && !rz_args->zone_cap_mismatch) - rz_args->zone_cap_mismatch = true; - + if (!rz_args->sbi->unusable_blocks_per_sec) { + rz_args->sbi->unusable_blocks_per_sec = unusable_blocks; + return 0; + } + if (rz_args->sbi->unusable_blocks_per_sec != unusable_blocks) { + f2fs_err(rz_args->sbi, "F2FS supports single zone capacity\n"); + return -EINVAL; + } return 0; } @@ -3694,26 +3735,13 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) if (!FDEV(devi).blkz_seq) return -ENOMEM; - /* Get block zones type and zone-capacity */ - FDEV(devi).zone_capacity_blocks = f2fs_kzalloc(sbi, - FDEV(devi).nr_blkz * sizeof(block_t), - GFP_KERNEL); - if (!FDEV(devi).zone_capacity_blocks) - return -ENOMEM; - + rep_zone_arg.sbi = sbi; rep_zone_arg.dev = &FDEV(devi); - rep_zone_arg.zone_cap_mismatch = false; ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES, f2fs_report_zone_cb, &rep_zone_arg); if (ret < 0) return ret; - - if (!rep_zone_arg.zone_cap_mismatch) { - kfree(FDEV(devi).zone_capacity_blocks); - FDEV(devi).zone_capacity_blocks = NULL; - } - return 0; } #endif @@ -4579,7 +4607,7 @@ static int __init init_f2fs_fs(void) err = f2fs_init_sysfs(); if (err) goto free_garbage_collection_cache; - err = register_shrinker(&f2fs_shrinker_info); + err = register_shrinker(&f2fs_shrinker_info, "f2fs-shrinker"); if (err) goto free_sysfs; err = register_filesystem(&f2fs_fs_type); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 4c50aedd5144..eba5fb1629d7 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -339,6 +339,21 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, sbi->gc_reclaimed_segs[sbi->gc_segment_mode]); } + if (!strcmp(a->attr.name, "current_atomic_write")) { + s64 current_write = atomic64_read(&sbi->current_atomic_write); + + return sysfs_emit(buf, "%lld\n", current_write); + } + + if (!strcmp(a->attr.name, "peak_atomic_write")) + return sysfs_emit(buf, "%lld\n", sbi->peak_atomic_write); + + if (!strcmp(a->attr.name, "committed_atomic_block")) + return sysfs_emit(buf, "%llu\n", sbi->committed_atomic_block); + + if (!strcmp(a->attr.name, "revoked_atomic_block")) + return sysfs_emit(buf, "%llu\n", sbi->revoked_atomic_block); + ui = (unsigned int *)(ptr + a->offset); return sprintf(buf, "%u\n", *ui); @@ -608,6 +623,27 @@ out: return count; } + if (!strcmp(a->attr.name, "peak_atomic_write")) { + if (t != 0) + return -EINVAL; + sbi->peak_atomic_write = 0; + return count; + } + + if (!strcmp(a->attr.name, "committed_atomic_block")) { + if (t != 0) + return -EINVAL; + sbi->committed_atomic_block = 0; + return count; + } + + if (!strcmp(a->attr.name, "revoked_atomic_block")) { + if (t != 0) + return -EINVAL; + sbi->revoked_atomic_block = 0; + return count; + } + *ui = (unsigned int)t; return count; @@ -713,6 +749,11 @@ static struct f2fs_attr f2fs_attr_##_name = { \ .offset = _offset \ } +#define F2FS_RO_ATTR(struct_type, struct_name, name, elname) \ + F2FS_ATTR_OFFSET(struct_type, name, 0444, \ + f2fs_sbi_show, NULL, \ + offsetof(struct struct_name, elname)) + #define F2FS_RW_ATTR(struct_type, struct_name, name, elname) \ F2FS_ATTR_OFFSET(struct_type, name, 0644, \ f2fs_sbi_show, f2fs_sbi_store, \ @@ -811,6 +852,8 @@ F2FS_FEATURE_RO_ATTR(encrypted_casefold); #endif /* CONFIG_FS_ENCRYPTION */ #ifdef CONFIG_BLK_DEV_ZONED F2FS_FEATURE_RO_ATTR(block_zoned); +F2FS_RO_ATTR(F2FS_SBI, f2fs_sb_info, unusable_blocks_per_sec, + unusable_blocks_per_sec); #endif F2FS_FEATURE_RO_ATTR(atomic_write); F2FS_FEATURE_RO_ATTR(extra_attr); @@ -848,6 +891,12 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_reclaimed_segments, gc_reclaimed_segs); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_chunk, max_fragment_chunk); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_hole, max_fragment_hole); +/* For atomic write */ +F2FS_RO_ATTR(F2FS_SBI, f2fs_sb_info, current_atomic_write, current_atomic_write); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, peak_atomic_write, peak_atomic_write); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, committed_atomic_block, committed_atomic_block); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, revoked_atomic_block, revoked_atomic_block); + #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { ATTR_LIST(gc_urgent_sleep_time), @@ -919,6 +968,9 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(moved_blocks_background), ATTR_LIST(avg_vblocks), #endif +#ifdef CONFIG_BLK_DEV_ZONED + ATTR_LIST(unusable_blocks_per_sec), +#endif #ifdef CONFIG_F2FS_FS_COMPRESSION ATTR_LIST(compr_written_block), ATTR_LIST(compr_saved_block), @@ -934,6 +986,10 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(gc_reclaimed_segments), ATTR_LIST(max_fragment_chunk), ATTR_LIST(max_fragment_hole), + ATTR_LIST(current_atomic_write), + ATTR_LIST(peak_atomic_write), + ATTR_LIST(committed_atomic_block), + ATTR_LIST(revoked_atomic_block), NULL, }; ATTRIBUTE_GROUPS(f2fs); diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index c573314806cf..21620054e1c4 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -889,22 +889,57 @@ out: return err; } -static int vfat_rename(struct user_namespace *mnt_userns, struct inode *old_dir, - struct dentry *old_dentry, struct inode *new_dir, - struct dentry *new_dentry, unsigned int flags) +static int vfat_get_dotdot_de(struct inode *inode, struct buffer_head **bh, + struct msdos_dir_entry **de) +{ + if (S_ISDIR(inode->i_mode)) { + if (fat_get_dotdot_entry(inode, bh, de)) + return -EIO; + } + return 0; +} + +static int vfat_sync_ipos(struct inode *dir, struct inode *inode) +{ + if (IS_DIRSYNC(dir)) + return fat_sync_inode(inode); + mark_inode_dirty(inode); + return 0; +} + +static int vfat_update_dotdot_de(struct inode *dir, struct inode *inode, + struct buffer_head *dotdot_bh, + struct msdos_dir_entry *dotdot_de) +{ + fat_set_start(dotdot_de, MSDOS_I(dir)->i_logstart); + mark_buffer_dirty_inode(dotdot_bh, inode); + if (IS_DIRSYNC(dir)) + return sync_dirty_buffer(dotdot_bh); + return 0; +} + +static void vfat_update_dir_metadata(struct inode *dir, struct timespec64 *ts) +{ + inode_inc_iversion(dir); + fat_truncate_time(dir, ts, S_CTIME | S_MTIME); + if (IS_DIRSYNC(dir)) + (void)fat_sync_inode(dir); + else + mark_inode_dirty(dir); +} + +static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) { struct buffer_head *dotdot_bh; - struct msdos_dir_entry *dotdot_de; + struct msdos_dir_entry *dotdot_de = NULL; struct inode *old_inode, *new_inode; struct fat_slot_info old_sinfo, sinfo; struct timespec64 ts; loff_t new_i_pos; - int err, is_dir, update_dotdot, corrupt = 0; + int err, is_dir, corrupt = 0; struct super_block *sb = old_dir->i_sb; - if (flags & ~RENAME_NOREPLACE) - return -EINVAL; - old_sinfo.bh = sinfo.bh = dotdot_bh = NULL; old_inode = d_inode(old_dentry); new_inode = d_inode(new_dentry); @@ -913,15 +948,13 @@ static int vfat_rename(struct user_namespace *mnt_userns, struct inode *old_dir, if (err) goto out; - is_dir = S_ISDIR(old_inode->i_mode); - update_dotdot = (is_dir && old_dir != new_dir); - if (update_dotdot) { - if (fat_get_dotdot_entry(old_inode, &dotdot_bh, &dotdot_de)) { - err = -EIO; + if (old_dir != new_dir) { + err = vfat_get_dotdot_de(old_inode, &dotdot_bh, &dotdot_de); + if (err) goto out; - } } + is_dir = S_ISDIR(old_inode->i_mode); ts = current_time(old_dir); if (new_inode) { if (is_dir) { @@ -942,21 +975,15 @@ static int vfat_rename(struct user_namespace *mnt_userns, struct inode *old_dir, fat_detach(old_inode); fat_attach(old_inode, new_i_pos); - if (IS_DIRSYNC(new_dir)) { - err = fat_sync_inode(old_inode); - if (err) - goto error_inode; - } else - mark_inode_dirty(old_inode); + err = vfat_sync_ipos(new_dir, old_inode); + if (err) + goto error_inode; - if (update_dotdot) { - fat_set_start(dotdot_de, MSDOS_I(new_dir)->i_logstart); - mark_buffer_dirty_inode(dotdot_bh, old_inode); - if (IS_DIRSYNC(new_dir)) { - err = sync_dirty_buffer(dotdot_bh); - if (err) - goto error_dotdot; - } + if (dotdot_de) { + err = vfat_update_dotdot_de(new_dir, old_inode, dotdot_bh, + dotdot_de); + if (err) + goto error_dotdot; drop_nlink(old_dir); if (!new_inode) inc_nlink(new_dir); @@ -966,12 +993,7 @@ static int vfat_rename(struct user_namespace *mnt_userns, struct inode *old_dir, old_sinfo.bh = NULL; if (err) goto error_dotdot; - inode_inc_iversion(old_dir); - fat_truncate_time(old_dir, &ts, S_CTIME|S_MTIME); - if (IS_DIRSYNC(old_dir)) - (void)fat_sync_inode(old_dir); - else - mark_inode_dirty(old_dir); + vfat_update_dir_metadata(old_dir, &ts); if (new_inode) { drop_nlink(new_inode); @@ -991,10 +1013,9 @@ error_dotdot: /* data cluster is shared, serious corruption */ corrupt = 1; - if (update_dotdot) { - fat_set_start(dotdot_de, MSDOS_I(old_dir)->i_logstart); - mark_buffer_dirty_inode(dotdot_bh, old_inode); - corrupt |= sync_dirty_buffer(dotdot_bh); + if (dotdot_de) { + corrupt |= vfat_update_dotdot_de(old_dir, old_inode, dotdot_bh, + dotdot_de); } error_inode: fat_detach(old_inode); @@ -1021,13 +1042,145 @@ error_inode: goto out; } +static void vfat_exchange_ipos(struct inode *old_inode, struct inode *new_inode, + loff_t old_i_pos, loff_t new_i_pos) +{ + fat_detach(old_inode); + fat_detach(new_inode); + fat_attach(old_inode, new_i_pos); + fat_attach(new_inode, old_i_pos); +} + +static void vfat_move_nlink(struct inode *src, struct inode *dst) +{ + drop_nlink(src); + inc_nlink(dst); +} + +static int vfat_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct buffer_head *old_dotdot_bh = NULL, *new_dotdot_bh = NULL; + struct msdos_dir_entry *old_dotdot_de = NULL, *new_dotdot_de = NULL; + struct inode *old_inode, *new_inode; + struct timespec64 ts = current_time(old_dir); + loff_t old_i_pos, new_i_pos; + int err, corrupt = 0; + struct super_block *sb = old_dir->i_sb; + + old_inode = d_inode(old_dentry); + new_inode = d_inode(new_dentry); + + /* Acquire super block lock for the operation to be atomic */ + mutex_lock(&MSDOS_SB(sb)->s_lock); + + /* if directories are not the same, get ".." info to update */ + if (old_dir != new_dir) { + err = vfat_get_dotdot_de(old_inode, &old_dotdot_bh, + &old_dotdot_de); + if (err) + goto out; + + err = vfat_get_dotdot_de(new_inode, &new_dotdot_bh, + &new_dotdot_de); + if (err) + goto out; + } + + old_i_pos = MSDOS_I(old_inode)->i_pos; + new_i_pos = MSDOS_I(new_inode)->i_pos; + + vfat_exchange_ipos(old_inode, new_inode, old_i_pos, new_i_pos); + + err = vfat_sync_ipos(old_dir, new_inode); + if (err) + goto error_exchange; + err = vfat_sync_ipos(new_dir, old_inode); + if (err) + goto error_exchange; + + /* update ".." directory entry info */ + if (old_dotdot_de) { + err = vfat_update_dotdot_de(new_dir, old_inode, old_dotdot_bh, + old_dotdot_de); + if (err) + goto error_old_dotdot; + } + if (new_dotdot_de) { + err = vfat_update_dotdot_de(old_dir, new_inode, new_dotdot_bh, + new_dotdot_de); + if (err) + goto error_new_dotdot; + } + + /* if cross directory and only one is a directory, adjust nlink */ + if (!old_dotdot_de != !new_dotdot_de) { + if (old_dotdot_de) + vfat_move_nlink(old_dir, new_dir); + else + vfat_move_nlink(new_dir, old_dir); + } + + vfat_update_dir_metadata(old_dir, &ts); + /* if directories are not the same, update new_dir as well */ + if (old_dir != new_dir) + vfat_update_dir_metadata(new_dir, &ts); + +out: + brelse(old_dotdot_bh); + brelse(new_dotdot_bh); + mutex_unlock(&MSDOS_SB(sb)->s_lock); + + return err; + +error_new_dotdot: + if (new_dotdot_de) { + corrupt |= vfat_update_dotdot_de(new_dir, new_inode, + new_dotdot_bh, new_dotdot_de); + } + +error_old_dotdot: + if (old_dotdot_de) { + corrupt |= vfat_update_dotdot_de(old_dir, old_inode, + old_dotdot_bh, old_dotdot_de); + } + +error_exchange: + vfat_exchange_ipos(old_inode, new_inode, new_i_pos, old_i_pos); + corrupt |= vfat_sync_ipos(new_dir, new_inode); + corrupt |= vfat_sync_ipos(old_dir, old_inode); + + if (corrupt < 0) { + fat_fs_error(new_dir->i_sb, + "%s: Filesystem corrupted (i_pos %lld, %lld)", + __func__, old_i_pos, new_i_pos); + } + goto out; +} + +static int vfat_rename2(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) +{ + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + return -EINVAL; + + if (flags & RENAME_EXCHANGE) { + return vfat_rename_exchange(old_dir, old_dentry, + new_dir, new_dentry); + } + + /* VFS already handled RENAME_NOREPLACE, handle it as a normal rename */ + return vfat_rename(old_dir, old_dentry, new_dir, new_dentry); +} + static const struct inode_operations vfat_dir_inode_operations = { .create = vfat_create, .lookup = vfat_lookup, .unlink = vfat_unlink, .mkdir = vfat_mkdir, .rmdir = vfat_rmdir, - .rename = vfat_rename, + .rename = vfat_rename2, .setattr = fat_setattr, .getattr = fat_getattr, .update_time = fat_update_time, diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 05221366a16d..08a1993ab7fd 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -134,10 +134,10 @@ static bool inode_io_list_move_locked(struct inode *inode, static void wb_wakeup(struct bdi_writeback *wb) { - spin_lock_bh(&wb->work_lock); + spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); - spin_unlock_bh(&wb->work_lock); + spin_unlock_irq(&wb->work_lock); } static void finish_writeback_work(struct bdi_writeback *wb, @@ -164,7 +164,7 @@ static void wb_queue_work(struct bdi_writeback *wb, if (work->done) atomic_inc(&work->done->cnt); - spin_lock_bh(&wb->work_lock); + spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); @@ -172,7 +172,7 @@ static void wb_queue_work(struct bdi_writeback *wb, } else finish_writeback_work(wb, work); - spin_unlock_bh(&wb->work_lock); + spin_unlock_irq(&wb->work_lock); } /** @@ -2082,13 +2082,13 @@ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; - spin_lock_bh(&wb->work_lock); + spin_lock_irq(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } - spin_unlock_bh(&wb->work_lock); + spin_unlock_irq(&wb->work_lock); return work; } diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 74920826d8f6..451d8a077e12 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -263,6 +263,8 @@ void fscache_caching_failed(struct fscache_cookie *cookie) { clear_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags); fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_FAILED); + trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref), + fscache_cookie_failed); } EXPORT_SYMBOL(fscache_caching_failed); @@ -739,6 +741,9 @@ again_locked: fallthrough; case FSCACHE_COOKIE_STATE_FAILED: + if (test_and_clear_bit(FSCACHE_COOKIE_DO_INVALIDATE, &cookie->flags)) + fscache_end_cookie_access(cookie, fscache_access_invalidate_cookie_end); + if (atomic_read(&cookie->n_accesses) != 0) break; if (test_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags)) { @@ -1063,8 +1068,8 @@ void __fscache_invalidate(struct fscache_cookie *cookie, return; case FSCACHE_COOKIE_STATE_LOOKING_UP: - __fscache_begin_cookie_access(cookie, fscache_access_invalidate_cookie); - set_bit(FSCACHE_COOKIE_DO_INVALIDATE, &cookie->flags); + if (!test_and_set_bit(FSCACHE_COOKIE_DO_INVALIDATE, &cookie->flags)) + __fscache_begin_cookie_access(cookie, fscache_access_invalidate_cookie); fallthrough; case FSCACHE_COOKIE_STATE_CREATING: spin_unlock(&cookie->lock); diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 7cede9a3bc96..247ef4f76761 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -258,7 +258,7 @@ int fuse_ctl_add_conn(struct fuse_conn *fc) struct dentry *parent; char name[32]; - if (!fuse_control_sb) + if (!fuse_control_sb || fc->no_control) return 0; parent = fuse_control_sb->s_root; @@ -296,7 +296,7 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc) { int i; - if (!fuse_control_sb) + if (!fuse_control_sb || fc->no_control) return; for (i = fc->ctl_ndents - 1; i >= 0; i--) { diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index 10eb50cbf398..e23e802a8013 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -138,9 +138,9 @@ static struct fuse_dax_mapping *alloc_dax_mapping(struct fuse_conn_dax *fcd) WARN_ON(fcd->nr_free_ranges <= 0); fcd->nr_free_ranges--; } + __kick_dmap_free_worker(fcd, 0); spin_unlock(&fcd->lock); - kick_dmap_free_worker(fcd, 0); return dmap; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 0e537e580dc1..51897427a534 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -730,14 +730,13 @@ static int fuse_copy_fill(struct fuse_copy_state *cs) } } else { size_t off; - err = iov_iter_get_pages(cs->iter, &page, PAGE_SIZE, 1, &off); + err = iov_iter_get_pages2(cs->iter, &page, PAGE_SIZE, 1, &off); if (err < 0) return err; BUG_ON(!err); cs->len = err; cs->offset = off; cs->pg = page; - iov_iter_advance(cs->iter, err); } return lock_request(cs->req); @@ -1356,7 +1355,7 @@ static ssize_t fuse_dev_read(struct kiocb *iocb, struct iov_iter *to) if (!fud) return -EPERM; - if (!iter_is_iovec(to)) + if (!user_backed_iter(to)) return -EINVAL; fuse_copy_init(&cs, 1, to); @@ -1949,7 +1948,7 @@ static ssize_t fuse_dev_write(struct kiocb *iocb, struct iov_iter *from) if (!fud) return -EPERM; - if (!iter_is_iovec(from)) + if (!user_backed_iter(from)) return -EINVAL; fuse_copy_init(&cs, 0, from); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 74303d6e987b..b585b04e815e 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -11,6 +11,7 @@ #include <linux/pagemap.h> #include <linux/file.h> #include <linux/fs_context.h> +#include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/namei.h> #include <linux/slab.h> @@ -21,6 +22,11 @@ #include <linux/types.h> #include <linux/kernel.h> +static bool __read_mostly allow_sys_admin_access; +module_param(allow_sys_admin_access, bool, 0644); +MODULE_PARM_DESC(allow_sys_admin_access, + "Allow users with CAP_SYS_ADMIN in initial userns to bypass allow_other access check"); + static void fuse_advise_use_readdirplus(struct inode *dir) { struct fuse_inode *fi = get_fuse_inode(dir); @@ -537,6 +543,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, struct fuse_file *ff; void *security_ctx = NULL; u32 security_ctxlen; + bool trunc = flags & O_TRUNC; /* Userspace expects S_IFREG in create mode */ BUG_ON((mode & S_IFMT) != S_IFREG); @@ -561,7 +568,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, inarg.mode = mode; inarg.umask = current_umask(); - if (fm->fc->handle_killpriv_v2 && (flags & O_TRUNC) && + if (fm->fc->handle_killpriv_v2 && trunc && !(flags & O_EXCL) && !capable(CAP_FSETID)) { inarg.open_flags |= FUSE_OPEN_KILL_SUIDGID; } @@ -623,6 +630,10 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, } else { file->private_data = ff; fuse_finish_open(inode, file); + if (fm->fc->atomic_o_trunc && trunc) + truncate_pagecache(inode, 0); + else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); } return err; @@ -1224,6 +1235,9 @@ int fuse_allow_current_process(struct fuse_conn *fc) { const struct cred *cred; + if (allow_sys_admin_access && capable(CAP_SYS_ADMIN)) + return 1; + if (fc->allow_other) return current_in_userns(fc->user_ns); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 00fa861aeead..1a3afd469e3a 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -210,13 +210,9 @@ void fuse_finish_open(struct inode *inode, struct file *file) fi->attr_version = atomic64_inc_return(&fc->attr_version); i_size_write(inode, 0); spin_unlock(&fi->lock); - truncate_pagecache(inode, 0); file_update_time(file); fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE); - } else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) { - invalidate_inode_pages2(inode->i_mapping); } - if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache) fuse_link_write_file(file); } @@ -239,30 +235,38 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) if (err) return err; - if (is_wb_truncate || dax_truncate) { + if (is_wb_truncate || dax_truncate) inode_lock(inode); - fuse_set_nowrite(inode); - } if (dax_truncate) { filemap_invalidate_lock(inode->i_mapping); err = fuse_dax_break_layouts(inode, 0, 0); if (err) - goto out; + goto out_inode_unlock; } + if (is_wb_truncate || dax_truncate) + fuse_set_nowrite(inode); + err = fuse_do_open(fm, get_node_id(inode), file, isdir); if (!err) fuse_finish_open(inode, file); -out: + if (is_wb_truncate || dax_truncate) + fuse_release_nowrite(inode); + if (!err) { + struct fuse_file *ff = file->private_data; + + if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) + truncate_pagecache(inode, 0); + else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); + } if (dax_truncate) filemap_invalidate_unlock(inode->i_mapping); - - if (is_wb_truncate | dax_truncate) { - fuse_release_nowrite(inode); +out_inode_unlock: + if (is_wb_truncate || dax_truncate) inode_unlock(inode); - } return err; } @@ -338,6 +342,15 @@ static int fuse_open(struct inode *inode, struct file *file) static int fuse_release(struct inode *inode, struct file *file) { + struct fuse_conn *fc = get_fuse_conn(inode); + + /* + * Dirty pages might remain despite write_inode_now() call from + * fuse_flush() due to writes racing with the close. + */ + if (fc->writeback_cache) + write_inode_now(inode, 1); + fuse_release_common(file, false); /* return value is ignored by VFS */ @@ -1401,14 +1414,13 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, while (nbytes < *nbytesp && ap->num_pages < max_pages) { unsigned npages; size_t start; - ret = iov_iter_get_pages(ii, &ap->pages[ap->num_pages], + ret = iov_iter_get_pages2(ii, &ap->pages[ap->num_pages], *nbytesp - nbytes, max_pages - ap->num_pages, &start); if (ret < 0) break; - iov_iter_advance(ii, ret); nbytes += ret; ret += start; @@ -1465,7 +1477,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, inode_unlock(inode); } - io->should_dirty = !write && iter_is_iovec(iter); + io->should_dirty = !write && user_backed_iter(iter); while (count) { ssize_t nres; fl_owner_t owner = current->files; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 8c0665c5dff8..6b3beda16c1b 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -180,6 +180,12 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, inode->i_uid = make_kuid(fc->user_ns, attr->uid); inode->i_gid = make_kgid(fc->user_ns, attr->gid); inode->i_blocks = attr->blocks; + + /* Sanitize nsecs */ + attr->atimensec = min_t(u32, attr->atimensec, NSEC_PER_SEC - 1); + attr->mtimensec = min_t(u32, attr->mtimensec, NSEC_PER_SEC - 1); + attr->ctimensec = min_t(u32, attr->ctimensec, NSEC_PER_SEC - 1); + inode->i_atime.tv_sec = attr->atime; inode->i_atime.tv_nsec = attr->atimensec; /* mtime from server may be stale due to local buffered write */ @@ -476,8 +482,14 @@ static void fuse_umount_begin(struct super_block *sb) { struct fuse_conn *fc = get_fuse_conn_super(sb); - if (!fc->no_force_umount) - fuse_abort_conn(fc); + if (fc->no_force_umount) + return; + + fuse_abort_conn(fc); + + // Only retire block-device-based superblocks. + if (sb->s_bdev != NULL) + retire_super(sb); } static void fuse_send_destroy(struct fuse_mount *fm) diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c index 33cde4bbccdc..61d8afcb10a3 100644 --- a/fs/fuse/ioctl.c +++ b/fs/fuse/ioctl.c @@ -9,6 +9,17 @@ #include <linux/compat.h> #include <linux/fileattr.h> +static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args) +{ + ssize_t ret = fuse_simple_request(fm, args); + + /* Translate ENOSYS, which shouldn't be returned from fs */ + if (ret == -ENOSYS) + ret = -ENOTTY; + + return ret; +} + /* * CUSE servers compiled on 32bit broke on 64bit kernels because the * ABI was defined to be 'struct iovec' which is different on 32bit @@ -259,7 +270,7 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, ap.args.out_pages = true; ap.args.out_argvar = true; - transferred = fuse_simple_request(fm, &ap.args); + transferred = fuse_send_ioctl(fm, &ap.args); err = transferred; if (transferred < 0) goto out; @@ -393,7 +404,7 @@ static int fuse_priv_ioctl(struct inode *inode, struct fuse_file *ff, args.out_args[1].size = inarg.out_size; args.out_args[1].value = ptr; - err = fuse_simple_request(fm, &args); + err = fuse_send_ioctl(fm, &args); if (!err) { if (outarg.result < 0) err = outarg.result; diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 8db53fa67359..4d8d4f16c727 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -741,8 +741,7 @@ out: } /* Free virtqueues (device must already be reset) */ -static void virtio_fs_cleanup_vqs(struct virtio_device *vdev, - struct virtio_fs *fs) +static void virtio_fs_cleanup_vqs(struct virtio_device *vdev) { vdev->config->del_vqs(vdev); } @@ -757,7 +756,7 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, { struct virtio_fs *fs = dax_get_private(dax_dev); phys_addr_t offset = PFN_PHYS(pgoff); - size_t max_nr_pages = fs->window_len/PAGE_SIZE - pgoff; + size_t max_nr_pages = fs->window_len / PAGE_SIZE - pgoff; if (kaddr) *kaddr = fs->window_kaddr + offset; @@ -895,7 +894,7 @@ static int virtio_fs_probe(struct virtio_device *vdev) out_vqs: virtio_reset_device(vdev); - virtio_fs_cleanup_vqs(vdev, fs); + virtio_fs_cleanup_vqs(vdev); kfree(fs->vqs); out: @@ -927,7 +926,7 @@ static void virtio_fs_remove(struct virtio_device *vdev) virtio_fs_stop_all_queues(fs); virtio_fs_drain_all_queues_locked(fs); virtio_reset_device(vdev); - virtio_fs_cleanup_vqs(vdev, fs); + virtio_fs_cleanup_vqs(vdev); vdev->priv = NULL; /* Put device reference on virtio_fs object */ diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 57ff883d432c..05bee80ac7de 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -82,31 +82,6 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, } /** - * gfs2_writepage - Write page for writeback mappings - * @page: The page - * @wbc: The writeback control - */ -static int gfs2_writepage(struct page *page, struct writeback_control *wbc) -{ - struct inode *inode = page->mapping->host; - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_sbd *sdp = GFS2_SB(inode); - struct iomap_writepage_ctx wpc = { }; - - if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl))) - goto out; - if (current->journal_info) - goto redirty; - return iomap_writepage(page, wbc, &wpc, &gfs2_writeback_ops); - -redirty: - redirty_page_for_writepage(wbc, page); -out: - unlock_page(page); - return 0; -} - -/** * gfs2_write_jdata_page - gfs2 jdata-specific version of block_write_full_page * @page: The page to write * @wbc: The writeback control @@ -765,7 +740,6 @@ cannot_release: } static const struct address_space_operations gfs2_aops = { - .writepage = gfs2_writepage, .writepages = gfs2_writepages, .read_folio = gfs2_read_folio, .readahead = gfs2_readahead, diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index a0562dd1bada..54a6d17b8c25 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -2016,7 +2016,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, l_blocks++; } - gfs2_rlist_alloc(&rlist); + gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE, LM_FLAG_NODE_SCOPE); for (x = 0; x < rlist.rl_rgrps; x++) { struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(rlist.rl_ghs[x].gh_gl); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 2cceb193dcd8..892006fbbb09 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -780,7 +780,7 @@ static inline bool should_fault_in_pages(struct iov_iter *i, if (!count) return false; - if (!iter_is_iovec(i)) + if (!user_backed_iter(i)) return false; size = PAGE_SIZE; @@ -1066,8 +1066,7 @@ out_unlock: gfs2_glock_dq(gh); out_uninit: gfs2_holder_uninit(gh); - if (statfs_gh) - kfree(statfs_gh); + kfree(statfs_gh); from->count = orig_count - written; return written ? written : ret; } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index c992d53013d3..41b6c89e4bf7 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -405,10 +405,13 @@ static void do_error(struct gfs2_glock *gl, const int ret) /** * demote_incompat_holders - demote incompatible demoteable holders * @gl: the glock we want to promote - * @new_gh: the new holder to be promoted + * @current_gh: the newly promoted holder + * + * We're passing the newly promoted holder in @current_gh, but actually, any of + * the strong holders would do. */ static void demote_incompat_holders(struct gfs2_glock *gl, - struct gfs2_holder *new_gh) + struct gfs2_holder *current_gh) { struct gfs2_holder *gh, *tmp; @@ -424,8 +427,10 @@ static void demote_incompat_holders(struct gfs2_glock *gl, */ if (!test_bit(HIF_HOLDER, &gh->gh_iflags)) return; + if (gh == current_gh) + continue; if (test_bit(HIF_MAY_DEMOTE, &gh->gh_iflags) && - !may_grant(gl, new_gh, gh)) { + !may_grant(gl, current_gh, gh)) { /* * We should not recurse into do_promote because * __gfs2_glock_dq only calls handle_callback, @@ -478,8 +483,7 @@ find_first_strong_holder(struct gfs2_glock *gl) * gfs2_instantiate - Call the glops instantiate function * @gh: The glock holder * - * Returns: 0 if instantiate was successful, 2 if type specific operation is - * underway, or error. + * Returns: 0 if instantiate was successful, or error. */ int gfs2_instantiate(struct gfs2_holder *gh) { @@ -489,7 +493,7 @@ int gfs2_instantiate(struct gfs2_holder *gh) again: if (!test_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags)) - return 0; + goto done; /* * Since we unlock the lockref lock, we set a flag to indicate @@ -508,78 +512,55 @@ again: goto again; } - ret = glops->go_instantiate(gh); + ret = glops->go_instantiate(gl); if (!ret) clear_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags); clear_and_wake_up_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags); - return ret; + if (ret) + return ret; + +done: + if (glops->go_held) + return glops->go_held(gh); + return 0; } /** * do_promote - promote as many requests as possible on the current queue * @gl: The glock * - * Returns: 1 if there is a blocked holder at the head of the list, or 2 - * if a type specific operation is underway. + * Returns: 1 if there is a blocked holder at the head of the list */ static int do_promote(struct gfs2_glock *gl) -__releases(&gl->gl_lockref.lock) -__acquires(&gl->gl_lockref.lock) { - struct gfs2_holder *gh, *tmp, *first_gh; + struct gfs2_holder *gh, *current_gh; bool incompat_holders_demoted = false; - bool lock_released; - int ret; -restart: - first_gh = find_first_strong_holder(gl); - list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) { - lock_released = false; + current_gh = find_first_strong_holder(gl); + list_for_each_entry(gh, &gl->gl_holders, gh_list) { if (test_bit(HIF_HOLDER, &gh->gh_iflags)) continue; - if (!may_grant(gl, first_gh, gh)) { + if (!may_grant(gl, current_gh, gh)) { /* - * If we get here, it means we may not grant this holder for - * some reason. If this holder is the head of the list, it - * means we have a blocked holder at the head, so return 1. + * If we get here, it means we may not grant this + * holder for some reason. If this holder is at the + * head of the list, it means we have a blocked holder + * at the head, so return 1. */ if (list_is_first(&gh->gh_list, &gl->gl_holders)) return 1; do_error(gl, 0); break; } - if (!incompat_holders_demoted) { - demote_incompat_holders(gl, first_gh); - incompat_holders_demoted = true; - first_gh = gh; - } - if (test_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags) && - !(gh->gh_flags & GL_SKIP) && gl->gl_ops->go_instantiate) { - lock_released = true; - spin_unlock(&gl->gl_lockref.lock); - ret = gfs2_instantiate(gh); - spin_lock(&gl->gl_lockref.lock); - if (ret) { - if (ret == 1) - return 2; - gh->gh_error = ret; - list_del_init(&gh->gh_list); - trace_gfs2_glock_queue(gh, 0); - gfs2_holder_wake(gh); - goto restart; - } - } set_bit(HIF_HOLDER, &gh->gh_iflags); trace_gfs2_promote(gh); gfs2_holder_wake(gh); - /* - * If we released the gl_lockref.lock the holders list may have - * changed. For that reason, we start again at the start of - * the holders queue. - */ - if (lock_released) - goto restart; + if (!incompat_holders_demoted) { + current_gh = gh; + demote_incompat_holders(gl, current_gh); + incompat_holders_demoted = true; + } } return 0; } @@ -657,7 +638,6 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret) const struct gfs2_glock_operations *glops = gl->gl_ops; struct gfs2_holder *gh; unsigned state = ret & LM_OUT_ST_MASK; - int rv; spin_lock(&gl->gl_lockref.lock); trace_gfs2_glock_state_change(gl, state); @@ -715,6 +695,8 @@ retry: gfs2_demote_wake(gl); if (state != LM_ST_UNLOCKED) { if (glops->go_xmote_bh) { + int rv; + spin_unlock(&gl->gl_lockref.lock); rv = glops->go_xmote_bh(gl); spin_lock(&gl->gl_lockref.lock); @@ -723,13 +705,10 @@ retry: goto out; } } - rv = do_promote(gl); - if (rv == 2) - goto out_locked; + do_promote(gl); } out: clear_bit(GLF_LOCK, &gl->gl_flags); -out_locked: spin_unlock(&gl->gl_lockref.lock); } @@ -886,7 +865,6 @@ __releases(&gl->gl_lockref.lock) __acquires(&gl->gl_lockref.lock) { struct gfs2_holder *gh = NULL; - int ret; if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) return; @@ -905,18 +883,14 @@ __acquires(&gl->gl_lockref.lock) } else { if (test_bit(GLF_DEMOTE, &gl->gl_flags)) gfs2_demote_wake(gl); - ret = do_promote(gl); - if (ret == 0) + if (do_promote(gl) == 0) goto out_unlock; - if (ret == 2) - goto out; gh = find_first_waiter(gl); gl->gl_target = gh->gh_state; if (!(gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) do_error(gl, 0); /* Fail queued try locks */ } do_xmote(gl, gh, gl->gl_target); -out: return; out_sched: @@ -1314,6 +1288,25 @@ static void gfs2_glock_update_hold_time(struct gfs2_glock *gl, } /** + * gfs2_glock_holder_ready - holder is ready and its error code can be collected + * @gh: the glock holder + * + * Called when a glock holder no longer needs to be waited for because it is + * now either held (HIF_HOLDER set; gh_error == 0), or acquiring the lock has + * failed (gh_error != 0). + */ + +int gfs2_glock_holder_ready(struct gfs2_holder *gh) +{ + if (gh->gh_error || (gh->gh_flags & GL_SKIP)) + return gh->gh_error; + gh->gh_error = gfs2_instantiate(gh); + if (gh->gh_error) + gfs2_glock_dq(gh); + return gh->gh_error; +} + +/** * gfs2_glock_wait - wait on a glock acquisition * @gh: the glock holder * @@ -1327,7 +1320,7 @@ int gfs2_glock_wait(struct gfs2_holder *gh) might_sleep(); wait_on_bit(&gh->gh_iflags, HIF_WAIT, TASK_UNINTERRUPTIBLE); gfs2_glock_update_hold_time(gh->gh_gl, start_time); - return gh->gh_error; + return gfs2_glock_holder_ready(gh); } static int glocks_pending(unsigned int num_gh, struct gfs2_holder *ghs) @@ -1355,7 +1348,6 @@ int gfs2_glock_async_wait(unsigned int num_gh, struct gfs2_holder *ghs) struct gfs2_sbd *sdp = ghs[0].gh_gl->gl_name.ln_sbd; int i, ret = 0, timeout = 0; unsigned long start_time = jiffies; - bool keep_waiting; might_sleep(); /* @@ -1365,53 +1357,33 @@ int gfs2_glock_async_wait(unsigned int num_gh, struct gfs2_holder *ghs) for (i = 0; i < num_gh; i++) timeout += ghs[i].gh_gl->gl_hold_time << 1; -wait_for_dlm: if (!wait_event_timeout(sdp->sd_async_glock_wait, - !glocks_pending(num_gh, ghs), timeout)) + !glocks_pending(num_gh, ghs), timeout)) { ret = -ESTALE; /* request timed out. */ + goto out; + } - /* - * If dlm granted all our requests, we need to adjust the glock - * minimum hold time values according to how long we waited. - * - * If our request timed out, we need to repeatedly release any held - * glocks we acquired thus far to allow dlm to acquire the remaining - * glocks without deadlocking. We cannot currently cancel outstanding - * glock acquisitions. - * - * The HIF_WAIT bit tells us which requests still need a response from - * dlm. - * - * If dlm sent us any errors, we return the first error we find. - */ - keep_waiting = false; for (i = 0; i < num_gh; i++) { - /* Skip holders we have already dequeued below. */ - if (!gfs2_holder_queued(&ghs[i])) - continue; - /* Skip holders with a pending DLM response. */ - if (test_bit(HIF_WAIT, &ghs[i].gh_iflags)) { - keep_waiting = true; - continue; - } + struct gfs2_holder *gh = &ghs[i]; + int ret2; - if (test_bit(HIF_HOLDER, &ghs[i].gh_iflags)) { - if (ret == -ESTALE) - gfs2_glock_dq(&ghs[i]); - else - gfs2_glock_update_hold_time(ghs[i].gh_gl, - start_time); + if (test_bit(HIF_HOLDER, &gh->gh_iflags)) { + gfs2_glock_update_hold_time(gh->gh_gl, + start_time); } + ret2 = gfs2_glock_holder_ready(gh); if (!ret) - ret = ghs[i].gh_error; + ret = ret2; } - if (keep_waiting) - goto wait_for_dlm; +out: + if (ret) { + for (i = 0; i < num_gh; i++) { + struct gfs2_holder *gh = &ghs[i]; - /* - * At this point, we've either acquired all locks or released them all. - */ + gfs2_glock_dq(gh); + } + } return ret; } @@ -1490,10 +1462,10 @@ __acquires(&gl->gl_lockref.lock) if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) { if (test_bit(GLF_LOCK, &gl->gl_flags)) { - struct gfs2_holder *first_gh; + struct gfs2_holder *current_gh; - first_gh = find_first_strong_holder(gl); - try_futile = !may_grant(gl, first_gh, gh); + current_gh = find_first_strong_holder(gl); + try_futile = !may_grant(gl, current_gh, gh); } if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags)) goto fail; @@ -1779,7 +1751,7 @@ static int glock_compare(const void *arg_a, const void *arg_b) } /** - * nq_m_sync - synchonously acquire more than one glock in deadlock free order + * nq_m_sync - synchronously acquire more than one glock in deadlock free order * @num_gh: the number of structures * @ghs: an array of struct gfs2_holder structures * @p: placeholder for the holder structure to pass back @@ -1800,8 +1772,6 @@ static int nq_m_sync(unsigned int num_gh, struct gfs2_holder *ghs, sort(p, num_gh, sizeof(struct gfs2_holder *), glock_compare, NULL); for (x = 0; x < num_gh; x++) { - p[x]->gh_flags &= ~(LM_FLAG_TRY | GL_ASYNC); - error = gfs2_glock_nq(p[x]); if (error) { while (x--) @@ -1818,7 +1788,6 @@ static int nq_m_sync(unsigned int num_gh, struct gfs2_holder *ghs, * @num_gh: the number of structures * @ghs: an array of struct gfs2_holder structures * - * * Returns: 0 on success (all glocks acquired), * errno on failure (no glocks acquired) */ @@ -1833,7 +1802,6 @@ int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs) case 0: return 0; case 1: - ghs->gh_flags &= ~(LM_FLAG_TRY | GL_ASYNC); return gfs2_glock_nq(ghs); default: if (num_gh <= 4) @@ -2245,20 +2213,6 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp) glock_hash_walk(dump_glock_func, sdp); } -void gfs2_glock_finish_truncate(struct gfs2_inode *ip) -{ - struct gfs2_glock *gl = ip->i_gl; - int ret; - - ret = gfs2_truncatei_resume(ip); - gfs2_glock_assert_withdraw(gl, ret == 0); - - spin_lock(&gl->gl_lockref.lock); - clear_bit(GLF_LOCK, &gl->gl_flags); - run_queue(gl, 1); - spin_unlock(&gl->gl_lockref.lock); -} - static const char *state2str(unsigned state) { switch(state) { @@ -2533,7 +2487,7 @@ int __init gfs2_glock_init(void) return -ENOMEM; } - ret = register_shrinker(&glock_shrinker); + ret = register_shrinker(&glock_shrinker, "gfs2-glock"); if (ret) { destroy_workqueue(gfs2_delete_workqueue); destroy_workqueue(glock_workqueue); diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index c0ae9100a0bc..5aed8b500cf5 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -213,6 +213,7 @@ extern void gfs2_holder_uninit(struct gfs2_holder *gh); extern int gfs2_glock_nq(struct gfs2_holder *gh); extern int gfs2_glock_poll(struct gfs2_holder *gh); extern int gfs2_instantiate(struct gfs2_holder *gh); +extern int gfs2_glock_holder_ready(struct gfs2_holder *gh); extern int gfs2_glock_wait(struct gfs2_holder *gh); extern int gfs2_glock_async_wait(unsigned int num_gh, struct gfs2_holder *ghs); extern void gfs2_glock_dq(struct gfs2_holder *gh); @@ -273,7 +274,6 @@ extern void gfs2_cancel_delete_work(struct gfs2_glock *gl); extern bool gfs2_delete_work_queued(const struct gfs2_glock *gl); extern void gfs2_flush_delete_work(struct gfs2_sbd *sdp); extern void gfs2_gl_hash_clear(struct gfs2_sbd *sdp); -extern void gfs2_glock_finish_truncate(struct gfs2_inode *ip); extern void gfs2_glock_thaw(struct gfs2_sbd *sdp); extern void gfs2_glock_add_to_lru(struct gfs2_glock *gl); extern void gfs2_glock_free(struct gfs2_glock *gl); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 392800f082a6..49210a2e7ce7 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -485,35 +485,33 @@ int gfs2_inode_refresh(struct gfs2_inode *ip) * Returns: errno */ -static int inode_go_instantiate(struct gfs2_holder *gh) +static int inode_go_instantiate(struct gfs2_glock *gl) +{ + struct gfs2_inode *ip = gl->gl_object; + + if (!ip) /* no inode to populate - read it in later */ + return 0; + + return gfs2_inode_refresh(ip); +} + +static int inode_go_held(struct gfs2_holder *gh) { struct gfs2_glock *gl = gh->gh_gl; - struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct gfs2_inode *ip = gl->gl_object; int error = 0; if (!ip) /* no inode to populate - read it in later */ - goto out; - - error = gfs2_inode_refresh(ip); - if (error) - goto out; + return 0; if (gh->gh_state != LM_ST_DEFERRED) inode_dio_wait(&ip->i_inode); if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) && (gl->gl_state == LM_ST_EXCLUSIVE) && - (gh->gh_state == LM_ST_EXCLUSIVE)) { - spin_lock(&sdp->sd_trunc_lock); - if (list_empty(&ip->i_trunc_list)) - list_add(&ip->i_trunc_list, &sdp->sd_trunc_list); - spin_unlock(&sdp->sd_trunc_lock); - wake_up(&sdp->sd_quota_wait); - error = 1; - } + (gh->gh_state == LM_ST_EXCLUSIVE)) + error = gfs2_truncatei_resume(ip); -out: return error; } @@ -737,6 +735,7 @@ const struct gfs2_glock_operations gfs2_inode_glops = { .go_inval = inode_go_inval, .go_demote_ok = inode_go_demote_ok, .go_instantiate = inode_go_instantiate, + .go_held = inode_go_held, .go_dump = inode_go_dump, .go_type = LM_TYPE_INODE, .go_flags = GLOF_ASPACE | GLOF_LRU | GLOF_LVB, diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 8c00fb389ae5..d09d9892cd05 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -219,7 +219,8 @@ struct gfs2_glock_operations { int (*go_xmote_bh)(struct gfs2_glock *gl); void (*go_inval) (struct gfs2_glock *gl, int flags); int (*go_demote_ok) (const struct gfs2_glock *gl); - int (*go_instantiate) (struct gfs2_holder *gh); + int (*go_instantiate) (struct gfs2_glock *gl); + int (*go_held)(struct gfs2_holder *gh); void (*go_dump)(struct seq_file *seq, struct gfs2_glock *gl, const char *fs_id_buf); void (*go_callback)(struct gfs2_glock *gl, bool remote); @@ -396,7 +397,6 @@ struct gfs2_inode { atomic_t i_sizehint; /* hint of the write size */ struct rw_semaphore i_rw_mutex; struct list_head i_ordered; - struct list_head i_trunc_list; __be64 *i_hash_cache; u32 i_entries; u32 i_diskflags; @@ -784,8 +784,6 @@ struct gfs2_sbd { struct mutex sd_quota_mutex; struct mutex sd_quota_sync_mutex; wait_queue_head_t sd_quota_wait; - struct list_head sd_trunc_list; - spinlock_t sd_trunc_lock; unsigned int sd_quota_slots; unsigned long *sd_quota_bitmap; diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 2559a79cf14b..6ce369b096d4 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -1058,7 +1058,7 @@ restart: /* * Expand static jid arrays if necessary (by increments of RECOVER_SIZE_INC) - * to accomodate the largest slot number. (NB dlm slot numbers start at 1, + * to accommodate the largest slot number. (NB dlm slot numbers start at 1, * gfs2 jids start at 0, so jid = slot - 1) */ diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index eec4159b08aa..723639376ae2 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -131,7 +131,7 @@ __acquires(&sdp->sd_ail_lock) if (!mapping) continue; spin_unlock(&sdp->sd_ail_lock); - ret = generic_writepages(mapping, wbc); + ret = filemap_fdatawrite_wbc(mapping, wbc); if (need_resched()) { blk_finish_plug(plug); cond_resched(); @@ -222,8 +222,7 @@ out: spin_unlock(&sdp->sd_ail_lock); blk_finish_plug(&plug); if (ret) { - gfs2_lm(sdp, "gfs2_ail1_start_one (generic_writepages) " - "returned: %d\n", ret); + gfs2_lm(sdp, "gfs2_ail1_start_one returned: %d\n", ret); gfs2_withdraw(sdp); } trace_gfs2_ail_flush(sdp, wbc, 0); diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 244187e3e70f..14ae9de76277 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -38,7 +38,6 @@ static void gfs2_init_inode_once(void *foo) inode_init_once(&ip->i_inode); atomic_set(&ip->i_sizehint, 0); init_rwsem(&ip->i_rw_mutex); - INIT_LIST_HEAD(&ip->i_trunc_list); INIT_LIST_HEAD(&ip->i_ordered); ip->i_qadata = NULL; gfs2_holder_mark_uninitialized(&ip->i_rgd_gh); @@ -148,7 +147,7 @@ static int __init init_gfs2_fs(void) if (!gfs2_trans_cachep) goto fail_cachep8; - error = register_shrinker(&gfs2_qd_shrinker); + error = register_shrinker(&gfs2_qd_shrinker, "gfs2-qd"); if (error) goto fail_shrinker; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index c9b423c874a3..549879929c84 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -106,8 +106,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mutex_init(&sdp->sd_quota_mutex); mutex_init(&sdp->sd_quota_sync_mutex); init_waitqueue_head(&sdp->sd_quota_wait); - INIT_LIST_HEAD(&sdp->sd_trunc_list); - spin_lock_init(&sdp->sd_trunc_lock); spin_lock_init(&sdp->sd_bitmap_lock); INIT_LIST_HEAD(&sdp->sd_sc_inodes_list); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index c98a7faa67d3..f201eaf59d0d 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1517,25 +1517,6 @@ static void quotad_check_timeo(struct gfs2_sbd *sdp, const char *msg, } } -static void quotad_check_trunc_list(struct gfs2_sbd *sdp) -{ - struct gfs2_inode *ip; - - while(1) { - ip = NULL; - spin_lock(&sdp->sd_trunc_lock); - if (!list_empty(&sdp->sd_trunc_list)) { - ip = list_first_entry(&sdp->sd_trunc_list, - struct gfs2_inode, i_trunc_list); - list_del_init(&ip->i_trunc_list); - } - spin_unlock(&sdp->sd_trunc_lock); - if (ip == NULL) - return; - gfs2_glock_finish_truncate(ip); - } -} - void gfs2_wake_up_statfs(struct gfs2_sbd *sdp) { if (!sdp->sd_statfs_force_sync) { sdp->sd_statfs_force_sync = 1; @@ -1558,7 +1539,6 @@ int gfs2_quotad(void *data) unsigned long quotad_timeo = 0; unsigned long t = 0; DEFINE_WAIT(wait); - int empty; while (!kthread_should_stop()) { @@ -1579,19 +1559,13 @@ int gfs2_quotad(void *data) quotad_check_timeo(sdp, "sync", gfs2_quota_sync, t, "ad_timeo, &tune->gt_quota_quantum); - /* Check for & recover partially truncated inodes */ - quotad_check_trunc_list(sdp); - try_to_freeze(); bypass: t = min(quotad_timeo, statfs_timeo); prepare_to_wait(&sdp->sd_quota_wait, &wait, TASK_INTERRUPTIBLE); - spin_lock(&sdp->sd_trunc_lock); - empty = list_empty(&sdp->sd_trunc_list); - spin_unlock(&sdp->sd_trunc_lock); - if (empty && !sdp->sd_statfs_force_sync) + if (!sdp->sd_statfs_force_sync) t -= schedule_timeout(t); else t = 0; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 8a63870eef5a..f602fb844951 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1196,9 +1196,8 @@ static void rgrp_set_bitmap_flags(struct gfs2_rgrpd *rgd) * Returns: errno */ -int gfs2_rgrp_go_instantiate(struct gfs2_holder *gh) +int gfs2_rgrp_go_instantiate(struct gfs2_glock *gl) { - struct gfs2_glock *gl = gh->gh_gl; struct gfs2_rgrpd *rgd = gl->gl_object; struct gfs2_sbd *sdp = rgd->rd_sbd; unsigned int length = rgd->rd_length; @@ -2720,12 +2719,15 @@ void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist, * gfs2_rlist_alloc - all RGs have been added to the rlist, now allocate * and initialize an array of glock holders for them * @rlist: the list of resource groups + * @state: the state we're requesting + * @flags: the modifier flags * * FIXME: Don't use NOFAIL * */ -void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist) +void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, + unsigned int state, u16 flags) { unsigned int x; @@ -2733,8 +2735,8 @@ void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist) sizeof(struct gfs2_holder), GFP_NOFS | __GFP_NOFAIL); for (x = 0; x < rlist->rl_rgrps; x++) - gfs2_holder_init(rlist->rl_rgd[x]->rd_gl, LM_ST_EXCLUSIVE, - LM_FLAG_NODE_SCOPE, &rlist->rl_ghs[x]); + gfs2_holder_init(rlist->rl_rgd[x]->rd_gl, state, flags, + &rlist->rl_ghs[x]); } /** diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index 46dd94e9e085..00b30cf893af 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -31,7 +31,7 @@ extern struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd); extern void gfs2_clear_rgrpd(struct gfs2_sbd *sdp); extern int gfs2_rindex_update(struct gfs2_sbd *sdp); extern void gfs2_free_clones(struct gfs2_rgrpd *rgd); -extern int gfs2_rgrp_go_instantiate(struct gfs2_holder *gh); +extern int gfs2_rgrp_go_instantiate(struct gfs2_glock *gl); extern void gfs2_rgrp_brelse(struct gfs2_rgrpd *rgd); extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip); @@ -64,7 +64,8 @@ struct gfs2_rgrp_list { extern void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist, u64 block); -extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist); +extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, + unsigned int state, u16 flags); extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist); extern u64 gfs2_ri_total(struct gfs2_sbd *sdp); extern void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_rgrpd *rgd, diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index bdb773e5c88f..b5b0f285b27f 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1196,7 +1196,7 @@ static bool gfs2_upgrade_iopen_glock(struct inode *inode) gfs2_glock_dq(gh); return false; } - return true; + return gfs2_glock_holder_ready(gh) == 0; } /** diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 0c5650fe1fd1..f6a66050380e 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -1313,7 +1313,7 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) else goto out; - gfs2_rlist_alloc(&rlist); + gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE, LM_FLAG_NODE_SCOPE); for (x = 0; x < rlist.rl_rgrps; x++) { rgd = gfs2_glock2rgrp(rlist.rl_ghs[x].gh_gl); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 20336cb3c040..f7a5b5124d8a 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -11,7 +11,6 @@ #include <linux/thread_info.h> #include <asm/current.h> -#include <linux/sched/signal.h> /* remove ASAP */ #include <linux/falloc.h> #include <linux/fs.h> #include <linux/mount.h> @@ -40,7 +39,6 @@ #include <linux/uaccess.h> #include <linux/sched/mm.h> -static const struct super_operations hugetlbfs_ops; static const struct address_space_operations hugetlbfs_aops; const struct file_operations hugetlbfs_file_operations; static const struct inode_operations hugetlbfs_dir_inode_operations; @@ -284,39 +282,9 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, } #endif -static size_t -hugetlbfs_read_actor(struct page *page, unsigned long offset, - struct iov_iter *to, unsigned long size) -{ - size_t copied = 0; - int i, chunksize; - - /* Find which 4k chunk and offset with in that chunk */ - i = offset >> PAGE_SHIFT; - offset = offset & ~PAGE_MASK; - - while (size) { - size_t n; - chunksize = PAGE_SIZE; - if (offset) - chunksize -= offset; - if (chunksize > size) - chunksize = size; - n = copy_page_to_iter(&page[i], offset, chunksize, to); - copied += n; - if (n != chunksize) - return copied; - offset = 0; - size -= chunksize; - i++; - } - return copied; -} - /* * Support for read() - Find the page attached to f_mapping and copy out the - * data. Its *very* similar to generic_file_buffered_read(), we can't use that - * since it has PAGE_SIZE assumptions. + * data. This provides functionality similar to filemap_read(). */ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) { @@ -363,7 +331,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) /* * We have the page, copy it to user space buffer. */ - copied = hugetlbfs_read_actor(page, offset, to, nr); + copied = copy_page_to_iter(page, offset, nr, to); put_page(page); } offset += copied; @@ -1082,7 +1050,7 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bsize = huge_page_size(h); if (sbinfo) { spin_lock(&sbinfo->stat_lock); - /* If no limits set, just report 0 for max/free/used + /* If no limits set, just report 0 or -1 for max/free/used * blocks, like simple_statfs() */ if (sbinfo->spool) { long free_pages; @@ -1309,7 +1277,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par ps = memparse(param->string, &rest); ctx->hstate = size_to_hstate(ps); if (!ctx->hstate) { - pr_err("Unsupported page size %lu MB\n", ps >> 20); + pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); return -EINVAL; } return 0; @@ -1385,7 +1353,7 @@ hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc) /* * Allocate and initialize subpool if maximum or minimum size is * specified. Any needed reservations (for minimum size) are taken - * taken when the subpool is created. + * when the subpool is created. */ if (ctx->max_hpages != -1 || ctx->min_hpages != -1) { sbinfo->spool = hugepage_new_subpool(ctx->hstate, @@ -1555,7 +1523,7 @@ static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h) } if (IS_ERR(mnt)) pr_err("Cannot mount internal hugetlbfs for page size %luK", - huge_page_size(h) >> 10); + huge_page_size(h) / SZ_1K); return mnt; } diff --git a/fs/inode.c b/fs/inode.c index 524ee91f74a6..ba1de23c13c1 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -422,6 +422,7 @@ void inode_init_once(struct inode *inode) INIT_LIST_HEAD(&inode->i_io_list); INIT_LIST_HEAD(&inode->i_wb_list); INIT_LIST_HEAD(&inode->i_lru); + INIT_LIST_HEAD(&inode->i_sb_list); __address_space_init_once(&inode->i_data); i_size_ordered_init(inode); } @@ -1021,7 +1022,6 @@ struct inode *new_inode_pseudo(struct super_block *sb) spin_lock(&inode->i_lock); inode->i_state = 0; spin_unlock(&inode->i_lock); - INIT_LIST_HEAD(&inode->i_sb_list); } return inode; } @@ -1165,7 +1165,6 @@ struct inode *inode_insert5(struct inode *inode, unsigned long hashval, { struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval); struct inode *old; - bool creating = inode->i_state & I_CREATING; again: spin_lock(&inode_hash_lock); @@ -1199,7 +1198,12 @@ again: inode->i_state |= I_NEW; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); - if (!creating) + + /* + * Add inode to the sb list if it's not already. It has I_NEW at this + * point, so it should be safe to test i_sb_list locklessly. + */ + if (list_empty(&inode->i_sb_list)) inode_sb_list_add(inode); unlock: spin_unlock(&inode_hash_lock); @@ -2014,23 +2018,25 @@ static int __file_remove_privs(struct file *file, unsigned int flags) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); - int error; + int error = 0; int kill; if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(dentry); - if (kill <= 0) + if (kill < 0) return kill; - if (flags & IOCB_NOWAIT) - return -EAGAIN; + if (kill) { + if (flags & IOCB_NOWAIT) + return -EAGAIN; + + error = __remove_privs(file_mnt_user_ns(file), dentry, kill); + } - error = __remove_privs(file_mnt_user_ns(file), dentry, kill); if (!error) inode_has_no_xattr(inode); - return error; } @@ -2326,10 +2332,6 @@ void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; - else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && - !in_group_p(i_gid_into_mnt(mnt_userns, dir)) && - !capable_wrt_inode_uidgid(mnt_userns, dir, CAP_FSETID)) - mode &= ~S_ISGID; } else inode_fsgid_set(inode, mnt_userns); inode->i_mode = mode; @@ -2485,3 +2487,33 @@ struct timespec64 current_time(struct inode *inode) return timestamp_truncate(now, inode); } EXPORT_SYMBOL(current_time); + +/** + * mode_strip_sgid - handle the sgid bit for non-directories + * @mnt_userns: User namespace of the mount the inode was created from + * @dir: parent directory inode + * @mode: mode of the file to be created in @dir + * + * If the @mode of the new file has both the S_ISGID and S_IXGRP bit + * raised and @dir has the S_ISGID bit raised ensure that the caller is + * either in the group of the parent directory or they have CAP_FSETID + * in their user namespace and are privileged over the parent directory. + * In all other cases, strip the S_ISGID bit from @mode. + * + * Return: the new mode to use for the file + */ +umode_t mode_strip_sgid(struct user_namespace *mnt_userns, + const struct inode *dir, umode_t mode) +{ + if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP)) + return mode; + if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) + return mode; + if (in_group_p(i_gid_into_mnt(mnt_userns, dir))) + return mode; + if (capable_wrt_inode_uidgid(mnt_userns, dir, CAP_FSETID)) + return mode; + + return mode & ~S_ISGID; +} +EXPORT_SYMBOL(mode_strip_sgid); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 2b82c7f1de88..ca5c62901541 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1529,21 +1529,6 @@ unlock: } int -iomap_writepage(struct page *page, struct writeback_control *wbc, - struct iomap_writepage_ctx *wpc, - const struct iomap_writeback_ops *ops) -{ - int ret; - - wpc->ops = ops; - ret = iomap_do_writepage(page, wbc, wpc); - if (!wpc->ioend) - return ret; - return iomap_submit_ioend(wpc, wpc->ioend, ret); -} -EXPORT_SYMBOL_GPL(iomap_writepage); - -int iomap_writepages(struct address_space *mapping, struct writeback_control *wbc, struct iomap_writepage_ctx *wpc, const struct iomap_writeback_ops *ops) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index c75d33d5c3ce..4eb559a16c9e 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -533,7 +533,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, iomi.flags |= IOMAP_NOWAIT; } - if (iter_is_iovec(iter)) + if (user_backed_iter(iter)) dio->flags |= IOMAP_DIO_DIRTY; } else { iomi.flags |= IOMAP_WRITE; diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 746132998c57..51bd38da21cd 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -203,7 +203,7 @@ int jbd2_log_do_checkpoint(journal_t *journal) tid_t this_tid; int result, batch_count = 0; - jbd_debug(1, "Start checkpoint\n"); + jbd2_debug(1, "Start checkpoint\n"); /* * First thing: if there are any transactions in the log which @@ -212,7 +212,7 @@ int jbd2_log_do_checkpoint(journal_t *journal) */ result = jbd2_cleanup_journal_tail(journal); trace_jbd2_checkpoint(journal, result); - jbd_debug(1, "cleanup_journal_tail returned %d\n", result); + jbd2_debug(1, "cleanup_journal_tail returned %d\n", result); if (result <= 0) return result; @@ -804,5 +804,5 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact trace_jbd2_drop_transaction(journal, transaction); - jbd_debug(1, "Dropping transaction %d, all done\n", transaction->t_tid); + jbd2_debug(1, "Dropping transaction %d, all done\n", transaction->t_tid); } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 890b5543a1c5..b2b2bc9b88d9 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -421,7 +421,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) /* Do we need to erase the effects of a prior jbd2_journal_flush? */ if (journal->j_flags & JBD2_FLUSHED) { - jbd_debug(3, "super block updated\n"); + jbd2_debug(3, "super block updated\n"); mutex_lock_io(&journal->j_checkpoint_mutex); /* * We hold j_checkpoint_mutex so tail cannot change under us. @@ -435,7 +435,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) REQ_SYNC); mutex_unlock(&journal->j_checkpoint_mutex); } else { - jbd_debug(3, "superblock not updated\n"); + jbd2_debug(3, "superblock not updated\n"); } J_ASSERT(journal->j_running_transaction != NULL); @@ -467,7 +467,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) commit_transaction = journal->j_running_transaction; trace_jbd2_start_commit(journal, commit_transaction); - jbd_debug(1, "JBD2: starting commit of transaction %d\n", + jbd2_debug(1, "JBD2: starting commit of transaction %d\n", commit_transaction->t_tid); write_lock(&journal->j_state_lock); @@ -540,7 +540,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) __jbd2_journal_clean_checkpoint_list(journal, false); spin_unlock(&journal->j_list_lock); - jbd_debug(3, "JBD2: commit phase 1\n"); + jbd2_debug(3, "JBD2: commit phase 1\n"); /* * Clear revoked flag to reflect there is no revoked buffers @@ -553,13 +553,13 @@ void jbd2_journal_commit_transaction(journal_t *journal) */ jbd2_journal_switch_revoke_table(journal); + write_lock(&journal->j_state_lock); /* * Reserved credits cannot be claimed anymore, free them */ atomic_sub(atomic_read(&journal->j_reserved_credits), &commit_transaction->t_outstanding_credits); - write_lock(&journal->j_state_lock); trace_jbd2_commit_flushing(journal, commit_transaction); stats.run.rs_flushing = jiffies; stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked, @@ -573,7 +573,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) wake_up(&journal->j_wait_transaction_locked); write_unlock(&journal->j_state_lock); - jbd_debug(3, "JBD2: commit phase 2a\n"); + jbd2_debug(3, "JBD2: commit phase 2a\n"); /* * Now start flushing things to disk, in the order they appear @@ -586,7 +586,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) blk_start_plug(&plug); jbd2_journal_write_revoke_records(commit_transaction, &log_bufs); - jbd_debug(3, "JBD2: commit phase 2b\n"); + jbd2_debug(3, "JBD2: commit phase 2b\n"); /* * Way to go: we have now written out all of the data for a @@ -642,7 +642,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) if (!descriptor) { J_ASSERT (bufs == 0); - jbd_debug(4, "JBD2: get descriptor\n"); + jbd2_debug(4, "JBD2: get descriptor\n"); descriptor = jbd2_journal_get_descriptor_buffer( commit_transaction, @@ -652,7 +652,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) continue; } - jbd_debug(4, "JBD2: got buffer %llu (%p)\n", + jbd2_debug(4, "JBD2: got buffer %llu (%p)\n", (unsigned long long)descriptor->b_blocknr, descriptor->b_data); tagp = &descriptor->b_data[sizeof(journal_header_t)]; @@ -737,7 +737,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) commit_transaction->t_buffers == NULL || space_left < tag_bytes + 16 + csum_size) { - jbd_debug(4, "JBD2: Submit %d IOs\n", bufs); + jbd2_debug(4, "JBD2: Submit %d IOs\n", bufs); /* Write an end-of-descriptor marker before submitting the IOs. "tag" still points to @@ -839,7 +839,7 @@ start_journal_io: so we incur less scheduling load. */ - jbd_debug(3, "JBD2: commit phase 3\n"); + jbd2_debug(3, "JBD2: commit phase 3\n"); while (!list_empty(&io_bufs)) { struct buffer_head *bh = list_entry(io_bufs.prev, @@ -882,7 +882,7 @@ start_journal_io: J_ASSERT (commit_transaction->t_shadow_list == NULL); - jbd_debug(3, "JBD2: commit phase 4\n"); + jbd2_debug(3, "JBD2: commit phase 4\n"); /* Here we wait for the revoke record and descriptor record buffers */ while (!list_empty(&log_bufs)) { @@ -906,7 +906,7 @@ start_journal_io: if (err) jbd2_journal_abort(journal, err); - jbd_debug(3, "JBD2: commit phase 5\n"); + jbd2_debug(3, "JBD2: commit phase 5\n"); write_lock(&journal->j_state_lock); J_ASSERT(commit_transaction->t_state == T_COMMIT_DFLUSH); commit_transaction->t_state = T_COMMIT_JFLUSH; @@ -945,7 +945,7 @@ start_journal_io: transaction can be removed from any checkpoint list it was on before. */ - jbd_debug(3, "JBD2: commit phase 6\n"); + jbd2_debug(3, "JBD2: commit phase 6\n"); J_ASSERT(list_empty(&commit_transaction->t_inode_list)); J_ASSERT(commit_transaction->t_buffers == NULL); @@ -1122,7 +1122,7 @@ restart_loop: /* Done with this transaction! */ - jbd_debug(3, "JBD2: commit phase 7\n"); + jbd2_debug(3, "JBD2: commit phase 7\n"); J_ASSERT(commit_transaction->t_state == T_COMMIT_JFLUSH); @@ -1164,7 +1164,7 @@ restart_loop: journal->j_fc_cleanup_callback(journal, 1, commit_transaction->t_tid); trace_jbd2_end_commit(journal, commit_transaction); - jbd_debug(1, "JBD2: commit %d complete, head %d\n", + jbd2_debug(1, "JBD2: commit %d complete, head %d\n", journal->j_commit_sequence, journal->j_tail_sequence); write_lock(&journal->j_state_lock); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 2a1b9da7c3e3..6350d3857c89 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -49,8 +49,7 @@ #include <asm/page.h> #ifdef CONFIG_JBD2_DEBUG -ushort jbd2_journal_enable_debug __read_mostly; -EXPORT_SYMBOL(jbd2_journal_enable_debug); +static ushort jbd2_journal_enable_debug __read_mostly; module_param_named(jbd2_debug, jbd2_journal_enable_debug, ushort, 0644); MODULE_PARM_DESC(jbd2_debug, "Debugging level for jbd2"); @@ -81,7 +80,6 @@ EXPORT_SYMBOL(jbd2_journal_errno); EXPORT_SYMBOL(jbd2_journal_ack_err); EXPORT_SYMBOL(jbd2_journal_clear_err); EXPORT_SYMBOL(jbd2_log_wait_commit); -EXPORT_SYMBOL(jbd2_log_start_commit); EXPORT_SYMBOL(jbd2_journal_start_commit); EXPORT_SYMBOL(jbd2_journal_force_commit_nested); EXPORT_SYMBOL(jbd2_journal_wipe); @@ -115,7 +113,6 @@ void __jbd2_debug(int level, const char *file, const char *func, printk(KERN_DEBUG "%s: (%s, %u): %pV", file, func, line, &vaf); va_end(args); } -EXPORT_SYMBOL(__jbd2_debug); #endif /* Checksumming functions */ @@ -203,11 +200,11 @@ loop: if (journal->j_flags & JBD2_UNMOUNT) goto end_loop; - jbd_debug(1, "commit_sequence=%u, commit_request=%u\n", + jbd2_debug(1, "commit_sequence=%u, commit_request=%u\n", journal->j_commit_sequence, journal->j_commit_request); if (journal->j_commit_sequence != journal->j_commit_request) { - jbd_debug(1, "OK, requests differ\n"); + jbd2_debug(1, "OK, requests differ\n"); write_unlock(&journal->j_state_lock); del_timer_sync(&journal->j_commit_timer); jbd2_journal_commit_transaction(journal); @@ -222,7 +219,7 @@ loop: * good idea, because that depends on threads that may * be already stopped. */ - jbd_debug(1, "Now suspending kjournald2\n"); + jbd2_debug(1, "Now suspending kjournald2\n"); write_unlock(&journal->j_state_lock); try_to_freeze(); write_lock(&journal->j_state_lock); @@ -252,7 +249,7 @@ loop: finish_wait(&journal->j_wait_commit, &wait); } - jbd_debug(1, "kjournald2 wakes\n"); + jbd2_debug(1, "kjournald2 wakes\n"); /* * Were we woken up by a commit wakeup event? @@ -260,7 +257,7 @@ loop: transaction = journal->j_running_transaction; if (transaction && time_after_eq(jiffies, transaction->t_expires)) { journal->j_commit_request = transaction->t_tid; - jbd_debug(1, "woke because of timeout\n"); + jbd2_debug(1, "woke because of timeout\n"); } goto loop; @@ -268,7 +265,7 @@ end_loop: del_timer_sync(&journal->j_commit_timer); journal->j_task = NULL; wake_up(&journal->j_wait_done_commit); - jbd_debug(1, "Journal thread exiting.\n"); + jbd2_debug(1, "Journal thread exiting.\n"); write_unlock(&journal->j_state_lock); return 0; } @@ -481,7 +478,7 @@ repeat: * Called with j_state_lock locked for writing. * Returns true if a transaction commit was started. */ -int __jbd2_log_start_commit(journal_t *journal, tid_t target) +static int __jbd2_log_start_commit(journal_t *journal, tid_t target) { /* Return if the txn has already requested to be committed */ if (journal->j_commit_request == target) @@ -500,7 +497,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target) */ journal->j_commit_request = target; - jbd_debug(1, "JBD2: requesting commit %u/%u\n", + jbd2_debug(1, "JBD2: requesting commit %u/%u\n", journal->j_commit_request, journal->j_commit_sequence); journal->j_running_transaction->t_requested = jiffies; @@ -705,7 +702,7 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) } #endif while (tid_gt(tid, journal->j_commit_sequence)) { - jbd_debug(1, "JBD2: want %u, j_commit_sequence=%u\n", + jbd2_debug(1, "JBD2: want %u, j_commit_sequence=%u\n", tid, journal->j_commit_sequence); read_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_commit); @@ -1117,7 +1114,7 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) freed += journal->j_last - journal->j_first; trace_jbd2_update_log_tail(journal, tid, block, freed); - jbd_debug(1, + jbd2_debug(1, "Cleaning journal tail from %u to %u (offset %lu), " "freeing %lu\n", journal->j_tail_sequence, tid, block, freed); @@ -1418,7 +1415,8 @@ static journal_t *journal_init_common(struct block_device *bdev, if (percpu_counter_init(&journal->j_checkpoint_jh_count, 0, GFP_KERNEL)) goto err_cleanup; - if (register_shrinker(&journal->j_shrinker)) { + if (register_shrinker(&journal->j_shrinker, "jbd2-journal:(%u:%u)", + MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev))) { percpu_counter_destroy(&journal->j_checkpoint_jh_count); goto err_cleanup; } @@ -1497,7 +1495,7 @@ journal_t *jbd2_journal_init_inode(struct inode *inode) return NULL; } - jbd_debug(1, "JBD2: inode %s/%ld, size %lld, bits %d, blksize %ld\n", + jbd2_debug(1, "JBD2: inode %s/%ld, size %lld, bits %d, blksize %ld\n", inode->i_sb->s_id, inode->i_ino, (long long) inode->i_size, inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize); @@ -1577,7 +1575,7 @@ static int journal_reset(journal_t *journal) * attempting a write to a potential-readonly device. */ if (sb->s_start == 0) { - jbd_debug(1, "JBD2: Skipping superblock update on recovered sb " + jbd2_debug(1, "JBD2: Skipping superblock update on recovered sb " "(start %ld, seq %u, errno %d)\n", journal->j_tail, journal->j_tail_sequence, journal->j_errno); @@ -1681,7 +1679,7 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, } BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); - jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", + jbd2_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", tail_block, tail_tid); lock_buffer(journal->j_sb_buffer); @@ -1722,7 +1720,7 @@ static void jbd2_mark_journal_empty(journal_t *journal, blk_opf_t write_flags) return; } - jbd_debug(1, "JBD2: Marking journal as empty (seq %u)\n", + jbd2_debug(1, "JBD2: Marking journal as empty (seq %u)\n", journal->j_tail_sequence); sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); @@ -1865,7 +1863,7 @@ void jbd2_journal_update_sb_errno(journal_t *journal) errcode = journal->j_errno; if (errcode == -ESHUTDOWN) errcode = 0; - jbd_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode); + jbd2_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode); sb->s_errno = cpu_to_be32(errcode); jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA); @@ -2337,7 +2335,7 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, compat & JBD2_FEATURE_COMPAT_CHECKSUM) compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM; - jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n", + jbd2_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n", compat, ro, incompat); sb = journal->j_superblock; @@ -2406,7 +2404,7 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, { journal_superblock_t *sb; - jbd_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n", + jbd2_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n", compat, ro, incompat); sb = journal->j_superblock; @@ -2863,7 +2861,7 @@ static struct journal_head *journal_alloc_journal_head(void) #endif ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS); if (!ret) { - jbd_debug(1, "out of memory for journal_head\n"); + jbd2_debug(1, "out of memory for journal_head\n"); pr_notice_ratelimited("ENOMEM in %s, retrying.\n", __func__); ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS | __GFP_NOFAIL); diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index e699d6ab2c0e..f548479615c6 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -245,11 +245,11 @@ static int fc_do_one_pass(journal_t *journal, return 0; while (next_fc_block <= journal->j_fc_last) { - jbd_debug(3, "Fast commit replay: next block %ld\n", + jbd2_debug(3, "Fast commit replay: next block %ld\n", next_fc_block); err = jread(&bh, journal, next_fc_block); if (err) { - jbd_debug(3, "Fast commit replay: read error\n"); + jbd2_debug(3, "Fast commit replay: read error\n"); break; } @@ -263,7 +263,7 @@ static int fc_do_one_pass(journal_t *journal, } if (err) - jbd_debug(3, "Fast commit replay failed, err = %d\n", err); + jbd2_debug(3, "Fast commit replay failed, err = %d\n", err); return err; } @@ -297,7 +297,7 @@ int jbd2_journal_recover(journal_t *journal) */ if (!sb->s_start) { - jbd_debug(1, "No recovery required, last transaction %d\n", + jbd2_debug(1, "No recovery required, last transaction %d\n", be32_to_cpu(sb->s_sequence)); journal->j_transaction_sequence = be32_to_cpu(sb->s_sequence) + 1; return 0; @@ -309,10 +309,10 @@ int jbd2_journal_recover(journal_t *journal) if (!err) err = do_one_pass(journal, &info, PASS_REPLAY); - jbd_debug(1, "JBD2: recovery, exit status %d, " + jbd2_debug(1, "JBD2: recovery, exit status %d, " "recovered transactions %u to %u\n", err, info.start_transaction, info.end_transaction); - jbd_debug(1, "JBD2: Replayed %d and revoked %d/%d blocks\n", + jbd2_debug(1, "JBD2: Replayed %d and revoked %d/%d blocks\n", info.nr_replays, info.nr_revoke_hits, info.nr_revokes); /* Restart the log at the next transaction ID, thus invalidating @@ -362,7 +362,7 @@ int jbd2_journal_skip_recovery(journal_t *journal) #ifdef CONFIG_JBD2_DEBUG int dropped = info.end_transaction - be32_to_cpu(journal->j_superblock->s_sequence); - jbd_debug(1, + jbd2_debug(1, "JBD2: ignoring %d transaction%s from the journal.\n", dropped, (dropped == 1) ? "" : "s"); #endif @@ -484,7 +484,7 @@ static int do_one_pass(journal_t *journal, if (pass == PASS_SCAN) info->start_transaction = first_commit_ID; - jbd_debug(1, "Starting recovery pass %d\n", pass); + jbd2_debug(1, "Starting recovery pass %d\n", pass); /* * Now we walk through the log, transaction by transaction, @@ -510,7 +510,7 @@ static int do_one_pass(journal_t *journal, if (tid_geq(next_commit_ID, info->end_transaction)) break; - jbd_debug(2, "Scanning for sequence ID %u at %lu/%lu\n", + jbd2_debug(2, "Scanning for sequence ID %u at %lu/%lu\n", next_commit_ID, next_log_block, jbd2_has_feature_fast_commit(journal) ? journal->j_fc_last : journal->j_last); @@ -519,7 +519,7 @@ static int do_one_pass(journal_t *journal, * either the next descriptor block or the final commit * record. */ - jbd_debug(3, "JBD2: checking block %ld\n", next_log_block); + jbd2_debug(3, "JBD2: checking block %ld\n", next_log_block); err = jread(&bh, journal, next_log_block); if (err) goto failed; @@ -542,7 +542,7 @@ static int do_one_pass(journal_t *journal, blocktype = be32_to_cpu(tmp->h_blocktype); sequence = be32_to_cpu(tmp->h_sequence); - jbd_debug(3, "Found magic %d, sequence %d\n", + jbd2_debug(3, "Found magic %d, sequence %d\n", blocktype, sequence); if (sequence != next_commit_ID) { @@ -575,7 +575,7 @@ static int do_one_pass(journal_t *journal, goto failed; } need_check_commit_time = true; - jbd_debug(1, + jbd2_debug(1, "invalid descriptor block found in %lu\n", next_log_block); } @@ -758,7 +758,7 @@ static int do_one_pass(journal_t *journal, * It likely does not belong to same journal, * just end this recovery with success. */ - jbd_debug(1, "JBD2: Invalid checksum ignored in transaction %u, likely stale data\n", + jbd2_debug(1, "JBD2: Invalid checksum ignored in transaction %u, likely stale data\n", next_commit_ID); brelse(bh); goto done; @@ -826,7 +826,7 @@ static int do_one_pass(journal_t *journal, if (pass == PASS_SCAN && !jbd2_descriptor_block_csum_verify(journal, bh->b_data)) { - jbd_debug(1, "JBD2: invalid revoke block found in %lu\n", + jbd2_debug(1, "JBD2: invalid revoke block found in %lu\n", next_log_block); need_check_commit_time = true; } @@ -845,7 +845,7 @@ static int do_one_pass(journal_t *journal, continue; default: - jbd_debug(3, "Unrecognised magic %d, end of scan.\n", + jbd2_debug(3, "Unrecognised magic %d, end of scan.\n", blocktype); brelse(bh); goto done; diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index fa608788b93d..4556e4689024 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -398,7 +398,7 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr, } handle->h_revoke_credits--; - jbd_debug(2, "insert revoke for block %llu, bh_in=%p\n",blocknr, bh_in); + jbd2_debug(2, "insert revoke for block %llu, bh_in=%p\n",blocknr, bh_in); err = insert_revoke_hash(journal, blocknr, handle->h_transaction->t_tid); BUFFER_TRACE(bh_in, "exit"); @@ -428,7 +428,7 @@ int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh) int did_revoke = 0; /* akpm: debug */ struct buffer_head *bh = jh2bh(jh); - jbd_debug(4, "journal_head %p, cancelling revoke\n", jh); + jbd2_debug(4, "journal_head %p, cancelling revoke\n", jh); /* Is the existing Revoke bit valid? If so, we trust it, and * only perform the full cancel if the revoke bit is set. If @@ -444,7 +444,7 @@ int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh) if (need_cancel) { record = find_revoke_record(journal, bh->b_blocknr); if (record) { - jbd_debug(4, "cancelled existing revoke on " + jbd2_debug(4, "cancelled existing revoke on " "blocknr %llu\n", (unsigned long long)bh->b_blocknr); spin_lock(&journal->j_revoke_lock); list_del(&record->hash); @@ -560,7 +560,7 @@ void jbd2_journal_write_revoke_records(transaction_t *transaction, } if (descriptor) flush_descriptor(journal, descriptor, offset); - jbd_debug(1, "Wrote %d revoke records\n", count); + jbd2_debug(1, "Wrote %d revoke records\n", count); } /* diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index e9c308ae475f..e1be93ccd81c 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -373,7 +373,7 @@ alloc_transaction: return -ENOMEM; } - jbd_debug(3, "New handle %p going live.\n", handle); + jbd2_debug(3, "New handle %p going live.\n", handle); /* * We need to hold j_state_lock until t_updates has been incremented, @@ -453,7 +453,7 @@ repeat: handle->h_start_jiffies = jiffies; atomic_inc(&transaction->t_updates); atomic_inc(&transaction->t_handle_count); - jbd_debug(4, "Handle %p given %d credits (total %d, free %lu)\n", + jbd2_debug(4, "Handle %p given %d credits (total %d, free %lu)\n", handle, blocks, atomic_read(&transaction->t_outstanding_credits), jbd2_log_space_left(journal)); @@ -674,7 +674,7 @@ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records) /* Don't extend a locked-down transaction! */ if (transaction->t_state != T_RUNNING) { - jbd_debug(3, "denied handle %p %d blocks: " + jbd2_debug(3, "denied handle %p %d blocks: " "transaction not running\n", handle, nblocks); goto error_out; } @@ -689,7 +689,7 @@ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records) &transaction->t_outstanding_credits); if (wanted > journal->j_max_transaction_buffers) { - jbd_debug(3, "denied handle %p %d blocks: " + jbd2_debug(3, "denied handle %p %d blocks: " "transaction too large\n", handle, nblocks); atomic_sub(nblocks, &transaction->t_outstanding_credits); goto error_out; @@ -707,7 +707,7 @@ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records) handle->h_revoke_credits_requested += revoke_records; result = 0; - jbd_debug(3, "extended handle %p by %d\n", handle, nblocks); + jbd2_debug(3, "extended handle %p by %d\n", handle, nblocks); error_out: read_unlock(&journal->j_state_lock); return result; @@ -795,7 +795,7 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int revoke_records, * First unlink the handle from its current transaction, and start the * commit on that. */ - jbd_debug(2, "restarting handle %p\n", handle); + jbd2_debug(2, "restarting handle %p\n", handle); stop_this_handle(handle); handle->h_transaction = NULL; @@ -979,7 +979,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, journal = transaction->t_journal; - jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy); + jbd2_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy); JBUFFER_TRACE(jh, "entry"); repeat: @@ -1271,7 +1271,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) struct journal_head *jh = jbd2_journal_add_journal_head(bh); int err; - jbd_debug(5, "journal_head %p\n", jh); + jbd2_debug(5, "journal_head %p\n", jh); err = -EROFS; if (is_handle_aborted(handle)) goto out; @@ -1486,8 +1486,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; int ret = 0; - if (is_handle_aborted(handle)) - return -EROFS; if (!buffer_jbd(bh)) return -EUCLEAN; @@ -1496,7 +1494,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) * of the running transaction. */ jh = bh2jh(bh); - jbd_debug(5, "journal_head %p\n", jh); + jbd2_debug(5, "journal_head %p\n", jh); JBUFFER_TRACE(jh, "entry"); /* @@ -1534,6 +1532,18 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) journal = transaction->t_journal; spin_lock(&jh->b_state_lock); + if (is_handle_aborted(handle)) { + /* + * Check journal aborting with @jh->b_state_lock locked, + * since 'jh->b_transaction' could be replaced with + * 'jh->b_next_transaction' during old transaction + * committing if journal aborted, which may fail + * assertion on 'jh->b_frozen_data == NULL'. + */ + ret = -EROFS; + goto out_unlock_bh; + } + if (jh->b_modified == 0) { /* * This buffer's got modified and becoming part @@ -1818,7 +1828,7 @@ int jbd2_journal_stop(handle_t *handle) pid_t pid; if (--handle->h_ref > 0) { - jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1, + jbd2_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1, handle->h_ref); if (is_handle_aborted(handle)) return -EIO; @@ -1838,7 +1848,7 @@ int jbd2_journal_stop(handle_t *handle) if (is_handle_aborted(handle)) err = -EIO; - jbd_debug(4, "Handle %p going down\n", handle); + jbd2_debug(4, "Handle %p going down\n", handle); trace_jbd2_handle_stats(journal->j_fs_dev->bd_dev, tid, handle->h_type, handle->h_line_no, jiffies - handle->h_start_jiffies, @@ -1916,7 +1926,7 @@ int jbd2_journal_stop(handle_t *handle) * completes the commit thread, it just doesn't write * anything to disk. */ - jbd_debug(2, "transaction too old, requesting commit for " + jbd2_debug(2, "transaction too old, requesting commit for " "handle %p\n", handle); /* This is non-blocking */ jbd2_log_start_commit(journal, tid); @@ -2662,7 +2672,7 @@ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode, return -EROFS; journal = transaction->t_journal; - jbd_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino, + jbd2_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino, transaction->t_tid); spin_lock(&journal->j_list_lock); diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c index 1b07550485b9..5d826274570c 100644 --- a/fs/kernel_read_file.c +++ b/fs/kernel_read_file.c @@ -29,15 +29,15 @@ * change between calls to kernel_read_file(). * * Returns number of bytes read (no single read will be bigger - * than INT_MAX), or negative on error. + * than SSIZE_MAX), or negative on error. * */ -int kernel_read_file(struct file *file, loff_t offset, void **buf, - size_t buf_size, size_t *file_size, - enum kernel_read_file_id id) +ssize_t kernel_read_file(struct file *file, loff_t offset, void **buf, + size_t buf_size, size_t *file_size, + enum kernel_read_file_id id) { loff_t i_size, pos; - size_t copied; + ssize_t copied; void *allocated = NULL; bool whole_file; int ret; @@ -58,7 +58,7 @@ int kernel_read_file(struct file *file, loff_t offset, void **buf, goto out; } /* The file is too big for sane activities. */ - if (i_size > INT_MAX) { + if (i_size > SSIZE_MAX) { ret = -EFBIG; goto out; } @@ -124,12 +124,12 @@ out: } EXPORT_SYMBOL_GPL(kernel_read_file); -int kernel_read_file_from_path(const char *path, loff_t offset, void **buf, - size_t buf_size, size_t *file_size, - enum kernel_read_file_id id) +ssize_t kernel_read_file_from_path(const char *path, loff_t offset, void **buf, + size_t buf_size, size_t *file_size, + enum kernel_read_file_id id) { struct file *file; - int ret; + ssize_t ret; if (!path || !*path) return -EINVAL; @@ -144,14 +144,14 @@ int kernel_read_file_from_path(const char *path, loff_t offset, void **buf, } EXPORT_SYMBOL_GPL(kernel_read_file_from_path); -int kernel_read_file_from_path_initns(const char *path, loff_t offset, - void **buf, size_t buf_size, - size_t *file_size, - enum kernel_read_file_id id) +ssize_t kernel_read_file_from_path_initns(const char *path, loff_t offset, + void **buf, size_t buf_size, + size_t *file_size, + enum kernel_read_file_id id) { struct file *file; struct path root; - int ret; + ssize_t ret; if (!path || !*path) return -EINVAL; @@ -171,12 +171,12 @@ int kernel_read_file_from_path_initns(const char *path, loff_t offset, } EXPORT_SYMBOL_GPL(kernel_read_file_from_path_initns); -int kernel_read_file_from_fd(int fd, loff_t offset, void **buf, - size_t buf_size, size_t *file_size, - enum kernel_read_file_id id) +ssize_t kernel_read_file_from_fd(int fd, loff_t offset, void **buf, + size_t buf_size, size_t *file_size, + enum kernel_read_file_id id) { struct fd f = fdget(fd); - int ret = -EBADF; + ssize_t ret = -EBADF; if (!f.file || !(f.file->f_mode & FMODE_READ)) goto out; diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index 911444d21267..c5a5c7b90d72 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -121,8 +121,8 @@ out: return rc; } -static int calc_ntlmv2_hash(struct ksmbd_session *sess, char *ntlmv2_hash, - char *dname) +static int calc_ntlmv2_hash(struct ksmbd_conn *conn, struct ksmbd_session *sess, + char *ntlmv2_hash, char *dname) { int ret, len, conv_len; wchar_t *domain = NULL; @@ -158,7 +158,7 @@ static int calc_ntlmv2_hash(struct ksmbd_session *sess, char *ntlmv2_hash, } conv_len = smb_strtoUTF16(uniname, user_name(sess->user), len, - sess->conn->local_nls); + conn->local_nls); if (conv_len < 0 || conv_len > len) { ret = -EINVAL; goto out; @@ -182,7 +182,7 @@ static int calc_ntlmv2_hash(struct ksmbd_session *sess, char *ntlmv2_hash, } conv_len = smb_strtoUTF16((__le16 *)domain, dname, len, - sess->conn->local_nls); + conn->local_nls); if (conv_len < 0 || conv_len > len) { ret = -EINVAL; goto out; @@ -215,8 +215,9 @@ out: * * Return: 0 on success, error number on error */ -int ksmbd_auth_ntlmv2(struct ksmbd_session *sess, struct ntlmv2_resp *ntlmv2, - int blen, char *domain_name, char *cryptkey) +int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, + struct ntlmv2_resp *ntlmv2, int blen, char *domain_name, + char *cryptkey) { char ntlmv2_hash[CIFS_ENCPWD_SIZE]; char ntlmv2_rsp[CIFS_HMAC_MD5_HASH_SIZE]; @@ -230,7 +231,7 @@ int ksmbd_auth_ntlmv2(struct ksmbd_session *sess, struct ntlmv2_resp *ntlmv2, return -ENOMEM; } - rc = calc_ntlmv2_hash(sess, ntlmv2_hash, domain_name); + rc = calc_ntlmv2_hash(conn, sess, ntlmv2_hash, domain_name); if (rc) { ksmbd_debug(AUTH, "could not get v2 hash rc %d\n", rc); goto out; @@ -333,7 +334,8 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, /* process NTLMv2 authentication */ ksmbd_debug(AUTH, "decode_ntlmssp_authenticate_blob dname%s\n", domain_name); - ret = ksmbd_auth_ntlmv2(sess, (struct ntlmv2_resp *)((char *)authblob + nt_off), + ret = ksmbd_auth_ntlmv2(conn, sess, + (struct ntlmv2_resp *)((char *)authblob + nt_off), nt_len - CIFS_ENCPWD_SIZE, domain_name, conn->ntlmssp.cryptkey); kfree(domain_name); @@ -659,8 +661,9 @@ struct derivation { bool binding; }; -static int generate_key(struct ksmbd_session *sess, struct kvec label, - struct kvec context, __u8 *key, unsigned int key_size) +static int generate_key(struct ksmbd_conn *conn, struct ksmbd_session *sess, + struct kvec label, struct kvec context, __u8 *key, + unsigned int key_size) { unsigned char zero = 0x0; __u8 i[4] = {0, 0, 0, 1}; @@ -720,8 +723,8 @@ static int generate_key(struct ksmbd_session *sess, struct kvec label, goto smb3signkey_ret; } - if (sess->conn->cipher_type == SMB2_ENCRYPTION_AES256_CCM || - sess->conn->cipher_type == SMB2_ENCRYPTION_AES256_GCM) + if (conn->cipher_type == SMB2_ENCRYPTION_AES256_CCM || + conn->cipher_type == SMB2_ENCRYPTION_AES256_GCM) rc = crypto_shash_update(CRYPTO_HMACSHA256(ctx), L256, 4); else rc = crypto_shash_update(CRYPTO_HMACSHA256(ctx), L128, 4); @@ -756,17 +759,17 @@ static int generate_smb3signingkey(struct ksmbd_session *sess, if (!chann) return 0; - if (sess->conn->dialect >= SMB30_PROT_ID && signing->binding) + if (conn->dialect >= SMB30_PROT_ID && signing->binding) key = chann->smb3signingkey; else key = sess->smb3signingkey; - rc = generate_key(sess, signing->label, signing->context, key, + rc = generate_key(conn, sess, signing->label, signing->context, key, SMB3_SIGN_KEY_SIZE); if (rc) return rc; - if (!(sess->conn->dialect >= SMB30_PROT_ID && signing->binding)) + if (!(conn->dialect >= SMB30_PROT_ID && signing->binding)) memcpy(chann->smb3signingkey, key, SMB3_SIGN_KEY_SIZE); ksmbd_debug(AUTH, "dumping generated AES signing keys\n"); @@ -820,30 +823,31 @@ struct derivation_twin { struct derivation decryption; }; -static int generate_smb3encryptionkey(struct ksmbd_session *sess, +static int generate_smb3encryptionkey(struct ksmbd_conn *conn, + struct ksmbd_session *sess, const struct derivation_twin *ptwin) { int rc; - rc = generate_key(sess, ptwin->encryption.label, + rc = generate_key(conn, sess, ptwin->encryption.label, ptwin->encryption.context, sess->smb3encryptionkey, SMB3_ENC_DEC_KEY_SIZE); if (rc) return rc; - rc = generate_key(sess, ptwin->decryption.label, + rc = generate_key(conn, sess, ptwin->decryption.label, ptwin->decryption.context, sess->smb3decryptionkey, SMB3_ENC_DEC_KEY_SIZE); if (rc) return rc; ksmbd_debug(AUTH, "dumping generated AES encryption keys\n"); - ksmbd_debug(AUTH, "Cipher type %d\n", sess->conn->cipher_type); + ksmbd_debug(AUTH, "Cipher type %d\n", conn->cipher_type); ksmbd_debug(AUTH, "Session Id %llu\n", sess->id); ksmbd_debug(AUTH, "Session Key %*ph\n", SMB2_NTLMV2_SESSKEY_SIZE, sess->sess_key); - if (sess->conn->cipher_type == SMB2_ENCRYPTION_AES256_CCM || - sess->conn->cipher_type == SMB2_ENCRYPTION_AES256_GCM) { + if (conn->cipher_type == SMB2_ENCRYPTION_AES256_CCM || + conn->cipher_type == SMB2_ENCRYPTION_AES256_GCM) { ksmbd_debug(AUTH, "ServerIn Key %*ph\n", SMB3_GCM256_CRYPTKEY_SIZE, sess->smb3encryptionkey); ksmbd_debug(AUTH, "ServerOut Key %*ph\n", @@ -857,7 +861,8 @@ static int generate_smb3encryptionkey(struct ksmbd_session *sess, return 0; } -int ksmbd_gen_smb30_encryptionkey(struct ksmbd_session *sess) +int ksmbd_gen_smb30_encryptionkey(struct ksmbd_conn *conn, + struct ksmbd_session *sess) { struct derivation_twin twin; struct derivation *d; @@ -874,10 +879,11 @@ int ksmbd_gen_smb30_encryptionkey(struct ksmbd_session *sess) d->context.iov_base = "ServerIn "; d->context.iov_len = 10; - return generate_smb3encryptionkey(sess, &twin); + return generate_smb3encryptionkey(conn, sess, &twin); } -int ksmbd_gen_smb311_encryptionkey(struct ksmbd_session *sess) +int ksmbd_gen_smb311_encryptionkey(struct ksmbd_conn *conn, + struct ksmbd_session *sess) { struct derivation_twin twin; struct derivation *d; @@ -894,7 +900,7 @@ int ksmbd_gen_smb311_encryptionkey(struct ksmbd_session *sess) d->context.iov_base = sess->Preauth_HashValue; d->context.iov_len = 64; - return generate_smb3encryptionkey(sess, &twin); + return generate_smb3encryptionkey(conn, sess, &twin); } int ksmbd_gen_preauth_integrity_hash(struct ksmbd_conn *conn, char *buf, diff --git a/fs/ksmbd/auth.h b/fs/ksmbd/auth.h index 95629651cf26..25b772653de0 100644 --- a/fs/ksmbd/auth.h +++ b/fs/ksmbd/auth.h @@ -38,8 +38,9 @@ struct kvec; int ksmbd_crypt_message(struct ksmbd_conn *conn, struct kvec *iov, unsigned int nvec, int enc); void ksmbd_copy_gss_neg_header(void *buf); -int ksmbd_auth_ntlmv2(struct ksmbd_session *sess, struct ntlmv2_resp *ntlmv2, - int blen, char *domain_name, char *cryptkey); +int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, + struct ntlmv2_resp *ntlmv2, int blen, char *domain_name, + char *cryptkey); int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, int blob_len, struct ksmbd_conn *conn, struct ksmbd_session *sess); @@ -58,8 +59,10 @@ int ksmbd_gen_smb30_signingkey(struct ksmbd_session *sess, struct ksmbd_conn *conn); int ksmbd_gen_smb311_signingkey(struct ksmbd_session *sess, struct ksmbd_conn *conn); -int ksmbd_gen_smb30_encryptionkey(struct ksmbd_session *sess); -int ksmbd_gen_smb311_encryptionkey(struct ksmbd_session *sess); +int ksmbd_gen_smb30_encryptionkey(struct ksmbd_conn *conn, + struct ksmbd_session *sess); +int ksmbd_gen_smb311_encryptionkey(struct ksmbd_conn *conn, + struct ksmbd_session *sess); int ksmbd_gen_preauth_integrity_hash(struct ksmbd_conn *conn, char *buf, __u8 *pi_hash); int ksmbd_gen_sd_hash(struct ksmbd_conn *conn, char *sd_buf, int len, diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index e8f476c5f189..756ad631c019 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -36,6 +36,7 @@ void ksmbd_conn_free(struct ksmbd_conn *conn) list_del(&conn->conns_list); write_unlock(&conn_list_lock); + xa_destroy(&conn->sessions); kvfree(conn->request_buf); kfree(conn->preauth_info); kfree(conn); @@ -65,13 +66,14 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) conn->outstanding_credits = 0; init_waitqueue_head(&conn->req_running_q); + init_waitqueue_head(&conn->r_count_q); INIT_LIST_HEAD(&conn->conns_list); - INIT_LIST_HEAD(&conn->sessions); INIT_LIST_HEAD(&conn->requests); INIT_LIST_HEAD(&conn->async_requests); spin_lock_init(&conn->request_lock); spin_lock_init(&conn->credits_lock); ida_init(&conn->async_ida); + xa_init(&conn->sessions); spin_lock_init(&conn->llist_lock); INIT_LIST_HEAD(&conn->lock_list); @@ -164,7 +166,6 @@ int ksmbd_conn_write(struct ksmbd_work *work) struct kvec iov[3]; int iov_idx = 0; - ksmbd_conn_try_dequeue_request(work); if (!work->response_buf) { pr_err("NULL response header\n"); return -EINVAL; @@ -346,8 +347,8 @@ int ksmbd_conn_handler_loop(void *p) out: /* Wait till all reference dropped to the Server object*/ - while (atomic_read(&conn->r_count) > 0) - schedule_timeout(HZ); + wait_event(conn->r_count_q, atomic_read(&conn->r_count) == 0); + unload_nls(conn->local_nls); if (default_conn_ops.terminate_fn) diff --git a/fs/ksmbd/connection.h b/fs/ksmbd/connection.h index 98c1cbe45ec9..e7f7d5707951 100644 --- a/fs/ksmbd/connection.h +++ b/fs/ksmbd/connection.h @@ -20,13 +20,6 @@ #define KSMBD_SOCKET_BACKLOG 16 -/* - * WARNING - * - * This is nothing but a HACK. Session status should move to channel - * or to session. As of now we have 1 tcp_conn : 1 ksmbd_session, but - * we need to change it to 1 tcp_conn : N ksmbd_sessions. - */ enum { KSMBD_SESS_NEW = 0, KSMBD_SESS_GOOD, @@ -55,7 +48,7 @@ struct ksmbd_conn { struct nls_table *local_nls; struct list_head conns_list; /* smb session 1 per user */ - struct list_head sessions; + struct xarray sessions; unsigned long last_active; /* How many request are running currently */ atomic_t req_running; @@ -65,6 +58,7 @@ struct ksmbd_conn { unsigned int outstanding_credits; spinlock_t credits_lock; wait_queue_head_t req_running_q; + wait_queue_head_t r_count_q; /* Lock to protect requests list*/ spinlock_t request_lock; struct list_head requests; diff --git a/fs/ksmbd/ksmbd_netlink.h b/fs/ksmbd/ksmbd_netlink.h index 52aa0adeb951..e0cbcfa98c7e 100644 --- a/fs/ksmbd/ksmbd_netlink.h +++ b/fs/ksmbd/ksmbd_netlink.h @@ -349,6 +349,7 @@ enum KSMBD_TREE_CONN_STATUS { #define KSMBD_SHARE_FLAG_STREAMS BIT(11) #define KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS BIT(12) #define KSMBD_SHARE_FLAG_ACL_XATTR BIT(13) +#define KSMBD_SHARE_FLAG_UPDATE BIT(14) /* * Tree connect request flags. @@ -364,6 +365,7 @@ enum KSMBD_TREE_CONN_STATUS { #define KSMBD_TREE_CONN_FLAG_READ_ONLY BIT(1) #define KSMBD_TREE_CONN_FLAG_WRITABLE BIT(2) #define KSMBD_TREE_CONN_FLAG_ADMIN_ACCOUNT BIT(3) +#define KSMBD_TREE_CONN_FLAG_UPDATE BIT(4) /* * RPC over IPC. diff --git a/fs/ksmbd/mgmt/share_config.c b/fs/ksmbd/mgmt/share_config.c index cb72d30f5b71..c9bca1c2c834 100644 --- a/fs/ksmbd/mgmt/share_config.c +++ b/fs/ksmbd/mgmt/share_config.c @@ -51,12 +51,16 @@ static void kill_share(struct ksmbd_share_config *share) kfree(share); } -void __ksmbd_share_config_put(struct ksmbd_share_config *share) +void ksmbd_share_config_del(struct ksmbd_share_config *share) { down_write(&shares_table_lock); hash_del(&share->hlist); up_write(&shares_table_lock); +} +void __ksmbd_share_config_put(struct ksmbd_share_config *share) +{ + ksmbd_share_config_del(share); kill_share(share); } @@ -222,17 +226,3 @@ bool ksmbd_share_veto_filename(struct ksmbd_share_config *share, } return false; } - -void ksmbd_share_configs_cleanup(void) -{ - struct ksmbd_share_config *share; - struct hlist_node *tmp; - int i; - - down_write(&shares_table_lock); - hash_for_each_safe(shares_table, i, tmp, share, hlist) { - hash_del(&share->hlist); - kill_share(share); - } - up_write(&shares_table_lock); -} diff --git a/fs/ksmbd/mgmt/share_config.h b/fs/ksmbd/mgmt/share_config.h index 953befc94e84..902f2cb1963a 100644 --- a/fs/ksmbd/mgmt/share_config.h +++ b/fs/ksmbd/mgmt/share_config.h @@ -64,6 +64,7 @@ static inline int test_share_config_flag(struct ksmbd_share_config *share, return share->flags & flag; } +void ksmbd_share_config_del(struct ksmbd_share_config *share); void __ksmbd_share_config_put(struct ksmbd_share_config *share); static inline void ksmbd_share_config_put(struct ksmbd_share_config *share) @@ -76,6 +77,4 @@ static inline void ksmbd_share_config_put(struct ksmbd_share_config *share) struct ksmbd_share_config *ksmbd_share_config_get(char *name); bool ksmbd_share_veto_filename(struct ksmbd_share_config *share, const char *filename); -void ksmbd_share_configs_cleanup(void); - #endif /* __SHARE_CONFIG_MANAGEMENT_H__ */ diff --git a/fs/ksmbd/mgmt/tree_connect.c b/fs/ksmbd/mgmt/tree_connect.c index 0d28e723a28c..97ab7987df6e 100644 --- a/fs/ksmbd/mgmt/tree_connect.c +++ b/fs/ksmbd/mgmt/tree_connect.c @@ -16,9 +16,10 @@ #include "user_session.h" struct ksmbd_tree_conn_status -ksmbd_tree_conn_connect(struct ksmbd_session *sess, char *share_name) +ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, + char *share_name) { - struct ksmbd_tree_conn_status status = {-EINVAL, NULL}; + struct ksmbd_tree_conn_status status = {-ENOENT, NULL}; struct ksmbd_tree_connect_response *resp = NULL; struct ksmbd_share_config *sc; struct ksmbd_tree_connect *tree_conn = NULL; @@ -41,7 +42,7 @@ ksmbd_tree_conn_connect(struct ksmbd_session *sess, char *share_name) goto out_error; } - peer_addr = KSMBD_TCP_PEER_SOCKADDR(sess->conn); + peer_addr = KSMBD_TCP_PEER_SOCKADDR(conn); resp = ksmbd_ipc_tree_connect_request(sess, sc, tree_conn, @@ -56,6 +57,20 @@ ksmbd_tree_conn_connect(struct ksmbd_session *sess, char *share_name) goto out_error; tree_conn->flags = resp->connection_flags; + if (test_tree_conn_flag(tree_conn, KSMBD_TREE_CONN_FLAG_UPDATE)) { + struct ksmbd_share_config *new_sc; + + ksmbd_share_config_del(sc); + new_sc = ksmbd_share_config_get(share_name); + if (!new_sc) { + pr_err("Failed to update stale share config\n"); + status.ret = -ESTALE; + goto out_error; + } + ksmbd_share_config_put(sc); + sc = new_sc; + } + tree_conn->user = sess->user; tree_conn->share_conf = sc; status.tree_conn = tree_conn; diff --git a/fs/ksmbd/mgmt/tree_connect.h b/fs/ksmbd/mgmt/tree_connect.h index 18e2a996e0aa..71e50271dccf 100644 --- a/fs/ksmbd/mgmt/tree_connect.h +++ b/fs/ksmbd/mgmt/tree_connect.h @@ -12,6 +12,7 @@ struct ksmbd_share_config; struct ksmbd_user; +struct ksmbd_conn; struct ksmbd_tree_connect { int id; @@ -40,7 +41,8 @@ static inline int test_tree_conn_flag(struct ksmbd_tree_connect *tree_conn, struct ksmbd_session; struct ksmbd_tree_conn_status -ksmbd_tree_conn_connect(struct ksmbd_session *sess, char *share_name); +ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, + char *share_name); int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *tree_conn); diff --git a/fs/ksmbd/mgmt/user_session.c b/fs/ksmbd/mgmt/user_session.c index 8d8ffd8c6f19..3fa2139a0b30 100644 --- a/fs/ksmbd/mgmt/user_session.c +++ b/fs/ksmbd/mgmt/user_session.c @@ -32,11 +32,13 @@ static void free_channel_list(struct ksmbd_session *sess) { struct channel *chann, *tmp; + write_lock(&sess->chann_lock); list_for_each_entry_safe(chann, tmp, &sess->ksmbd_chann_list, chann_list) { list_del(&chann->chann_list); kfree(chann); } + write_unlock(&sess->chann_lock); } static void __session_rpc_close(struct ksmbd_session *sess, @@ -149,11 +151,6 @@ void ksmbd_session_destroy(struct ksmbd_session *sess) if (!sess) return; - if (!atomic_dec_and_test(&sess->refcnt)) - return; - - list_del(&sess->sessions_entry); - down_write(&sessions_table_lock); hash_del(&sess->hlist); up_write(&sessions_table_lock); @@ -181,53 +178,70 @@ static struct ksmbd_session *__session_lookup(unsigned long long id) return NULL; } -void ksmbd_session_register(struct ksmbd_conn *conn, - struct ksmbd_session *sess) +int ksmbd_session_register(struct ksmbd_conn *conn, + struct ksmbd_session *sess) { - sess->conn = conn; - list_add(&sess->sessions_entry, &conn->sessions); + sess->dialect = conn->dialect; + memcpy(sess->ClientGUID, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE); + return xa_err(xa_store(&conn->sessions, sess->id, sess, GFP_KERNEL)); } -void ksmbd_sessions_deregister(struct ksmbd_conn *conn) +static int ksmbd_chann_del(struct ksmbd_conn *conn, struct ksmbd_session *sess) { - struct ksmbd_session *sess; - - while (!list_empty(&conn->sessions)) { - sess = list_entry(conn->sessions.next, - struct ksmbd_session, - sessions_entry); + struct channel *chann, *tmp; - ksmbd_session_destroy(sess); + write_lock(&sess->chann_lock); + list_for_each_entry_safe(chann, tmp, &sess->ksmbd_chann_list, + chann_list) { + if (chann->conn == conn) { + list_del(&chann->chann_list); + kfree(chann); + write_unlock(&sess->chann_lock); + return 0; + } } -} + write_unlock(&sess->chann_lock); -static bool ksmbd_session_id_match(struct ksmbd_session *sess, - unsigned long long id) -{ - return sess->id == id; + return -ENOENT; } -struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, - unsigned long long id) +void ksmbd_sessions_deregister(struct ksmbd_conn *conn) { - struct ksmbd_session *sess = NULL; + struct ksmbd_session *sess; - list_for_each_entry(sess, &conn->sessions, sessions_entry) { - if (ksmbd_session_id_match(sess, id)) - return sess; + if (conn->binding) { + int bkt; + + down_write(&sessions_table_lock); + hash_for_each(sessions_table, bkt, sess, hlist) { + if (!ksmbd_chann_del(conn, sess)) { + up_write(&sessions_table_lock); + goto sess_destroy; + } + } + up_write(&sessions_table_lock); + } else { + unsigned long id; + + xa_for_each(&conn->sessions, id, sess) { + if (!ksmbd_chann_del(conn, sess)) + goto sess_destroy; + } } - return NULL; -} -int get_session(struct ksmbd_session *sess) -{ - return atomic_inc_not_zero(&sess->refcnt); + return; + +sess_destroy: + if (list_empty(&sess->ksmbd_chann_list)) { + xa_erase(&conn->sessions, sess->id); + ksmbd_session_destroy(sess); + } } -void put_session(struct ksmbd_session *sess) +struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, + unsigned long long id) { - if (atomic_dec_and_test(&sess->refcnt)) - pr_err("get/%s seems to be mismatched.", __func__); + return xa_load(&conn->sessions, id); } struct ksmbd_session *ksmbd_session_lookup_slowpath(unsigned long long id) @@ -236,10 +250,6 @@ struct ksmbd_session *ksmbd_session_lookup_slowpath(unsigned long long id) down_read(&sessions_table_lock); sess = __session_lookup(id); - if (sess) { - if (!get_session(sess)) - sess = NULL; - } up_read(&sessions_table_lock); return sess; @@ -253,6 +263,8 @@ struct ksmbd_session *ksmbd_session_lookup_all(struct ksmbd_conn *conn, sess = ksmbd_session_lookup(conn, id); if (!sess && conn->binding) sess = ksmbd_session_lookup_slowpath(id); + if (sess && sess->state != SMB2_SESSION_VALID) + sess = NULL; return sess; } @@ -314,12 +326,11 @@ static struct ksmbd_session *__session_create(int protocol) goto error; set_session_flag(sess, protocol); - INIT_LIST_HEAD(&sess->sessions_entry); xa_init(&sess->tree_conns); INIT_LIST_HEAD(&sess->ksmbd_chann_list); INIT_LIST_HEAD(&sess->rpc_handle_list); sess->sequence_number = 1; - atomic_set(&sess->refcnt, 1); + rwlock_init(&sess->chann_lock); switch (protocol) { case CIFDS_SESSION_FLAG_SMB2: diff --git a/fs/ksmbd/mgmt/user_session.h b/fs/ksmbd/mgmt/user_session.h index e241f16a3851..8934b8ee275b 100644 --- a/fs/ksmbd/mgmt/user_session.h +++ b/fs/ksmbd/mgmt/user_session.h @@ -33,8 +33,10 @@ struct preauth_session { struct ksmbd_session { u64 id; + __u16 dialect; + char ClientGUID[SMB2_CLIENT_GUID_SIZE]; + struct ksmbd_user *user; - struct ksmbd_conn *conn; unsigned int sequence_number; unsigned int flags; @@ -48,6 +50,7 @@ struct ksmbd_session { char sess_key[CIFS_KEY_SIZE]; struct hlist_node hlist; + rwlock_t chann_lock; struct list_head ksmbd_chann_list; struct xarray tree_conns; struct ida tree_conn_ida; @@ -57,9 +60,7 @@ struct ksmbd_session { __u8 smb3decryptionkey[SMB3_ENC_DEC_KEY_SIZE]; __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; - struct list_head sessions_entry; struct ksmbd_file_table file_table; - atomic_t refcnt; }; static inline int test_session_flag(struct ksmbd_session *sess, int bit) @@ -84,8 +85,8 @@ void ksmbd_session_destroy(struct ksmbd_session *sess); struct ksmbd_session *ksmbd_session_lookup_slowpath(unsigned long long id); struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, unsigned long long id); -void ksmbd_session_register(struct ksmbd_conn *conn, - struct ksmbd_session *sess); +int ksmbd_session_register(struct ksmbd_conn *conn, + struct ksmbd_session *sess); void ksmbd_sessions_deregister(struct ksmbd_conn *conn); struct ksmbd_session *ksmbd_session_lookup_all(struct ksmbd_conn *conn, unsigned long long id); @@ -100,6 +101,4 @@ void ksmbd_release_tree_conn_id(struct ksmbd_session *sess, int id); int ksmbd_session_rpc_open(struct ksmbd_session *sess, char *rpc_name); void ksmbd_session_rpc_close(struct ksmbd_session *sess, int id); int ksmbd_session_rpc_method(struct ksmbd_session *sess, int id); -int get_session(struct ksmbd_session *sess); -void put_session(struct ksmbd_session *sess); #endif /* __USER_SESSION_MANAGEMENT_H__ */ diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 8b5560574d4c..9046cff4374b 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -30,6 +30,7 @@ static DEFINE_RWLOCK(lease_list_lock); static struct oplock_info *alloc_opinfo(struct ksmbd_work *work, u64 id, __u16 Tid) { + struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess = work->sess; struct oplock_info *opinfo; @@ -38,7 +39,7 @@ static struct oplock_info *alloc_opinfo(struct ksmbd_work *work, return NULL; opinfo->sess = sess; - opinfo->conn = sess->conn; + opinfo->conn = conn; opinfo->level = SMB2_OPLOCK_LEVEL_NONE; opinfo->op_state = OPLOCK_STATE_NONE; opinfo->pending_break = 0; @@ -615,18 +616,13 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) struct ksmbd_file *fp; fp = ksmbd_lookup_durable_fd(br_info->fid); - if (!fp) { - atomic_dec(&conn->r_count); - ksmbd_free_work_struct(work); - return; - } + if (!fp) + goto out; if (allocate_oplock_break_buf(work)) { pr_err("smb2_allocate_rsp_buf failed! "); - atomic_dec(&conn->r_count); ksmbd_fd_put(work, fp); - ksmbd_free_work_struct(work); - return; + goto out; } rsp_hdr = smb2_get_msg(work->response_buf); @@ -667,8 +663,16 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) ksmbd_fd_put(work, fp); ksmbd_conn_write(work); + +out: ksmbd_free_work_struct(work); - atomic_dec(&conn->r_count); + /* + * Checking waitqueue to dropping pending requests on + * disconnection. waitqueue_active is safe because it + * uses atomic operation for condition. + */ + if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) + wake_up(&conn->r_count_q); } /** @@ -731,9 +735,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk) if (allocate_oplock_break_buf(work)) { ksmbd_debug(OPLOCK, "smb2_allocate_rsp_buf failed! "); - ksmbd_free_work_struct(work); - atomic_dec(&conn->r_count); - return; + goto out; } rsp_hdr = smb2_get_msg(work->response_buf); @@ -771,8 +773,16 @@ static void __smb2_lease_break_noti(struct work_struct *wk) inc_rfc1001_len(work->response_buf, 44); ksmbd_conn_write(work); + +out: ksmbd_free_work_struct(work); - atomic_dec(&conn->r_count); + /* + * Checking waitqueue to dropping pending requests on + * disconnection. waitqueue_active is safe because it + * uses atomic operation for condition. + */ + if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) + wake_up(&conn->r_count_q); } /** @@ -972,7 +982,7 @@ int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, } list_for_each_entry(lb, &lease_table_list, l_entry) { - if (!memcmp(lb->client_guid, sess->conn->ClientGUID, + if (!memcmp(lb->client_guid, sess->ClientGUID, SMB2_CLIENT_GUID_SIZE)) goto found; } @@ -988,7 +998,7 @@ found: rcu_read_unlock(); if (opinfo->o_fp->f_ci == ci) goto op_next; - err = compare_guid_key(opinfo, sess->conn->ClientGUID, + err = compare_guid_key(opinfo, sess->ClientGUID, lctx->lease_key); if (err) { err = -EINVAL; @@ -1122,7 +1132,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, struct oplock_info *m_opinfo; /* is lease already granted ? */ - m_opinfo = same_client_has_lease(ci, sess->conn->ClientGUID, + m_opinfo = same_client_has_lease(ci, sess->ClientGUID, lctx); if (m_opinfo) { copy_lease(m_opinfo, opinfo); @@ -1240,7 +1250,7 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, { struct oplock_info *op, *brk_op; struct ksmbd_inode *ci; - struct ksmbd_conn *conn = work->sess->conn; + struct ksmbd_conn *conn = work->conn; if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS)) diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 4cd03d661df0..ce42bff42ef9 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -261,7 +261,13 @@ static void handle_ksmbd_work(struct work_struct *wk) ksmbd_conn_try_dequeue_request(work); ksmbd_free_work_struct(work); - atomic_dec(&conn->r_count); + /* + * Checking waitqueue to dropping pending requests on + * disconnection. waitqueue_active is safe because it + * uses atomic operation for condition. + */ + if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) + wake_up(&conn->r_count_q); } /** diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c index f8f456377a51..6e25ace36568 100644 --- a/fs/ksmbd/smb2misc.c +++ b/fs/ksmbd/smb2misc.c @@ -90,11 +90,6 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, *off = 0; *len = 0; - /* error reqeusts do not have data area */ - if (hdr->Status && hdr->Status != STATUS_MORE_PROCESSING_REQUIRED && - (((struct smb2_err_rsp *)hdr)->StructureSize) == SMB2_ERROR_STRUCTURE_SIZE2_LE) - return ret; - /* * Following commands have data areas so we have to get the location * of the data buffer offset and data buffer length for the particular @@ -136,8 +131,11 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, *len = le16_to_cpu(((struct smb2_read_req *)hdr)->ReadChannelInfoLength); break; case SMB2_WRITE: - if (((struct smb2_write_req *)hdr)->DataOffset) { - *off = le16_to_cpu(((struct smb2_write_req *)hdr)->DataOffset); + if (((struct smb2_write_req *)hdr)->DataOffset || + ((struct smb2_write_req *)hdr)->Length) { + *off = max_t(unsigned int, + le16_to_cpu(((struct smb2_write_req *)hdr)->DataOffset), + offsetof(struct smb2_write_req, Buffer)); *len = le32_to_cpu(((struct smb2_write_req *)hdr)->Length); break; } diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 353f047e783c..19412ac701a6 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -535,9 +535,10 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) struct smb2_query_info_req *req; req = smb2_get_msg(work->request_buf); - if (req->InfoType == SMB2_O_INFO_FILE && - (req->FileInfoClass == FILE_FULL_EA_INFORMATION || - req->FileInfoClass == FILE_ALL_INFORMATION)) + if ((req->InfoType == SMB2_O_INFO_FILE && + (req->FileInfoClass == FILE_FULL_EA_INFORMATION || + req->FileInfoClass == FILE_ALL_INFORMATION)) || + req->InfoType == SMB2_O_INFO_SECURITY) sz = large_sz; } @@ -588,10 +589,12 @@ int smb2_check_user_session(struct ksmbd_work *work) return -EINVAL; } -static void destroy_previous_session(struct ksmbd_user *user, u64 id) +static void destroy_previous_session(struct ksmbd_conn *conn, + struct ksmbd_user *user, u64 id) { struct ksmbd_session *prev_sess = ksmbd_session_lookup_slowpath(id); struct ksmbd_user *prev_user; + struct channel *chann; if (!prev_sess) return; @@ -601,13 +604,14 @@ static void destroy_previous_session(struct ksmbd_user *user, u64 id) if (!prev_user || strcmp(user->name, prev_user->name) || user->passkey_sz != prev_user->passkey_sz || - memcmp(user->passkey, prev_user->passkey, user->passkey_sz)) { - put_session(prev_sess); + memcmp(user->passkey, prev_user->passkey, user->passkey_sz)) return; - } - put_session(prev_sess); - ksmbd_session_destroy(prev_sess); + prev_sess->state = SMB2_SESSION_EXPIRED; + write_lock(&prev_sess->chann_lock); + list_for_each_entry(chann, &prev_sess->ksmbd_chann_list, chann_list) + chann->conn->status = KSMBD_SESS_EXITING; + write_unlock(&prev_sess->chann_lock); } /** @@ -1139,12 +1143,16 @@ int smb2_handle_negotiate(struct ksmbd_work *work) status); rsp->hdr.Status = status; rc = -EINVAL; + kfree(conn->preauth_info); + conn->preauth_info = NULL; goto err_out; } rc = init_smb3_11_server(conn); if (rc < 0) { rsp->hdr.Status = STATUS_INVALID_PARAMETER; + kfree(conn->preauth_info); + conn->preauth_info = NULL; goto err_out; } @@ -1439,7 +1447,7 @@ static int ntlm_authenticate(struct ksmbd_work *work) /* Check for previous session */ prev_id = le64_to_cpu(req->PreviousSessionId); if (prev_id && prev_id != sess->id) - destroy_previous_session(user, prev_id); + destroy_previous_session(conn, user, prev_id); if (sess->state == SMB2_SESSION_VALID) { /* @@ -1493,7 +1501,7 @@ static int ntlm_authenticate(struct ksmbd_work *work) if (smb3_encryption_negotiated(conn) && !(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { - rc = conn->ops->generate_encryptionkey(sess); + rc = conn->ops->generate_encryptionkey(conn, sess); if (rc) { ksmbd_debug(SMB, "SMB3 encryption key generation failed\n"); @@ -1510,7 +1518,9 @@ static int ntlm_authenticate(struct ksmbd_work *work) binding_session: if (conn->dialect >= SMB30_PROT_ID) { + read_lock(&sess->chann_lock); chann = lookup_chann_list(sess, conn); + read_unlock(&sess->chann_lock); if (!chann) { chann = kmalloc(sizeof(struct channel), GFP_KERNEL); if (!chann) @@ -1518,7 +1528,9 @@ binding_session: chann->conn = conn; INIT_LIST_HEAD(&chann->chann_list); + write_lock(&sess->chann_lock); list_add(&chann->chann_list, &sess->ksmbd_chann_list); + write_unlock(&sess->chann_lock); } } @@ -1561,7 +1573,7 @@ static int krb5_authenticate(struct ksmbd_work *work) /* Check previous session */ prev_sess_id = le64_to_cpu(req->PreviousSessionId); if (prev_sess_id && prev_sess_id != sess->id) - destroy_previous_session(sess->user, prev_sess_id); + destroy_previous_session(conn, sess->user, prev_sess_id); if (sess->state == SMB2_SESSION_VALID) ksmbd_free_user(sess->user); @@ -1580,7 +1592,7 @@ static int krb5_authenticate(struct ksmbd_work *work) sess->sign = true; if (smb3_encryption_negotiated(conn)) { - retval = conn->ops->generate_encryptionkey(sess); + retval = conn->ops->generate_encryptionkey(conn, sess); if (retval) { ksmbd_debug(SMB, "SMB3 encryption key generation failed\n"); @@ -1592,7 +1604,9 @@ static int krb5_authenticate(struct ksmbd_work *work) } if (conn->dialect >= SMB30_PROT_ID) { + read_lock(&sess->chann_lock); chann = lookup_chann_list(sess, conn); + read_unlock(&sess->chann_lock); if (!chann) { chann = kmalloc(sizeof(struct channel), GFP_KERNEL); if (!chann) @@ -1600,7 +1614,9 @@ static int krb5_authenticate(struct ksmbd_work *work) chann->conn = conn; INIT_LIST_HEAD(&chann->chann_list); + write_lock(&sess->chann_lock); list_add(&chann->chann_list, &sess->ksmbd_chann_list); + write_unlock(&sess->chann_lock); } } @@ -1650,7 +1666,9 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } rsp->hdr.SessionId = cpu_to_le64(sess->id); - ksmbd_session_register(conn, sess); + rc = ksmbd_session_register(conn, sess); + if (rc) + goto out_err; } else if (conn->dialect >= SMB30_PROT_ID && (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) && req->Flags & SMB2_SESSION_REQ_FLAG_BINDING) { @@ -1662,7 +1680,7 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } - if (conn->dialect != sess->conn->dialect) { + if (conn->dialect != sess->dialect) { rc = -EINVAL; goto out_err; } @@ -1672,7 +1690,7 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } - if (strncmp(conn->ClientGUID, sess->conn->ClientGUID, + if (strncmp(conn->ClientGUID, sess->ClientGUID, SMB2_CLIENT_GUID_SIZE)) { rc = -ENOENT; goto out_err; @@ -1828,6 +1846,7 @@ out_err: if (sess->user && sess->user->flags & KSMBD_USER_FLAG_DELAY_SESSION) try_delay = true; + xa_erase(&conn->sessions, sess->id); ksmbd_session_destroy(sess); work->sess = NULL; if (try_delay) @@ -1873,7 +1892,7 @@ int smb2_tree_connect(struct ksmbd_work *work) ksmbd_debug(SMB, "tree connect request for tree %s treename %s\n", name, treename); - status = ksmbd_tree_conn_connect(sess, name); + status = ksmbd_tree_conn_connect(conn, sess, name); if (status.ret == KSMBD_TREE_CONN_STATUS_OK) rsp->hdr.Id.SyncId.TreeId = cpu_to_le32(status.tree_conn->id); else @@ -1925,8 +1944,10 @@ out_err1: rsp->hdr.Status = STATUS_SUCCESS; rc = 0; break; + case -ESTALE: + case -ENOENT: case KSMBD_TREE_CONN_STATUS_NO_SHARE: - rsp->hdr.Status = STATUS_BAD_NETWORK_PATH; + rsp->hdr.Status = STATUS_BAD_NETWORK_NAME; break; case -ENOMEM: case KSMBD_TREE_CONN_STATUS_NOMEM: @@ -2039,6 +2060,7 @@ int smb2_tree_disconnect(struct ksmbd_work *work) ksmbd_close_tree_conn_fds(work); ksmbd_tree_conn_disconnect(sess, tcon); + work->tcon = NULL; return 0; } @@ -2308,15 +2330,15 @@ static int smb2_remove_smb_xattrs(struct path *path) name += strlen(name) + 1) { ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name)); - if (strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && - strncmp(&name[XATTR_USER_PREFIX_LEN], DOS_ATTRIBUTE_PREFIX, - DOS_ATTRIBUTE_PREFIX_LEN) && - strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, STREAM_PREFIX_LEN)) - continue; - - err = ksmbd_vfs_remove_xattr(user_ns, path->dentry, name); - if (err) - ksmbd_debug(SMB, "remove xattr failed : %s\n", name); + if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && + !strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, + STREAM_PREFIX_LEN)) { + err = ksmbd_vfs_remove_xattr(user_ns, path->dentry, + name); + if (err) + ksmbd_debug(SMB, "remove xattr failed : %s\n", + name); + } } out: kvfree(xattr_list); @@ -2969,7 +2991,7 @@ int smb2_open(struct ksmbd_work *work) goto err_out; rc = build_sec_desc(user_ns, - pntsd, NULL, + pntsd, NULL, 0, OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO, @@ -3022,12 +3044,6 @@ int smb2_open(struct ksmbd_work *work) list_add(&fp->node, &fp->f_ci->m_fp_list); write_unlock(&fp->f_ci->m_lock); - rc = ksmbd_vfs_getattr(&path, &stat); - if (rc) { - generic_fillattr(user_ns, d_inode(path.dentry), &stat); - rc = 0; - } - /* Check delete pending among previous fp before oplock break */ if (ksmbd_inode_pending_delete(fp)) { rc = -EBUSY; @@ -3114,6 +3130,10 @@ int smb2_open(struct ksmbd_work *work) } } + rc = ksmbd_vfs_getattr(&path, &stat); + if (rc) + goto err_out; + if (stat.result_mask & STATX_BTIME) fp->create_time = ksmbd_UnixTimeToNT(stat.btime); else @@ -3129,9 +3149,6 @@ int smb2_open(struct ksmbd_work *work) memcpy(fp->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE); - generic_fillattr(user_ns, file_inode(fp->filp), - &stat); - rsp->StructureSize = cpu_to_le16(89); rcu_read_lock(); opinfo = rcu_dereference(fp->f_opinfo); @@ -3814,6 +3831,15 @@ static int verify_info_level(int info_level) return 0; } +static int smb2_resp_buf_len(struct ksmbd_work *work, unsigned short hdr2_len) +{ + int free_len; + + free_len = (int)(work->response_sz - + (get_rfc1002_len(work->response_buf) + 4)) - hdr2_len; + return free_len; +} + static int smb2_calc_max_out_buf_len(struct ksmbd_work *work, unsigned short hdr2_len, unsigned int out_buf_len) @@ -3823,9 +3849,7 @@ static int smb2_calc_max_out_buf_len(struct ksmbd_work *work, if (out_buf_len > work->conn->vals->max_trans_size) return -EINVAL; - free_len = (int)(work->response_sz - - (get_rfc1002_len(work->response_buf) + 4)) - - hdr2_len; + free_len = smb2_resp_buf_len(work, hdr2_len); if (free_len < 0) return -EINVAL; @@ -4858,7 +4882,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, struct smb2_query_info_rsp *rsp) { struct ksmbd_session *sess = work->sess; - struct ksmbd_conn *conn = sess->conn; + struct ksmbd_conn *conn = work->conn; struct ksmbd_share_config *share = work->tcon->share_conf; int fsinfoclass = 0; struct kstatfs stfs; @@ -5088,10 +5112,10 @@ static int smb2_get_info_sec(struct ksmbd_work *work, struct smb_ntsd *pntsd = (struct smb_ntsd *)rsp->Buffer, *ppntsd = NULL; struct smb_fattr fattr = {{0}}; struct inode *inode; - __u32 secdesclen; + __u32 secdesclen = 0; unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; int addition_info = le32_to_cpu(req->AdditionalInformation); - int rc; + int rc = 0, ppntsd_size = 0; if (addition_info & ~(OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO | PROTECTED_DACL_SECINFO | @@ -5137,11 +5161,14 @@ static int smb2_get_info_sec(struct ksmbd_work *work, if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) - ksmbd_vfs_get_sd_xattr(work->conn, user_ns, - fp->filp->f_path.dentry, &ppntsd); - - rc = build_sec_desc(user_ns, pntsd, ppntsd, addition_info, - &secdesclen, &fattr); + ppntsd_size = ksmbd_vfs_get_sd_xattr(work->conn, user_ns, + fp->filp->f_path.dentry, + &ppntsd); + + /* Check if sd buffer size exceeds response buffer size */ + if (smb2_resp_buf_len(work, 8) > ppntsd_size) + rc = build_sec_desc(user_ns, pntsd, ppntsd, ppntsd_size, + addition_info, &secdesclen, &fattr); posix_acl_release(fattr.cf_acls); posix_acl_release(fattr.cf_dacls); kfree(ppntsd); @@ -5776,7 +5803,7 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, } next: return smb2_rename(work, fp, user_ns, rename_info, - work->sess->conn->local_nls); + work->conn->local_nls); } static int set_file_disposition_info(struct ksmbd_file *fp, @@ -5908,7 +5935,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return smb2_create_link(work, work->tcon->share_conf, (struct smb2_file_link_info *)req->Buffer, buf_len, fp->filp, - work->sess->conn->local_nls); + work->conn->local_nls); } case FILE_DISPOSITION_INFORMATION: { @@ -6495,14 +6522,12 @@ int smb2_write(struct ksmbd_work *work) writethrough = true; if (is_rdma_channel == false) { - if ((u64)le16_to_cpu(req->DataOffset) + length > - get_rfc1002_len(work->request_buf)) { - pr_err("invalid write data offset %u, smb_len %u\n", - le16_to_cpu(req->DataOffset), - get_rfc1002_len(work->request_buf)); + if (le16_to_cpu(req->DataOffset) < + offsetof(struct smb2_write_req, Buffer)) { err = -EINVAL; goto out; } + data_buf = (char *)(((char *)&req->hdr.ProtocolId) + le16_to_cpu(req->DataOffset)); @@ -8356,10 +8381,14 @@ int smb3_check_sign_req(struct ksmbd_work *work) if (le16_to_cpu(hdr->Command) == SMB2_SESSION_SETUP_HE) { signing_key = work->sess->smb3signingkey; } else { + read_lock(&work->sess->chann_lock); chann = lookup_chann_list(work->sess, conn); - if (!chann) + if (!chann) { + read_unlock(&work->sess->chann_lock); return 0; + } signing_key = chann->smb3signingkey; + read_unlock(&work->sess->chann_lock); } if (!signing_key) { @@ -8419,10 +8448,14 @@ void smb3_set_sign_rsp(struct ksmbd_work *work) le16_to_cpu(hdr->Command) == SMB2_SESSION_SETUP_HE) { signing_key = work->sess->smb3signingkey; } else { + read_lock(&work->sess->chann_lock); chann = lookup_chann_list(work->sess, work->conn); - if (!chann) + if (!chann) { + read_unlock(&work->sess->chann_lock); return; + } signing_key = chann->smb3signingkey; + read_unlock(&work->sess->chann_lock); } if (!signing_key) diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h index e1369b4345a9..318c16fa81da 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/ksmbd/smb_common.h @@ -421,7 +421,7 @@ struct smb_version_ops { int (*check_sign_req)(struct ksmbd_work *work); void (*set_sign_rsp)(struct ksmbd_work *work); int (*generate_signingkey)(struct ksmbd_session *sess, struct ksmbd_conn *conn); - int (*generate_encryptionkey)(struct ksmbd_session *sess); + int (*generate_encryptionkey)(struct ksmbd_conn *conn, struct ksmbd_session *sess); bool (*is_transform_hdr)(void *buf); int (*decrypt_req)(struct ksmbd_work *work); int (*encrypt_resp)(struct ksmbd_work *work); diff --git a/fs/ksmbd/smbacl.c b/fs/ksmbd/smbacl.c index 38f23bf981ac..3781bca2c8fc 100644 --- a/fs/ksmbd/smbacl.c +++ b/fs/ksmbd/smbacl.c @@ -690,6 +690,7 @@ posix_default_acl: static void set_ntacl_dacl(struct user_namespace *user_ns, struct smb_acl *pndacl, struct smb_acl *nt_dacl, + unsigned int aces_size, const struct smb_sid *pownersid, const struct smb_sid *pgrpsid, struct smb_fattr *fattr) @@ -703,9 +704,19 @@ static void set_ntacl_dacl(struct user_namespace *user_ns, if (nt_num_aces) { ntace = (struct smb_ace *)((char *)nt_dacl + sizeof(struct smb_acl)); for (i = 0; i < nt_num_aces; i++) { - memcpy((char *)pndace + size, ntace, le16_to_cpu(ntace->size)); - size += le16_to_cpu(ntace->size); - ntace = (struct smb_ace *)((char *)ntace + le16_to_cpu(ntace->size)); + unsigned short nt_ace_size; + + if (offsetof(struct smb_ace, access_req) > aces_size) + break; + + nt_ace_size = le16_to_cpu(ntace->size); + if (nt_ace_size > aces_size) + break; + + memcpy((char *)pndace + size, ntace, nt_ace_size); + size += nt_ace_size; + aces_size -= nt_ace_size; + ntace = (struct smb_ace *)((char *)ntace + nt_ace_size); num_aces++; } } @@ -878,7 +889,7 @@ int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, /* Convert permission bits from mode to equivalent CIFS ACL */ int build_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, struct smb_ntsd *ppntsd, - int addition_info, __u32 *secdesclen, + int ppntsd_size, int addition_info, __u32 *secdesclen, struct smb_fattr *fattr) { int rc = 0; @@ -938,15 +949,25 @@ int build_sec_desc(struct user_namespace *user_ns, if (!ppntsd) { set_mode_dacl(user_ns, dacl_ptr, fattr); - } else if (!ppntsd->dacloffset) { - goto out; } else { struct smb_acl *ppdacl_ptr; + unsigned int dacl_offset = le32_to_cpu(ppntsd->dacloffset); + int ppdacl_size, ntacl_size = ppntsd_size - dacl_offset; + + if (!dacl_offset || + (dacl_offset + sizeof(struct smb_acl) > ppntsd_size)) + goto out; + + ppdacl_ptr = (struct smb_acl *)((char *)ppntsd + dacl_offset); + ppdacl_size = le16_to_cpu(ppdacl_ptr->size); + if (ppdacl_size > ntacl_size || + ppdacl_size < sizeof(struct smb_acl)) + goto out; - ppdacl_ptr = (struct smb_acl *)((char *)ppntsd + - le32_to_cpu(ppntsd->dacloffset)); set_ntacl_dacl(user_ns, dacl_ptr, ppdacl_ptr, - nowner_sid_ptr, ngroup_sid_ptr, fattr); + ntacl_size - sizeof(struct smb_acl), + nowner_sid_ptr, ngroup_sid_ptr, + fattr); } pntsd->dacloffset = cpu_to_le32(offset); offset += le16_to_cpu(dacl_ptr->size); @@ -980,24 +1001,31 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, struct smb_sid owner_sid, group_sid; struct dentry *parent = path->dentry->d_parent; struct user_namespace *user_ns = mnt_user_ns(path->mnt); - int inherited_flags = 0, flags = 0, i, ace_cnt = 0, nt_size = 0; - int rc = 0, num_aces, dacloffset, pntsd_type, acl_len; + int inherited_flags = 0, flags = 0, i, ace_cnt = 0, nt_size = 0, pdacl_size; + int rc = 0, num_aces, dacloffset, pntsd_type, pntsd_size, acl_len, aces_size; char *aces_base; bool is_dir = S_ISDIR(d_inode(path->dentry)->i_mode); - acl_len = ksmbd_vfs_get_sd_xattr(conn, user_ns, - parent, &parent_pntsd); - if (acl_len <= 0) + pntsd_size = ksmbd_vfs_get_sd_xattr(conn, user_ns, + parent, &parent_pntsd); + if (pntsd_size <= 0) return -ENOENT; dacloffset = le32_to_cpu(parent_pntsd->dacloffset); - if (!dacloffset) { + if (!dacloffset || (dacloffset + sizeof(struct smb_acl) > pntsd_size)) { rc = -EINVAL; goto free_parent_pntsd; } parent_pdacl = (struct smb_acl *)((char *)parent_pntsd + dacloffset); + acl_len = pntsd_size - dacloffset; num_aces = le32_to_cpu(parent_pdacl->num_aces); pntsd_type = le16_to_cpu(parent_pntsd->type); + pdacl_size = le16_to_cpu(parent_pdacl->size); + + if (pdacl_size > acl_len || pdacl_size < sizeof(struct smb_acl)) { + rc = -EINVAL; + goto free_parent_pntsd; + } aces_base = kmalloc(sizeof(struct smb_ace) * num_aces * 2, GFP_KERNEL); if (!aces_base) { @@ -1008,11 +1036,23 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, aces = (struct smb_ace *)aces_base; parent_aces = (struct smb_ace *)((char *)parent_pdacl + sizeof(struct smb_acl)); + aces_size = acl_len - sizeof(struct smb_acl); if (pntsd_type & DACL_AUTO_INHERITED) inherited_flags = INHERITED_ACE; for (i = 0; i < num_aces; i++) { + int pace_size; + + if (offsetof(struct smb_ace, access_req) > aces_size) + break; + + pace_size = le16_to_cpu(parent_aces->size); + if (pace_size > aces_size) + break; + + aces_size -= pace_size; + flags = parent_aces->flags; if (!smb_inherit_flags(flags, is_dir)) goto pass; @@ -1057,8 +1097,7 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, aces = (struct smb_ace *)((char *)aces + le16_to_cpu(aces->size)); ace_cnt++; pass: - parent_aces = - (struct smb_ace *)((char *)parent_aces + le16_to_cpu(parent_aces->size)); + parent_aces = (struct smb_ace *)((char *)parent_aces + pace_size); } if (nt_size > 0) { @@ -1153,7 +1192,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, struct path *path, struct smb_ntsd *pntsd = NULL; struct smb_acl *pdacl; struct posix_acl *posix_acls; - int rc = 0, acl_size; + int rc = 0, pntsd_size, acl_size, aces_size, pdacl_size, dacl_offset; struct smb_sid sid; int granted = le32_to_cpu(*pdaccess & ~FILE_MAXIMAL_ACCESS_LE); struct smb_ace *ace; @@ -1162,37 +1201,33 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, struct path *path, struct smb_ace *others_ace = NULL; struct posix_acl_entry *pa_entry; unsigned int sid_type = SIDOWNER; - char *end_of_acl; + unsigned short ace_size; ksmbd_debug(SMB, "check permission using windows acl\n"); - acl_size = ksmbd_vfs_get_sd_xattr(conn, user_ns, - path->dentry, &pntsd); - if (acl_size <= 0 || !pntsd || !pntsd->dacloffset) { - kfree(pntsd); - return 0; - } + pntsd_size = ksmbd_vfs_get_sd_xattr(conn, user_ns, + path->dentry, &pntsd); + if (pntsd_size <= 0 || !pntsd) + goto err_out; + + dacl_offset = le32_to_cpu(pntsd->dacloffset); + if (!dacl_offset || + (dacl_offset + sizeof(struct smb_acl) > pntsd_size)) + goto err_out; pdacl = (struct smb_acl *)((char *)pntsd + le32_to_cpu(pntsd->dacloffset)); - end_of_acl = ((char *)pntsd) + acl_size; - if (end_of_acl <= (char *)pdacl) { - kfree(pntsd); - return 0; - } + acl_size = pntsd_size - dacl_offset; + pdacl_size = le16_to_cpu(pdacl->size); - if (end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size) || - le16_to_cpu(pdacl->size) < sizeof(struct smb_acl)) { - kfree(pntsd); - return 0; - } + if (pdacl_size > acl_size || pdacl_size < sizeof(struct smb_acl)) + goto err_out; if (!pdacl->num_aces) { - if (!(le16_to_cpu(pdacl->size) - sizeof(struct smb_acl)) && + if (!(pdacl_size - sizeof(struct smb_acl)) && *pdaccess & ~(FILE_READ_CONTROL_LE | FILE_WRITE_DAC_LE)) { rc = -EACCES; goto err_out; } - kfree(pntsd); - return 0; + goto err_out; } if (*pdaccess & FILE_MAXIMAL_ACCESS_LE) { @@ -1200,11 +1235,16 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, struct path *path, DELETE; ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl)); + aces_size = acl_size - sizeof(struct smb_acl); for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) { + if (offsetof(struct smb_ace, access_req) > aces_size) + break; + ace_size = le16_to_cpu(ace->size); + if (ace_size > aces_size) + break; + aces_size -= ace_size; granted |= le32_to_cpu(ace->access_req); ace = (struct smb_ace *)((char *)ace + le16_to_cpu(ace->size)); - if (end_of_acl < (char *)ace) - goto err_out; } if (!pdacl->num_aces) @@ -1216,7 +1256,15 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, struct path *path, id_to_sid(uid, sid_type, &sid); ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl)); + aces_size = acl_size - sizeof(struct smb_acl); for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) { + if (offsetof(struct smb_ace, access_req) > aces_size) + break; + ace_size = le16_to_cpu(ace->size); + if (ace_size > aces_size) + break; + aces_size -= ace_size; + if (!compare_sids(&sid, &ace->sid) || !compare_sids(&sid_unix_NFS_mode, &ace->sid)) { found = 1; @@ -1226,8 +1274,6 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, struct path *path, others_ace = ace; ace = (struct smb_ace *)((char *)ace + le16_to_cpu(ace->size)); - if (end_of_acl < (char *)ace) - goto err_out; } if (*pdaccess & FILE_MAXIMAL_ACCESS_LE && found) { diff --git a/fs/ksmbd/smbacl.h b/fs/ksmbd/smbacl.h index 811af3309429..fcb2c83f2992 100644 --- a/fs/ksmbd/smbacl.h +++ b/fs/ksmbd/smbacl.h @@ -193,7 +193,7 @@ struct posix_acl_state { int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, int acl_len, struct smb_fattr *fattr); int build_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, - struct smb_ntsd *ppntsd, int addition_info, + struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info, __u32 *secdesclen, struct smb_fattr *fattr); int init_acl_state(struct posix_acl_state *state, int cnt); void free_acl_state(struct posix_acl_state *state); diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 7c849024999f..78d01033604c 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -481,12 +481,11 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp, char *buf, size_t count, loff_t *pos, bool sync, ssize_t *written) { - struct ksmbd_session *sess = work->sess; struct file *filp; loff_t offset = *pos; int err = 0; - if (sess->conn->connection_type) { + if (work->conn->connection_type) { if (!(fp->daccess & FILE_WRITE_DATA_LE)) { pr_err("no right to write(%pd)\n", fp->filp->f_path.dentry); @@ -1540,6 +1539,11 @@ int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn, } *pntsd = acl.sd_buf; + if (acl.sd_size < sizeof(struct smb_ntsd)) { + pr_err("sd size is invalid\n"); + goto out_free; + } + (*pntsd)->osidoffset = cpu_to_le32(le32_to_cpu((*pntsd)->osidoffset) - NDR_NTSD_OFFSETOF); (*pntsd)->gsidoffset = cpu_to_le32(le32_to_cpu((*pntsd)->gsidoffset) - diff --git a/fs/ksmbd/vfs_cache.c b/fs/ksmbd/vfs_cache.c index c4d59d2735f0..da9163b00350 100644 --- a/fs/ksmbd/vfs_cache.c +++ b/fs/ksmbd/vfs_cache.c @@ -569,7 +569,7 @@ struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp) atomic_set(&fp->refcount, 1); fp->filp = filp; - fp->conn = work->sess->conn; + fp->conn = work->conn; fp->tcon = work->tcon; fp->volatile_id = KSMBD_NO_FID; fp->persistent_id = KSMBD_NO_FID; diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 176b468a61c7..bf274f23969b 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -32,6 +32,10 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, if (!nlmsvc_ops) return nlm_lck_denied_nolocks; + if (lock->lock_start > OFFSET_MAX || + (lock->lock_len && ((lock->lock_len - 1) > (OFFSET_MAX - lock->lock_start)))) + return nlm4_fbig; + /* Obtain host handle */ if (!(host = nlmsvc_lookup_host(rqstp, lock->caller, lock->len)) || (argp->monitor && nsm_monitor(host) < 0)) @@ -50,6 +54,10 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, /* Set up the missing parts of the file_lock structure */ lock->fl.fl_file = file->f_file[mode]; lock->fl.fl_pid = current->tgid; + lock->fl.fl_start = (loff_t)lock->lock_start; + lock->fl.fl_end = lock->lock_len ? + (loff_t)(lock->lock_start + lock->lock_len - 1) : + OFFSET_MAX; lock->fl.fl_lmops = &nlmsvc_lock_operations; nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid); if (!lock->fl.fl_owner) { @@ -87,6 +95,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; + struct nlm_lockowner *test_owner; __be32 rc = rpc_success; dprintk("lockd: TEST4 called\n"); @@ -96,6 +105,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file))) return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; + test_owner = argp->lock.fl.fl_owner; /* Now check for conflicting locks */ resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie); if (resp->status == nlm_drop_reply) @@ -103,7 +113,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) else dprintk("lockd: TEST4 status %d\n", ntohl(resp->status)); - nlmsvc_release_lockowner(&argp->lock); + nlmsvc_put_lockowner(test_owner); nlmsvc_release_host(host); nlm_release_file(file); return rc; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index cb3658ab9b7a..9c1aa75441e1 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -340,7 +340,7 @@ nlmsvc_get_lockowner(struct nlm_lockowner *lockowner) return lockowner; } -static void nlmsvc_put_lockowner(struct nlm_lockowner *lockowner) +void nlmsvc_put_lockowner(struct nlm_lockowner *lockowner) { if (!refcount_dec_and_lock(&lockowner->count, &lockowner->host->h_lock)) return; @@ -590,7 +590,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, int error; int mode; __be32 ret; - struct nlm_lockowner *test_owner; dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n", nlmsvc_file_inode(file)->i_sb->s_id, @@ -604,9 +603,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, goto out; } - /* If there's a conflicting lock, remember to clean up the test lock */ - test_owner = (struct nlm_lockowner *)lock->fl.fl_owner; - mode = lock_to_openmode(&lock->fl); error = vfs_test_lock(file->f_file[mode], &lock->fl); if (error) { @@ -635,10 +631,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, conflock->fl.fl_end = lock->fl.fl_end; locks_release_private(&lock->fl); - /* Clean up the test lock */ - lock->fl.fl_owner = NULL; - nlmsvc_put_lockowner(test_owner); - ret = nlm_lck_denied; out: return ret; diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 4dc1b40a489a..b09ca35b527c 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -116,6 +116,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; + struct nlm_lockowner *test_owner; __be32 rc = rpc_success; dprintk("lockd: TEST called\n"); @@ -125,6 +126,8 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file))) return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; + test_owner = argp->lock.fl.fl_owner; + /* Now check for conflicting locks */ resp->status = cast_status(nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie)); if (resp->status == nlm_drop_reply) @@ -133,7 +136,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) dprintk("lockd: TEST status %d vers %d\n", ntohl(resp->status), rqstp->rq_vers); - nlmsvc_release_lockowner(&argp->lock); + nlmsvc_put_lockowner(test_owner); nlmsvc_release_host(host); nlm_release_file(file); return rc; diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 856267c0864b..712fdfeb8ef0 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -20,13 +20,6 @@ #include "svcxdr.h" -static inline loff_t -s64_to_loff_t(__s64 offset) -{ - return (loff_t)offset; -} - - static inline s64 loff_t_to_s64(loff_t offset) { @@ -70,8 +63,6 @@ static bool svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock) { struct file_lock *fl = &lock->fl; - u64 len, start; - s64 end; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) return false; @@ -81,20 +72,14 @@ svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock) return false; if (xdr_stream_decode_u32(xdr, &lock->svid) < 0) return false; - if (xdr_stream_decode_u64(xdr, &start) < 0) + if (xdr_stream_decode_u64(xdr, &lock->lock_start) < 0) return false; - if (xdr_stream_decode_u64(xdr, &len) < 0) + if (xdr_stream_decode_u64(xdr, &lock->lock_len) < 0) return false; locks_init_lock(fl); fl->fl_flags = FL_POSIX; fl->fl_type = F_RDLCK; - end = start + len - 1; - fl->fl_start = s64_to_loff_t(start); - if (len == 0 || end < 0) - fl->fl_end = OFFSET_MAX; - else - fl->fl_end = s64_to_loff_t(end); return true; } diff --git a/fs/locks.c b/fs/locks.c index c266cfdc3291..607f94a0e789 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2129,6 +2129,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) else error = locks_lock_file_wait(f.file, &fl); + locks_release_private(&fl); out_putf: fdput(f); diff --git a/fs/mbcache.c b/fs/mbcache.c index 97c54d3a2227..47ccfcbe0a22 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -11,7 +11,7 @@ /* * Mbcache is a simple key-value store. Keys need not be unique, however * key-value pairs are expected to be unique (we use this fact in - * mb_cache_entry_delete()). + * mb_cache_entry_delete_or_get()). * * Ext2 and ext4 use this cache for deduplication of extended attribute blocks. * Ext4 also uses it for deduplication of xattr values stored in inodes. @@ -90,7 +90,7 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, return -ENOMEM; INIT_LIST_HEAD(&entry->e_list); - /* One ref for hash, one ref returned */ + /* Initial hash reference */ atomic_set(&entry->e_refcnt, 1); entry->e_key = key; entry->e_value = value; @@ -106,25 +106,45 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, } } hlist_bl_add_head(&entry->e_hash_list, head); - hlist_bl_unlock(head); - + /* + * Add entry to LRU list before it can be found by + * mb_cache_entry_delete() to avoid races + */ spin_lock(&cache->c_list_lock); list_add_tail(&entry->e_list, &cache->c_list); - /* Grab ref for LRU list */ - atomic_inc(&entry->e_refcnt); cache->c_entry_count++; spin_unlock(&cache->c_list_lock); + hlist_bl_unlock(head); return 0; } EXPORT_SYMBOL(mb_cache_entry_create); -void __mb_cache_entry_free(struct mb_cache_entry *entry) +void __mb_cache_entry_free(struct mb_cache *cache, struct mb_cache_entry *entry) { + struct hlist_bl_head *head; + + head = mb_cache_entry_head(cache, entry->e_key); + hlist_bl_lock(head); + hlist_bl_del(&entry->e_hash_list); + hlist_bl_unlock(head); kmem_cache_free(mb_entry_cache, entry); } EXPORT_SYMBOL(__mb_cache_entry_free); +/* + * mb_cache_entry_wait_unused - wait to be the last user of the entry + * + * @entry - entry to work on + * + * Wait to be the last user of the entry. + */ +void mb_cache_entry_wait_unused(struct mb_cache_entry *entry) +{ + wait_var_event(&entry->e_refcnt, atomic_read(&entry->e_refcnt) <= 2); +} +EXPORT_SYMBOL(mb_cache_entry_wait_unused); + static struct mb_cache_entry *__entry_find(struct mb_cache *cache, struct mb_cache_entry *entry, u32 key) @@ -142,10 +162,9 @@ static struct mb_cache_entry *__entry_find(struct mb_cache *cache, while (node) { entry = hlist_bl_entry(node, struct mb_cache_entry, e_hash_list); - if (entry->e_key == key && entry->e_reusable) { - atomic_inc(&entry->e_refcnt); + if (entry->e_key == key && entry->e_reusable && + atomic_inc_not_zero(&entry->e_refcnt)) goto out; - } node = node->next; } entry = NULL; @@ -205,10 +224,9 @@ struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(entry, node, head, e_hash_list) { - if (entry->e_key == key && entry->e_value == value) { - atomic_inc(&entry->e_refcnt); + if (entry->e_key == key && entry->e_value == value && + atomic_inc_not_zero(&entry->e_refcnt)) goto out; - } } entry = NULL; out: @@ -217,42 +235,42 @@ out: } EXPORT_SYMBOL(mb_cache_entry_get); -/* mb_cache_entry_delete - remove a cache entry +/* mb_cache_entry_delete_or_get - remove a cache entry if it has no users * @cache - cache we work with * @key - key * @value - value * - * Remove entry from cache @cache with key @key and value @value. + * Remove entry from cache @cache with key @key and value @value. The removal + * happens only if the entry is unused. The function returns NULL in case the + * entry was successfully removed or there's no entry in cache. Otherwise the + * function grabs reference of the entry that we failed to delete because it + * still has users and return it. */ -void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value) +struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache, + u32 key, u64 value) { - struct hlist_bl_node *node; - struct hlist_bl_head *head; struct mb_cache_entry *entry; - head = mb_cache_entry_head(cache, key); - hlist_bl_lock(head); - hlist_bl_for_each_entry(entry, node, head, e_hash_list) { - if (entry->e_key == key && entry->e_value == value) { - /* We keep hash list reference to keep entry alive */ - hlist_bl_del_init(&entry->e_hash_list); - hlist_bl_unlock(head); - spin_lock(&cache->c_list_lock); - if (!list_empty(&entry->e_list)) { - list_del_init(&entry->e_list); - if (!WARN_ONCE(cache->c_entry_count == 0, - "mbcache: attempt to decrement c_entry_count past zero")) - cache->c_entry_count--; - atomic_dec(&entry->e_refcnt); - } - spin_unlock(&cache->c_list_lock); - mb_cache_entry_put(cache, entry); - return; - } - } - hlist_bl_unlock(head); + entry = mb_cache_entry_get(cache, key, value); + if (!entry) + return NULL; + + /* + * Drop the ref we got from mb_cache_entry_get() and the initial hash + * ref if we are the last user + */ + if (atomic_cmpxchg(&entry->e_refcnt, 2, 0) != 2) + return entry; + + spin_lock(&cache->c_list_lock); + if (!list_empty(&entry->e_list)) + list_del_init(&entry->e_list); + cache->c_entry_count--; + spin_unlock(&cache->c_list_lock); + __mb_cache_entry_free(cache, entry); + return NULL; } -EXPORT_SYMBOL(mb_cache_entry_delete); +EXPORT_SYMBOL(mb_cache_entry_delete_or_get); /* mb_cache_entry_touch - cache entry got used * @cache - cache the entry belongs to @@ -281,34 +299,24 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache, unsigned long nr_to_scan) { struct mb_cache_entry *entry; - struct hlist_bl_head *head; unsigned long shrunk = 0; spin_lock(&cache->c_list_lock); while (nr_to_scan-- && !list_empty(&cache->c_list)) { entry = list_first_entry(&cache->c_list, struct mb_cache_entry, e_list); - if (entry->e_referenced) { + /* Drop initial hash reference if there is no user */ + if (entry->e_referenced || + atomic_cmpxchg(&entry->e_refcnt, 1, 0) != 1) { entry->e_referenced = 0; list_move_tail(&entry->e_list, &cache->c_list); continue; } list_del_init(&entry->e_list); cache->c_entry_count--; - /* - * We keep LRU list reference so that entry doesn't go away - * from under us. - */ spin_unlock(&cache->c_list_lock); - head = mb_cache_entry_head(cache, entry->e_key); - hlist_bl_lock(head); - if (!hlist_bl_unhashed(&entry->e_hash_list)) { - hlist_bl_del_init(&entry->e_hash_list); - atomic_dec(&entry->e_refcnt); - } - hlist_bl_unlock(head); - if (mb_cache_entry_put(cache, entry)) - shrunk++; + __mb_cache_entry_free(cache, entry); + shrunk++; cond_resched(); spin_lock(&cache->c_list_lock); } @@ -367,7 +375,7 @@ struct mb_cache *mb_cache_create(int bucket_bits) cache->c_shrink.count_objects = mb_cache_count; cache->c_shrink.scan_objects = mb_cache_scan; cache->c_shrink.seeks = DEFAULT_SEEKS; - if (register_shrinker(&cache->c_shrink)) { + if (register_shrinker(&cache->c_shrink, "mbcache-shrinker")) { kfree(cache->c_hash); kfree(cache); goto err_out; @@ -400,11 +408,6 @@ void mb_cache_destroy(struct mb_cache *cache) * point. */ list_for_each_entry_safe(entry, next, &cache->c_list, e_list) { - if (!hlist_bl_unhashed(&entry->e_hash_list)) { - hlist_bl_del_init(&entry->e_hash_list); - atomic_dec(&entry->e_refcnt); - } else - WARN_ON(1); list_del(&entry->e_list); WARN_ON(atomic_read(&entry->e_refcnt) != 1); mb_cache_entry_put(cache, entry); diff --git a/fs/namei.c b/fs/namei.c index ed3ffd9b22a3..53b4bc094db2 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3024,6 +3024,65 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) EXPORT_SYMBOL(unlock_rename); /** + * mode_strip_umask - handle vfs umask stripping + * @dir: parent directory of the new inode + * @mode: mode of the new inode to be created in @dir + * + * Umask stripping depends on whether or not the filesystem supports POSIX + * ACLs. If the filesystem doesn't support it umask stripping is done directly + * in here. If the filesystem does support POSIX ACLs umask stripping is + * deferred until the filesystem calls posix_acl_create(). + * + * Returns: mode + */ +static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) +{ + if (!IS_POSIXACL(dir)) + mode &= ~current_umask(); + return mode; +} + +/** + * vfs_prepare_mode - prepare the mode to be used for a new inode + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: parent directory of the new inode + * @mode: mode of the new inode + * @mask_perms: allowed permission by the vfs + * @type: type of file to be created + * + * This helper consolidates and enforces vfs restrictions on the @mode of a new + * object to be created. + * + * Umask stripping depends on whether the filesystem supports POSIX ACLs (see + * the kernel documentation for mode_strip_umask()). Moving umask stripping + * after setgid stripping allows the same ordering for both non-POSIX ACL and + * POSIX ACL supporting filesystems. + * + * Note that it's currently valid for @type to be 0 if a directory is created. + * Filesystems raise that flag individually and we need to check whether each + * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a + * non-zero type. + * + * Returns: mode to be passed to the filesystem + */ +static inline umode_t vfs_prepare_mode(struct user_namespace *mnt_userns, + const struct inode *dir, umode_t mode, + umode_t mask_perms, umode_t type) +{ + mode = mode_strip_sgid(mnt_userns, dir, mode); + mode = mode_strip_umask(dir, mode); + + /* + * Apply the vfs mandated allowed permission mask and set the type of + * file to be created before we call into the filesystem. + */ + mode &= (mask_perms & ~S_IFMT); + mode |= (type & S_IFMT); + + return mode; +} + +/** * vfs_create - create new file * @mnt_userns: user namespace of the mount the inode was found from * @dir: inode of @dentry @@ -3048,8 +3107,8 @@ int vfs_create(struct user_namespace *mnt_userns, struct inode *dir, if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ - mode &= S_IALLUGO; - mode |= S_IFREG; + + mode = vfs_prepare_mode(mnt_userns, dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; @@ -3312,8 +3371,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; - if (!IS_POSIXACL(dir->d_inode)) - mode &= ~current_umask(); + mode = vfs_prepare_mode(mnt_userns, dir->d_inode, mode, mode, mode); if (likely(got_write)) create_error = may_o_create(mnt_userns, &nd->path, dentry, mode); @@ -3544,6 +3602,7 @@ struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; + mode = vfs_prepare_mode(mnt_userns, dir, mode, mode, mode); error = dir->i_op->tmpfile(mnt_userns, dir, child, mode); if (error) goto out_err; @@ -3821,6 +3880,7 @@ int vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, if (!dir->i_op->mknod) return -EPERM; + mode = vfs_prepare_mode(mnt_userns, dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; @@ -3871,9 +3931,8 @@ retry: if (IS_ERR(dentry)) goto out1; - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); - error = security_path_mknod(&path, dentry, mode, dev); + error = security_path_mknod(&path, dentry, + mode_strip_umask(path.dentry->d_inode, mode), dev); if (error) goto out2; @@ -3943,7 +4002,7 @@ int vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, if (!dir->i_op->mkdir) return -EPERM; - mode &= (S_IRWXUGO|S_ISVTX); + mode = vfs_prepare_mode(mnt_userns, dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) return error; @@ -3971,9 +4030,8 @@ retry: if (IS_ERR(dentry)) goto out_putname; - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); - error = security_path_mkdir(&path, dentry, mode); + error = security_path_mkdir(&path, dentry, + mode_strip_umask(path.dentry->d_inode, mode)); if (!error) { struct user_namespace *mnt_userns; mnt_userns = mnt_user_ns(path.mnt); diff --git a/fs/namespace.c b/fs/namespace.c index 68789f896f08..df137ba19d37 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4238,6 +4238,13 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, err = -EPERM; goto out_fput; } + + /* We're not controlling the target namespace. */ + if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) { + err = -EPERM; + goto out_fput; + } + kattr->mnt_userns = get_user_ns(mnt_userns); out_fput: diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index 5e56da748b2a..fea5f8821da5 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -301,18 +301,14 @@ bl_validate_designator(struct pnfs_block_volume *v) } } -/* - * Try to open the udev path for the WWN. At least on Debian the udev - * by-id path will always point to the dm-multipath device if one exists. - */ static struct block_device * -bl_open_udev_path(struct pnfs_block_volume *v) +bl_open_path(struct pnfs_block_volume *v, const char *prefix) { struct block_device *bdev; const char *devname; - devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%*phN", - v->scsi.designator_len, v->scsi.designator); + devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/%s%*phN", + prefix, v->scsi.designator_len, v->scsi.designator); if (!devname) return ERR_PTR(-ENOMEM); @@ -326,28 +322,6 @@ bl_open_udev_path(struct pnfs_block_volume *v) return bdev; } -/* - * Try to open the RH/Fedora specific dm-mpath udev path for this WWN, as the - * wwn- links will only point to the first discovered SCSI device there. - */ -static struct block_device * -bl_open_dm_mpath_udev_path(struct pnfs_block_volume *v) -{ - struct block_device *bdev; - const char *devname; - - devname = kasprintf(GFP_KERNEL, - "/dev/disk/by-id/dm-uuid-mpath-%d%*phN", - v->scsi.designator_type, - v->scsi.designator_len, v->scsi.designator); - if (!devname) - return ERR_PTR(-ENOMEM); - - bdev = blkdev_get_by_path(devname, FMODE_READ | FMODE_WRITE, NULL); - kfree(devname); - return bdev; -} - static int bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) @@ -360,9 +334,15 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, if (!bl_validate_designator(v)) return -EINVAL; - bdev = bl_open_dm_mpath_udev_path(v); + /* + * Try to open the RH/Fedora specific dm-mpath udev path first, as the + * wwn- links will only point to the first discovered SCSI device there. + * On other distributions like Debian, the default SCSI by-id path will + * point to the dm-multipath device if one exists. + */ + bdev = bl_open_path(v, "dm-uuid-mpath-0x"); if (IS_ERR(bdev)) - bdev = bl_open_udev_path(v); + bdev = bl_open_path(v, "wwn-0x"); if (IS_ERR(bdev)) return PTR_ERR(bdev); d->bdev = bdev; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index e828504cc396..da8da5cdbbc1 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -708,9 +708,9 @@ static int nfs_init_server(struct nfs_server *server, } if (ctx->rsize) - server->rsize = nfs_block_size(ctx->rsize, NULL); + server->rsize = nfs_io_size(ctx->rsize, clp->cl_proto); if (ctx->wsize) - server->wsize = nfs_block_size(ctx->wsize, NULL); + server->wsize = nfs_io_size(ctx->wsize, clp->cl_proto); server->acregmin = ctx->acregmin * HZ; server->acregmax = ctx->acregmax * HZ; @@ -755,18 +755,19 @@ error: static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *fsinfo) { + struct nfs_client *clp = server->nfs_client; unsigned long max_rpc_payload, raw_max_rpc_payload; /* Work out a lot of parameters */ if (server->rsize == 0) - server->rsize = nfs_block_size(fsinfo->rtpref, NULL); + server->rsize = nfs_io_size(fsinfo->rtpref, clp->cl_proto); if (server->wsize == 0) - server->wsize = nfs_block_size(fsinfo->wtpref, NULL); + server->wsize = nfs_io_size(fsinfo->wtpref, clp->cl_proto); if (fsinfo->rtmax >= 512 && server->rsize > fsinfo->rtmax) - server->rsize = nfs_block_size(fsinfo->rtmax, NULL); + server->rsize = nfs_io_size(fsinfo->rtmax, clp->cl_proto); if (fsinfo->wtmax >= 512 && server->wsize > fsinfo->wtmax) - server->wsize = nfs_block_size(fsinfo->wtmax, NULL); + server->wsize = nfs_io_size(fsinfo->wtmax, clp->cl_proto); raw_max_rpc_payload = rpc_max_payload(server->client); max_rpc_payload = nfs_block_size(raw_max_rpc_payload, NULL); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 0c4e8dd6aa96..5d6c2ddc7ea6 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1084,7 +1084,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, struct nfs_cache_array *array; unsigned int i; - array = kmap(desc->page); + array = kmap_local_page(desc->page); for (i = desc->cache_entry_index; i < array->size; i++) { struct nfs_cache_array_entry *ent; @@ -1110,7 +1110,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, if (array->page_is_eof) desc->eof = !desc->eob; - kunmap(desc->page); + kunmap_local(array); dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %llu\n", (unsigned long long)desc->dir_cookie); } @@ -1739,6 +1739,10 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, goto out_bad; } + if ((flags & LOOKUP_RENAME_TARGET) && d_count(dentry) < 2 && + nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + goto out_bad; + if (nfs_verifier_is_delegated(dentry)) return nfs_lookup_revalidate_delegated(dir, dentry, inode); @@ -1778,6 +1782,8 @@ __nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags, int ret; if (flags & LOOKUP_RCU) { + if (dentry->d_fsdata == NFS_FSDATA_BLOCKED) + return -ECHILD; parent = READ_ONCE(dentry->d_parent); dir = d_inode_rcu(parent); if (!dir) @@ -1786,6 +1792,9 @@ __nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags, if (parent != READ_ONCE(dentry->d_parent)) return -ECHILD; } else { + /* Wait for unlink to complete */ + wait_var_event(&dentry->d_fsdata, + dentry->d_fsdata != NFS_FSDATA_BLOCKED); parent = dget_parent(dentry); ret = reval(d_inode(parent), dentry, flags); dput(parent); @@ -2373,7 +2382,8 @@ static void nfs_dentry_remove_handle_error(struct inode *dir, { switch (error) { case -ENOENT: - d_delete(dentry); + if (d_really_is_positive(dentry)) + d_delete(dentry); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); break; case 0: @@ -2454,7 +2464,6 @@ out: int nfs_unlink(struct inode *dir, struct dentry *dentry) { int error; - int need_rehash = 0; dfprintk(VFS, "NFS: unlink(%s/%lu, %pd)\n", dir->i_sb->s_id, dir->i_ino, dentry); @@ -2469,15 +2478,27 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) error = nfs_sillyrename(dir, dentry); goto out; } - if (!d_unhashed(dentry)) { - __d_drop(dentry); - need_rehash = 1; + /* We must prevent any concurrent open until the unlink + * completes. ->d_revalidate will wait for ->d_fsdata + * to clear. We set it here to ensure no lookup succeeds until + * the unlink is complete on the server. + */ + error = -ETXTBSY; + if (WARN_ON(dentry->d_flags & DCACHE_NFSFS_RENAMED) || + WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED)) { + spin_unlock(&dentry->d_lock); + goto out; } + if (dentry->d_fsdata) + /* old devname */ + kfree(dentry->d_fsdata); + dentry->d_fsdata = NFS_FSDATA_BLOCKED; + spin_unlock(&dentry->d_lock); error = nfs_safe_remove(dentry); nfs_dentry_remove_handle_error(dir, dentry, error); - if (need_rehash) - d_rehash(dentry); + dentry->d_fsdata = NULL; + wake_up_var(&dentry->d_fsdata); out: trace_nfs_unlink_exit(dir, dentry, error); return error; @@ -2584,6 +2605,15 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) } EXPORT_SYMBOL_GPL(nfs_link); +static void +nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data) +{ + struct dentry *new_dentry = data->new_dentry; + + new_dentry->d_fsdata = NULL; + wake_up_var(&new_dentry->d_fsdata); +} + /* * RENAME * FIXME: Some nfsds, like the Linux user space nfsd, may generate a @@ -2614,8 +2644,9 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); - struct dentry *dentry = NULL, *rehash = NULL; + struct dentry *dentry = NULL; struct rpc_task *task; + bool must_unblock = false; int error = -EBUSY; if (flags) @@ -2633,18 +2664,27 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, * the new target. */ if (new_inode && !S_ISDIR(new_inode->i_mode)) { - /* - * To prevent any new references to the target during the - * rename, we unhash the dentry in advance. + /* We must prevent any concurrent open until the unlink + * completes. ->d_revalidate will wait for ->d_fsdata + * to clear. We set it here to ensure no lookup succeeds until + * the unlink is complete on the server. */ - if (!d_unhashed(new_dentry)) { - d_drop(new_dentry); - rehash = new_dentry; + error = -ETXTBSY; + if (WARN_ON(new_dentry->d_flags & DCACHE_NFSFS_RENAMED) || + WARN_ON(new_dentry->d_fsdata == NFS_FSDATA_BLOCKED)) + goto out; + if (new_dentry->d_fsdata) { + /* old devname */ + kfree(new_dentry->d_fsdata); + new_dentry->d_fsdata = NULL; } + spin_lock(&new_dentry->d_lock); if (d_count(new_dentry) > 2) { int err; + spin_unlock(&new_dentry->d_lock); + /* copy the target dentry's name */ dentry = d_alloc(new_dentry->d_parent, &new_dentry->d_name); @@ -2657,14 +2697,19 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, goto out; new_dentry = dentry; - rehash = NULL; new_inode = NULL; + } else { + new_dentry->d_fsdata = NFS_FSDATA_BLOCKED; + must_unblock = true; + spin_unlock(&new_dentry->d_lock); } + } if (S_ISREG(old_inode->i_mode)) nfs_sync_inode(old_inode); - task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL); + task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, + must_unblock ? nfs_unblock_rename : NULL); if (IS_ERR(task)) { error = PTR_ERR(task); goto out; @@ -2688,8 +2733,6 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, spin_unlock(&old_inode->i_lock); } out: - if (rehash) - d_rehash(rehash); trace_nfs_rename_exit(old_dir, old_dentry, new_dir, new_dentry, error); if (!error) { diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 4eb2a8380a28..1707f46b1335 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -60,44 +60,12 @@ #include "iostat.h" #include "pnfs.h" #include "fscache.h" +#include "nfstrace.h" #define NFSDBG_FACILITY NFSDBG_VFS static struct kmem_cache *nfs_direct_cachep; -struct nfs_direct_req { - struct kref kref; /* release manager */ - - /* I/O parameters */ - struct nfs_open_context *ctx; /* file open context info */ - struct nfs_lock_context *l_ctx; /* Lock context info */ - struct kiocb * iocb; /* controlling i/o request */ - struct inode * inode; /* target file of i/o */ - - /* completion state */ - atomic_t io_count; /* i/os we're waiting for */ - spinlock_t lock; /* protect completion state */ - - loff_t io_start; /* Start offset for I/O */ - ssize_t count, /* bytes actually processed */ - max_count, /* max expected count */ - bytes_left, /* bytes left to be sent */ - error; /* any reported error */ - struct completion completion; /* wait for i/o completion */ - - /* commit state */ - struct nfs_mds_commit_info mds_cinfo; /* Storage for cinfo */ - struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ - struct work_struct work; - int flags; - /* for write */ -#define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ -#define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ - /* for read */ -#define NFS_ODIRECT_SHOULD_DIRTY (3) /* dirty user-space page after read */ -#define NFS_ODIRECT_DONE INT_MAX /* write verification failed */ -}; - static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops; static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops; static void nfs_direct_write_complete(struct nfs_direct_req *dreq); @@ -364,13 +332,12 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, size_t pgbase; unsigned npages, i; - result = iov_iter_get_pages_alloc(iter, &pagevec, + result = iov_iter_get_pages_alloc2(iter, &pagevec, rsize, &pgbase); if (result < 0) break; bytes = result; - iov_iter_advance(iter, bytes); npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE; for (i = 0; i < npages; i++) { struct nfs_page *req; @@ -478,7 +445,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; - if (iter_is_iovec(iter)) + if (user_backed_iter(iter)) dreq->flags = NFS_ODIRECT_SHOULD_DIRTY; if (!swap) @@ -595,14 +562,17 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) struct nfs_page *req; int status = data->task.tk_status; + trace_nfs_direct_commit_complete(dreq); + if (status < 0) { /* Errors in commit are fatal */ dreq->error = status; dreq->max_count = 0; dreq->count = 0; dreq->flags = NFS_ODIRECT_DONE; - } else if (dreq->flags == NFS_ODIRECT_DONE) + } else { status = dreq->error; + } nfs_init_cinfo_from_dreq(&cinfo, dreq); @@ -631,6 +601,8 @@ static void nfs_direct_resched_write(struct nfs_commit_info *cinfo, { struct nfs_direct_req *dreq = cinfo->dreq; + trace_nfs_direct_resched_write(dreq); + spin_lock(&dreq->lock); if (dreq->flags != NFS_ODIRECT_DONE) dreq->flags = NFS_ODIRECT_RESCHED_WRITES; @@ -695,6 +667,7 @@ static void nfs_direct_write_schedule_work(struct work_struct *work) static void nfs_direct_write_complete(struct nfs_direct_req *dreq) { + trace_nfs_direct_write_complete(dreq); queue_work(nfsiod_workqueue, &dreq->work); /* Calls nfs_direct_write_schedule_work */ } @@ -705,6 +678,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) struct nfs_page *req = nfs_list_entry(hdr->pages.next); int flags = NFS_ODIRECT_DONE; + trace_nfs_direct_write_completion(dreq); + nfs_init_cinfo_from_dreq(&cinfo, dreq); spin_lock(&dreq->lock); @@ -714,7 +689,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) } nfs_direct_count_bytes(dreq, hdr); - if (hdr->good_bytes != 0 && nfs_write_need_commit(hdr)) { + if (test_bit(NFS_IOHDR_UNSTABLE_WRITES, &hdr->flags)) { if (!dreq->flags) dreq->flags = NFS_ODIRECT_DO_COMMIT; flags = dreq->flags; @@ -759,6 +734,8 @@ static void nfs_direct_write_reschedule_io(struct nfs_pgio_header *hdr) { struct nfs_direct_req *dreq = hdr->dreq; + trace_nfs_direct_write_reschedule_io(dreq); + spin_lock(&dreq->lock); if (dreq->error == 0) { dreq->flags = NFS_ODIRECT_RESCHED_WRITES; @@ -799,6 +776,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, size_t requested_bytes = 0; size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE); + trace_nfs_direct_write_schedule_iovec(dreq); + nfs_pageio_init_write(&desc, inode, ioflags, false, &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; @@ -812,13 +791,12 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, size_t pgbase; unsigned npages, i; - result = iov_iter_get_pages_alloc(iter, &pagevec, + result = iov_iter_get_pages_alloc2(iter, &pagevec, wsize, &pgbase); if (result < 0) break; bytes = result; - iov_iter_advance(iter, bytes); npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE; for (i = 0; i < npages; i++) { struct nfs_page *req; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 549baed76351..e032fe201a36 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -221,8 +221,10 @@ nfs_file_fsync_commit(struct file *file, int datasync) int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - struct nfs_open_context *ctx = nfs_file_open_context(file); struct inode *inode = file_inode(file); + struct nfs_inode *nfsi = NFS_I(inode); + long save_nredirtied = atomic_long_read(&nfsi->redirtied_pages); + long nredirtied; int ret; trace_nfs_fsync_enter(inode); @@ -237,15 +239,10 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) ret = pnfs_sync_inode(inode, !!datasync); if (ret != 0) break; - if (!test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags)) + nredirtied = atomic_long_read(&nfsi->redirtied_pages); + if (nredirtied == save_nredirtied) break; - /* - * If nfs_file_fsync_commit detected a server reboot, then - * resend all dirty pages that might have been covered by - * the NFS_CONTEXT_RESEND_WRITES flag - */ - start = 0; - end = LLONG_MAX; + save_nredirtied = nredirtied; } trace_nfs_fsync_exit(inode, ret); @@ -661,8 +658,6 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) result = filemap_fdatawait_range(file->f_mapping, iocb->ki_pos - written, iocb->ki_pos - 1); - if (result < 0) - goto out; } result = generic_write_sync(iocb, written); if (result < 0) diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 2b2661582bbe..ad34a33b0737 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -181,6 +181,8 @@ static int filelayout_async_handle_error(struct rpc_task *task, case -EIO: case -ETIMEDOUT: case -EPIPE: + case -EPROTO: + case -ENODEV: dprintk("%s DS connection error %d\n", __func__, task->tk_status); nfs4_mark_deviceid_unavailable(devid); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 604be402ae13..7d285561e59f 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1131,6 +1131,8 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, case -EIO: case -ETIMEDOUT: case -EPIPE: + case -EPROTO: + case -ENODEV: dprintk("%s DS connection error %d\n", __func__, task->tk_status); nfs4_delete_deviceid(devid->ld, devid->nfs_client, @@ -1236,6 +1238,8 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, case -ENOBUFS: case -EPIPE: case -EPERM: + case -EPROTO: + case -ENODEV: *op_status = status = NFS4ERR_NXIO; break; case -EACCES: diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index bfa7202ca7be..e028f5a0ef5f 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -113,8 +113,10 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, goto out_err_drain_dsaddrs; ds_versions[i].version = be32_to_cpup(p++); ds_versions[i].minor_version = be32_to_cpup(p++); - ds_versions[i].rsize = nfs_block_size(be32_to_cpup(p++), NULL); - ds_versions[i].wsize = nfs_block_size(be32_to_cpup(p++), NULL); + ds_versions[i].rsize = nfs_io_size(be32_to_cpup(p++), + server->nfs_client->cl_proto); + ds_versions[i].wsize = nfs_io_size(be32_to_cpup(p++), + server->nfs_client->cl_proto); ds_versions[i].tightly_coupled = be32_to_cpup(p); if (ds_versions[i].rsize > NFS_MAX_FILE_IO_SIZE) diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index 9a16897e8dc6..4da701fd1424 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -21,6 +21,8 @@ #include "nfs.h" #include "internal.h" +#include "nfstrace.h" + #define NFSDBG_FACILITY NFSDBG_MOUNT #if IS_ENABLED(CONFIG_NFS_V3) @@ -284,7 +286,6 @@ static int nfs_verify_server_address(struct sockaddr *addr) } } - dfprintk(MOUNT, "NFS: Invalid IP address specified\n"); return 0; } @@ -378,7 +379,7 @@ static int nfs_parse_security_flavors(struct fs_context *fc, char *string = param->string, *p; int ret; - dfprintk(MOUNT, "NFS: parsing %s=%s option\n", param->key, param->string); + trace_nfs_mount_assign(param->key, string); while ((p = strsep(&string, ":")) != NULL) { if (!*p) @@ -480,11 +481,11 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, unsigned int len; int ret, opt; - dfprintk(MOUNT, "NFS: parsing nfs mount option '%s'\n", param->key); + trace_nfs_mount_option(param); opt = fs_parse(fc, nfs_fs_parameters, param, &result); if (opt < 0) - return ctx->sloppy ? 1 : opt; + return (opt == -ENOPARAM && ctx->sloppy) ? 1 : opt; if (fc->security) ctx->has_sec_mnt_opts = 1; @@ -683,6 +684,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, return ret; break; case Opt_vers: + trace_nfs_mount_assign(param->key, param->string); ret = nfs_parse_version_string(fc, param->string); if (ret < 0) return ret; @@ -694,6 +696,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, break; case Opt_proto: + trace_nfs_mount_assign(param->key, param->string); protofamily = AF_INET; switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { case Opt_xprt_udp6: @@ -729,6 +732,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, break; case Opt_mountproto: + trace_nfs_mount_assign(param->key, param->string); mountfamily = AF_INET; switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { case Opt_xprt_udp6: @@ -751,6 +755,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, break; case Opt_addr: + trace_nfs_mount_assign(param->key, param->string); len = rpc_pton(fc->net_ns, param->string, param->size, &ctx->nfs_server.address, sizeof(ctx->nfs_server._address)); @@ -759,16 +764,19 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, ctx->nfs_server.addrlen = len; break; case Opt_clientaddr: + trace_nfs_mount_assign(param->key, param->string); kfree(ctx->client_address); ctx->client_address = param->string; param->string = NULL; break; case Opt_mounthost: + trace_nfs_mount_assign(param->key, param->string); kfree(ctx->mount_server.hostname); ctx->mount_server.hostname = param->string; param->string = NULL; break; case Opt_mountaddr: + trace_nfs_mount_assign(param->key, param->string); len = rpc_pton(fc->net_ns, param->string, param->size, &ctx->mount_server.address, sizeof(ctx->mount_server._address)); @@ -846,7 +854,6 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, */ case Opt_sloppy: ctx->sloppy = true; - dfprintk(MOUNT, "NFS: relaxing parsing rules\n"); break; } @@ -879,10 +886,8 @@ static int nfs_parse_source(struct fs_context *fc, size_t len; const char *end; - if (unlikely(!dev_name || !*dev_name)) { - dfprintk(MOUNT, "NFS: device name not specified\n"); + if (unlikely(!dev_name || !*dev_name)) return -EINVAL; - } /* Is the host name protected with square brakcets? */ if (*dev_name == '[') { @@ -922,7 +927,7 @@ static int nfs_parse_source(struct fs_context *fc, if (!ctx->nfs_server.export_path) goto out_nomem; - dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", ctx->nfs_server.export_path); + trace_nfs_mount_path(ctx->nfs_server.export_path); return 0; out_bad_devname: @@ -1116,7 +1121,6 @@ out_no_sec: return nfs_invalf(fc, "NFS: nfs_mount_data version supports only AUTH_SYS"); out_nomem: - dfprintk(MOUNT, "NFS: not enough memory to handle mount options"); return -ENOMEM; out_no_address: @@ -1248,7 +1252,7 @@ static int nfs4_parse_monolithic(struct fs_context *fc, if (IS_ERR(c)) return PTR_ERR(c); ctx->nfs_server.export_path = c; - dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", c); + trace_nfs_mount_path(c); c = strndup_user(data->client_addr.data, 16); if (IS_ERR(c)) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b4e46b0ffa2d..bea7c005119c 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -426,6 +426,7 @@ nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) static void nfs_inode_init_regular(struct nfs_inode *nfsi) { atomic_long_set(&nfsi->nrequests, 0); + atomic_long_set(&nfsi->redirtied_pages, 0); INIT_LIST_HEAD(&nfsi->commit_info.list); atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 437ebe544aaf..27c720d71b4e 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -707,6 +707,24 @@ unsigned long nfs_block_size(unsigned long bsize, unsigned char *nrbitsp) } /* + * Compute and set NFS server rsize / wsize + */ +static inline +unsigned long nfs_io_size(unsigned long iosize, enum xprt_transports proto) +{ + if (iosize < NFS_MIN_FILE_IO_SIZE) + iosize = NFS_DEF_FILE_IO_SIZE; + else if (iosize >= NFS_MAX_FILE_IO_SIZE) + iosize = NFS_MAX_FILE_IO_SIZE; + else + iosize = iosize & PAGE_MASK; + + if (proto == XPRT_TRANSPORT_UDP) + return nfs_block_bits(iosize, NULL); + return iosize; +} + +/* * Determine the maximum file size for a superblock */ static inline @@ -861,3 +879,36 @@ static inline void nfs_set_port(struct sockaddr *sap, int *port, rpc_set_port(sap, *port); } + +struct nfs_direct_req { + struct kref kref; /* release manager */ + + /* I/O parameters */ + struct nfs_open_context *ctx; /* file open context info */ + struct nfs_lock_context *l_ctx; /* Lock context info */ + struct kiocb * iocb; /* controlling i/o request */ + struct inode * inode; /* target file of i/o */ + + /* completion state */ + atomic_t io_count; /* i/os we're waiting for */ + spinlock_t lock; /* protect completion state */ + + loff_t io_start; /* Start offset for I/O */ + ssize_t count, /* bytes actually processed */ + max_count, /* max expected count */ + bytes_left, /* bytes left to be sent */ + error; /* any reported error */ + struct completion completion; /* wait for i/o completion */ + + /* commit state */ + struct nfs_mds_commit_info mds_cinfo; /* Storage for cinfo */ + struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ + struct work_struct work; + int flags; + /* for write */ +#define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ +#define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ + /* for read */ +#define NFS_ODIRECT_SHOULD_DIRTY (3) /* dirty user-space page after read */ +#define NFS_ODIRECT_DONE INT_MAX /* write verification failed */ +}; diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 5601e47360c2..b49359afac88 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -108,7 +108,6 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, if (mds_srv->flags & NFS_MOUNT_NORESVPORT) __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); - __set_bit(NFS_CS_NOPING, &cl_init.init_flags); __set_bit(NFS_CS_DS, &cl_init.init_flags); /* Use the MDS nfs_client cl_ipaddr. */ diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index e7b34f7e0614..a9bf09fdf2c3 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -1017,15 +1017,16 @@ int __init nfs4_xattr_cache_init(void) if (ret) goto out2; - ret = register_shrinker(&nfs4_xattr_cache_shrinker); + ret = register_shrinker(&nfs4_xattr_cache_shrinker, "nfs-xattr_cache"); if (ret) goto out1; - ret = register_shrinker(&nfs4_xattr_entry_shrinker); + ret = register_shrinker(&nfs4_xattr_entry_shrinker, "nfs-xattr_entry"); if (ret) goto out; - ret = register_shrinker(&nfs4_xattr_large_entry_shrinker); + ret = register_shrinker(&nfs4_xattr_large_entry_shrinker, + "nfs-xattr_large_entry"); if (!ret) return 0; diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 271e5f92ed01..b56f05113d36 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -1025,82 +1025,95 @@ static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *re return decode_op_hdr(xdr, OP_DEALLOCATE); } -static int decode_read_plus_data(struct xdr_stream *xdr, - struct nfs_pgio_args *args, - struct nfs_pgio_res *res) -{ - uint32_t count, recvd; +struct read_plus_segment { + enum data_content4 type; uint64_t offset; - __be32 *p; - - p = xdr_inline_decode(xdr, 8 + 4); - if (!p) - return 1; + union { + struct { + uint64_t length; + } hole; + + struct { + uint32_t length; + unsigned int from; + } data; + }; +}; - p = xdr_decode_hyper(p, &offset); - count = be32_to_cpup(p); - recvd = xdr_align_data(xdr, res->count, xdr_align_size(count)); - if (recvd > count) - recvd = count; - if (res->count + recvd > args->count) { - if (args->count > res->count) - res->count += args->count - res->count; - return 1; - } - res->count += recvd; - if (count > recvd) - return 1; - return 0; +static inline uint64_t read_plus_segment_length(struct read_plus_segment *seg) +{ + return seg->type == NFS4_CONTENT_DATA ? seg->data.length : seg->hole.length; } -static int decode_read_plus_hole(struct xdr_stream *xdr, - struct nfs_pgio_args *args, - struct nfs_pgio_res *res, uint32_t *eof) +static int decode_read_plus_segment(struct xdr_stream *xdr, + struct read_plus_segment *seg) { - uint64_t offset, length, recvd; __be32 *p; - p = xdr_inline_decode(xdr, 8 + 8); + p = xdr_inline_decode(xdr, 4); if (!p) - return 1; - - p = xdr_decode_hyper(p, &offset); - p = xdr_decode_hyper(p, &length); - if (offset != args->offset + res->count) { - /* Server returned an out-of-sequence extent */ - if (offset > args->offset + res->count || - offset + length < args->offset + res->count) { - dprintk("NFS: server returned out of sequence extent: " - "offset/size = %llu/%llu != expected %llu\n", - (unsigned long long)offset, - (unsigned long long)length, - (unsigned long long)(args->offset + - res->count)); - return 1; - } - length -= args->offset + res->count - offset; - } - if (length + res->count > args->count) { - *eof = 0; - if (unlikely(res->count >= args->count)) - return 1; - length = args->count - res->count; - } - recvd = xdr_expand_hole(xdr, res->count, length); - res->count += recvd; + return -EIO; + seg->type = be32_to_cpup(p++); + + p = xdr_inline_decode(xdr, seg->type == NFS4_CONTENT_DATA ? 12 : 16); + if (!p) + return -EIO; + p = xdr_decode_hyper(p, &seg->offset); + + if (seg->type == NFS4_CONTENT_DATA) { + struct xdr_buf buf; + uint32_t len = be32_to_cpup(p); + + seg->data.length = len; + seg->data.from = xdr_stream_pos(xdr); - if (recvd < length) - return 1; + if (!xdr_stream_subsegment(xdr, &buf, xdr_align_size(len))) + return -EIO; + } else if (seg->type == NFS4_CONTENT_HOLE) { + xdr_decode_hyper(p, &seg->hole.length); + } else + return -EINVAL; return 0; } +static int process_read_plus_segment(struct xdr_stream *xdr, + struct nfs_pgio_args *args, + struct nfs_pgio_res *res, + struct read_plus_segment *seg) +{ + unsigned long offset = seg->offset; + unsigned long length = read_plus_segment_length(seg); + unsigned int bufpos; + + if (offset + length < args->offset) + return 0; + else if (offset > args->offset + args->count) { + res->eof = 0; + return 0; + } else if (offset < args->offset) { + length -= (args->offset - offset); + offset = args->offset; + } else if (offset + length > args->offset + args->count) { + length = (args->offset + args->count) - offset; + res->eof = 0; + } + + bufpos = xdr->buf->head[0].iov_len + (offset - args->offset); + if (seg->type == NFS4_CONTENT_HOLE) + return xdr_stream_zero(xdr, bufpos, length); + else + return xdr_stream_move_subsegment(xdr, seg->data.from, bufpos, length); +} + static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res) { struct nfs_pgio_header *hdr = container_of(res, struct nfs_pgio_header, res); struct nfs_pgio_args *args = &hdr->args; - uint32_t eof, segments, type; + uint32_t segments; + struct read_plus_segment *segs; int status, i; + char scratch_buf[16]; __be32 *p; status = decode_op_hdr(xdr, OP_READ_PLUS); @@ -1112,38 +1125,31 @@ static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res) return -EIO; res->count = 0; - eof = be32_to_cpup(p++); + res->eof = be32_to_cpup(p++); segments = be32_to_cpup(p++); if (segments == 0) - goto out; - - for (i = 0; i < segments; i++) { - p = xdr_inline_decode(xdr, 4); - if (!p) - goto early_out; + return status; - type = be32_to_cpup(p++); - if (type == NFS4_CONTENT_DATA) - status = decode_read_plus_data(xdr, args, res); - else if (type == NFS4_CONTENT_HOLE) - status = decode_read_plus_hole(xdr, args, res, &eof); - else - return -EINVAL; + segs = kmalloc_array(segments, sizeof(*segs), GFP_KERNEL); + if (!segs) + return -ENOMEM; + xdr_set_scratch_buffer(xdr, &scratch_buf, 32); + status = -EIO; + for (i = 0; i < segments; i++) { + status = decode_read_plus_segment(xdr, &segs[i]); if (status < 0) - return status; - if (status > 0) - goto early_out; + goto out; } + xdr_set_pagelen(xdr, xdr_align_size(args->count)); + for (i = segments; i > 0; i--) + res->count += process_read_plus_segment(xdr, args, res, &segs[i-1]); + status = 0; + out: - res->eof = eof; - return 0; -early_out: - if (unlikely(!i)) - return -EIO; - res->eof = 0; - return 0; + kfree(segs); + return status; } static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 47a6cf892c95..3c5678aec006 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -1161,9 +1161,9 @@ static int nfs4_init_server(struct nfs_server *server, struct fs_context *fc) return error; if (ctx->rsize) - server->rsize = nfs_block_size(ctx->rsize, NULL); + server->rsize = nfs_io_size(ctx->rsize, server->nfs_client->cl_proto); if (ctx->wsize) - server->wsize = nfs_block_size(ctx->wsize, NULL); + server->wsize = nfs_io_size(ctx->wsize, server->nfs_client->cl_proto); server->acregmin = ctx->acregmin * HZ; server->acregmax = ctx->acregmax * HZ; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index e88f6b18445e..9eb181287879 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -340,6 +340,11 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, goto out; } + if (!S_ISREG(fattr->mode)) { + res = ERR_PTR(-EBADF); + goto out; + } + res = ERR_PTR(-ENOMEM); len = strlen(SSC_READ_NAME_BODY) + 16; read_name = kzalloc(len, GFP_KERNEL); @@ -357,6 +362,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, r_ino->i_fop); if (IS_ERR(filep)) { res = ERR_CAST(filep); + iput(r_ino); goto out_free_name; } diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index f331866dd418..ec6afd3c4bca 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -561,22 +561,20 @@ nfs_idmap_prepare_pipe_upcall(struct idmap *idmap, return true; } -static void -nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret) +static void nfs_idmap_complete_pipe_upcall(struct idmap_legacy_upcalldata *data, + int ret) { - struct key *authkey = idmap->idmap_upcall_data->authkey; - - kfree(idmap->idmap_upcall_data); - idmap->idmap_upcall_data = NULL; - complete_request_key(authkey, ret); - key_put(authkey); + complete_request_key(data->authkey, ret); + key_put(data->authkey); + kfree(data); } -static void -nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret) +static void nfs_idmap_abort_pipe_upcall(struct idmap *idmap, + struct idmap_legacy_upcalldata *data, + int ret) { - if (idmap->idmap_upcall_data != NULL) - nfs_idmap_complete_pipe_upcall_locked(idmap, ret); + if (cmpxchg(&idmap->idmap_upcall_data, data, NULL) == data) + nfs_idmap_complete_pipe_upcall(data, ret); } static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) @@ -613,7 +611,7 @@ static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) ret = rpc_queue_upcall(idmap->idmap_pipe, msg); if (ret < 0) - nfs_idmap_abort_pipe_upcall(idmap, ret); + nfs_idmap_abort_pipe_upcall(idmap, data, ret); return ret; out2: @@ -669,6 +667,7 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) struct request_key_auth *rka; struct rpc_inode *rpci = RPC_I(file_inode(filp)); struct idmap *idmap = (struct idmap *)rpci->private; + struct idmap_legacy_upcalldata *data; struct key *authkey; struct idmap_msg im; size_t namelen_in; @@ -678,10 +677,11 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) * will have been woken up and someone else may now have used * idmap_key_cons - so after this point we may no longer touch it. */ - if (idmap->idmap_upcall_data == NULL) + data = xchg(&idmap->idmap_upcall_data, NULL); + if (data == NULL) goto out_noupcall; - authkey = idmap->idmap_upcall_data->authkey; + authkey = data->authkey; rka = get_request_key_auth(authkey); if (mlen != sizeof(im)) { @@ -703,18 +703,17 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) { ret = -EINVAL; goto out; -} + } - ret = nfs_idmap_read_and_verify_message(&im, - &idmap->idmap_upcall_data->idmap_msg, - rka->target_key, authkey); + ret = nfs_idmap_read_and_verify_message(&im, &data->idmap_msg, + rka->target_key, authkey); if (ret >= 0) { key_set_timeout(rka->target_key, nfs_idmap_cache_timeout); ret = mlen; } out: - nfs_idmap_complete_pipe_upcall_locked(idmap, ret); + nfs_idmap_complete_pipe_upcall(data, ret); out_noupcall: return ret; } @@ -728,7 +727,7 @@ idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg) struct idmap *idmap = data->idmap; if (msg->errno) - nfs_idmap_abort_pipe_upcall(idmap, msg->errno); + nfs_idmap_abort_pipe_upcall(idmap, data, msg->errno); } static void @@ -736,8 +735,11 @@ idmap_release_pipe(struct inode *inode) { struct rpc_inode *rpci = RPC_I(inode); struct idmap *idmap = (struct idmap *)rpci->private; + struct idmap_legacy_upcalldata *data; - nfs_idmap_abort_pipe_upcall(idmap, -EPIPE); + data = xchg(&idmap->idmap_upcall_data, NULL); + if (data) + nfs_idmap_complete_pipe_upcall(data, -EPIPE); } int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, kuid_t *uid) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index bb0e84a46d61..3ed14a2a84a4 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -784,10 +784,9 @@ static void nfs4_slot_sequence_record_sent(struct nfs4_slot *slot, if ((s32)(seqnr - slot->seq_nr_highest_sent) > 0) slot->seq_nr_highest_sent = seqnr; } -static void nfs4_slot_sequence_acked(struct nfs4_slot *slot, - u32 seqnr) +static void nfs4_slot_sequence_acked(struct nfs4_slot *slot, u32 seqnr) { - slot->seq_nr_highest_sent = seqnr; + nfs4_slot_sequence_record_sent(slot, seqnr); slot->seq_nr_last_acked = seqnr; } @@ -854,7 +853,6 @@ static int nfs41_sequence_process(struct rpc_task *task, __func__, slot->slot_nr, slot->seq_nr); - nfs4_slot_sequence_acked(slot, slot->seq_nr); goto out_retry; case -NFS4ERR_RETRY_UNCACHED_REP: case -NFS4ERR_SEQ_FALSE_RETRY: @@ -3098,12 +3096,13 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, } out: - if (opendata->lgp) { - nfs4_lgopen_release(opendata->lgp); - opendata->lgp = NULL; - } - if (!opendata->cancelled) + if (!opendata->cancelled) { + if (opendata->lgp) { + nfs4_lgopen_release(opendata->lgp); + opendata->lgp = NULL; + } nfs4_sequence_free_slot(&opendata->o_res.seq_res); + } return ret; } @@ -8924,6 +8923,9 @@ void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, if (status == 0) rpc_clnt_xprt_switch_add_xprt(clnt, xprt); + else if (rpc_clnt_xprt_switch_has_addr(clnt, + (struct sockaddr *)&xprt->addr)) + rpc_clnt_xprt_switch_remove_xprt(clnt, xprt); rpc_put_task(task); } @@ -9248,6 +9250,13 @@ int nfs4_proc_create_session(struct nfs_client *clp, const struct cred *cred) int status; unsigned *ptr; struct nfs4_session *session = clp->cl_session; + struct nfs4_add_xprt_data xprtdata = { + .clp = clp, + }; + struct rpc_add_xprt_test rpcdata = { + .add_xprt_test = clp->cl_mvops->session_trunk, + .data = &xprtdata, + }; dprintk("--> %s clp=%p session=%p\n", __func__, clp, session); @@ -9264,6 +9273,7 @@ int nfs4_proc_create_session(struct nfs_client *clp, const struct cred *cred) ptr = (unsigned *)&session->sess_id.data[0]; dprintk("%s client>seqid %d sessionid %u:%u:%u:%u\n", __func__, clp->cl_seqid, ptr[0], ptr[1], ptr[2], ptr[3]); + rpc_clnt_probe_trunked_xprts(clp->cl_rpcclient, &rpcdata); out: return status; } @@ -9293,6 +9303,7 @@ int nfs4_proc_destroy_session(struct nfs4_session *session, if (status) dprintk("NFS: Got error %d from the server on DESTROY_SESSION. " "Session has been destroyed regardless...\n", status); + rpc_clnt_manage_trunked_xprts(session->clp->cl_rpcclient); return status; } @@ -9477,6 +9488,9 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf rpc_delay(task, NFS4_POLL_RETRY_MAX); fallthrough; case -NFS4ERR_RETRY_UNCACHED_REP: + case -EACCES: + dprintk("%s: failed to reclaim complete error %d for server %s, retrying\n", + __func__, task->tk_status, clp->cl_hostname); return -EAGAIN; case -NFS4ERR_BADSESSION: case -NFS4ERR_DEADSESSION: diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 012bd7339862..8c6cc58679ff 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1137,7 +1137,7 @@ TRACE_EVENT(nfs_readpage_done, __field(u32, arg_count) __field(u32, res_count) __field(bool, eof) - __field(int, status) + __field(int, error) ), TP_fast_assign( @@ -1146,7 +1146,7 @@ TRACE_EVENT(nfs_readpage_done, const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; - __entry->status = task->tk_status; + __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; @@ -1157,14 +1157,13 @@ TRACE_EVENT(nfs_readpage_done, ), TP_printk( - "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%u res=%u status=%d%s", + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u res=%u%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, - __entry->res_count, __entry->status, - __entry->eof ? " eof" : "" + __entry->res_count, __entry->eof ? " eof" : "" ) ); @@ -1184,7 +1183,7 @@ TRACE_EVENT(nfs_readpage_short, __field(u32, arg_count) __field(u32, res_count) __field(bool, eof) - __field(int, status) + __field(int, error) ), TP_fast_assign( @@ -1193,7 +1192,7 @@ TRACE_EVENT(nfs_readpage_short, const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; - __entry->status = task->tk_status; + __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; @@ -1204,14 +1203,13 @@ TRACE_EVENT(nfs_readpage_short, ), TP_printk( - "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%u res=%u status=%d%s", + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u res=%u%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, - __entry->res_count, __entry->status, - __entry->eof ? " eof" : "" + __entry->res_count, __entry->eof ? " eof" : "" ) ); @@ -1323,7 +1321,7 @@ TRACE_EVENT(nfs_pgio_error, __field(u32, arg_count) __field(u32, res_count) __field(loff_t, pos) - __field(int, status) + __field(int, error) ), TP_fast_assign( @@ -1332,7 +1330,7 @@ TRACE_EVENT(nfs_pgio_error, const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; - __entry->status = error; + __entry->error = error; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; @@ -1341,12 +1339,12 @@ TRACE_EVENT(nfs_pgio_error, __entry->fhandle = nfs_fhandle_hash(fh); ), - TP_printk("fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%u res=%u pos=%llu status=%d", + TP_printk("error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u res=%u pos=%llu", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, - __entry->pos, __entry->status + __entry->pos ) ); @@ -1406,7 +1404,7 @@ TRACE_EVENT(nfs_writeback_done, __field(loff_t, offset) __field(u32, arg_count) __field(u32, res_count) - __field(int, status) + __field(int, error) __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), @@ -1418,7 +1416,7 @@ TRACE_EVENT(nfs_writeback_done, hdr->args.fh : &nfsi->fh; const struct nfs_writeverf *verf = hdr->res.verf; - __entry->status = task->tk_status; + __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; @@ -1432,14 +1430,14 @@ TRACE_EVENT(nfs_writeback_done, ), TP_printk( - "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld count=%u res=%u status=%d stable=%s " - "verifier=%s", + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u res=%u stable=%s " + "verifier=%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, - __entry->res_count, __entry->status, + __entry->res_count, show_nfs_stable_how(__entry->stable), show_nfs4_verifier(__entry->verifier) ) @@ -1447,44 +1445,50 @@ TRACE_EVENT(nfs_writeback_done, DECLARE_EVENT_CLASS(nfs_page_error_class, TP_PROTO( + const struct inode *inode, const struct nfs_page *req, int error ), - TP_ARGS(req, error), + TP_ARGS(inode, req, error), TP_STRUCT__entry( - __field(const void *, req) - __field(pgoff_t, index) - __field(unsigned int, offset) - __field(unsigned int, pgbase) - __field(unsigned int, bytes) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + __field(unsigned int, count) __field(int, error) ), TP_fast_assign( - __entry->req = req; - __entry->index = req->wb_index; - __entry->offset = req->wb_offset; - __entry->pgbase = req->wb_pgbase; - __entry->bytes = req->wb_bytes; + const struct nfs_inode *nfsi = NFS_I(inode); + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->offset = req_offset(req); + __entry->count = req->wb_bytes; __entry->error = error; ), TP_printk( - "req=%p index=%lu offset=%u pgbase=%u bytes=%u error=%d", - __entry->req, __entry->index, __entry->offset, - __entry->pgbase, __entry->bytes, __entry->error + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%u", __entry->error, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __entry->offset, + __entry->count ) ); #define DEFINE_NFS_PAGEERR_EVENT(name) \ DEFINE_EVENT(nfs_page_error_class, name, \ TP_PROTO( \ + const struct inode *inode, \ const struct nfs_page *req, \ int error \ ), \ - TP_ARGS(req, error)) + TP_ARGS(inode, req, error)) DEFINE_NFS_PAGEERR_EVENT(nfs_write_error); DEFINE_NFS_PAGEERR_EVENT(nfs_comp_error); @@ -1541,7 +1545,7 @@ TRACE_EVENT(nfs_commit_done, __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) - __field(int, status) + __field(int, error) __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), @@ -1553,7 +1557,7 @@ TRACE_EVENT(nfs_commit_done, data->args.fh : &nfsi->fh; const struct nfs_writeverf *verf = data->res.verf; - __entry->status = task->tk_status; + __entry->error = task->tk_status; __entry->offset = data->args.offset; __entry->stable = verf->committed; memcpy(__entry->verifier, @@ -1565,17 +1569,83 @@ TRACE_EVENT(nfs_commit_done, ), TP_printk( - "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld status=%d stable=%s verifier=%s", + "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld stable=%s verifier=%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - (long long)__entry->offset, __entry->status, + (long long)__entry->offset, show_nfs_stable_how(__entry->stable), show_nfs4_verifier(__entry->verifier) ) ); +#define nfs_show_direct_req_flags(v) \ + __print_flags(v, "|", \ + { NFS_ODIRECT_DO_COMMIT, "DO_COMMIT" }, \ + { NFS_ODIRECT_RESCHED_WRITES, "RESCHED_WRITES" }, \ + { NFS_ODIRECT_SHOULD_DIRTY, "SHOULD DIRTY" }, \ + { NFS_ODIRECT_DONE, "DONE" } ) + +DECLARE_EVENT_CLASS(nfs_direct_req_class, + TP_PROTO( + const struct nfs_direct_req *dreq + ), + + TP_ARGS(dreq), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, fileid) + __field(u32, fhandle) + __field(loff_t, offset) + __field(ssize_t, count) + __field(ssize_t, bytes_left) + __field(ssize_t, error) + __field(int, flags) + ), + + TP_fast_assign( + const struct inode *inode = dreq->inode; + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = &nfsi->fh; + + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(fh); + __entry->offset = dreq->io_start; + __entry->count = dreq->count; + __entry->bytes_left = dreq->bytes_left; + __entry->error = dreq->error; + __entry->flags = dreq->flags; + ), + + TP_printk( + "error=%zd fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%zd bytes_left=%zd flags=%s", + __entry->error, MAJOR(__entry->dev), + MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __entry->offset, + __entry->count, __entry->bytes_left, + nfs_show_direct_req_flags(__entry->flags) + ) +); + +#define DEFINE_NFS_DIRECT_REQ_EVENT(name) \ + DEFINE_EVENT(nfs_direct_req_class, name, \ + TP_PROTO( \ + const struct nfs_direct_req *dreq \ + ), \ + TP_ARGS(dreq)) + +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_commit_complete); +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_resched_write); +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_complete); +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_completion); +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_schedule_iovec); +DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_reschedule_io); + TRACE_EVENT(nfs_fh_to_dentry, TP_PROTO( const struct super_block *sb, @@ -1609,6 +1679,65 @@ TRACE_EVENT(nfs_fh_to_dentry, ) ); +TRACE_EVENT(nfs_mount_assign, + TP_PROTO( + const char *option, + const char *value + ), + + TP_ARGS(option, value), + + TP_STRUCT__entry( + __string(option, option) + __string(value, value) + ), + + TP_fast_assign( + __assign_str(option, option); + __assign_str(value, value); + ), + + TP_printk("option %s=%s", + __get_str(option), __get_str(value) + ) +); + +TRACE_EVENT(nfs_mount_option, + TP_PROTO( + const struct fs_parameter *param + ), + + TP_ARGS(param), + + TP_STRUCT__entry( + __string(option, param->key) + ), + + TP_fast_assign( + __assign_str(option, param->key); + ), + + TP_printk("option %s", __get_str(option)) +); + +TRACE_EVENT(nfs_mount_path, + TP_PROTO( + const char *path + ), + + TP_ARGS(path), + + TP_STRUCT__entry( + __string(path, path) + ), + + TP_fast_assign( + __assign_str(path, path); + ), + + TP_printk("path='%s'", __get_str(path)) +); + DECLARE_EVENT_CLASS(nfs_xdr_event, TP_PROTO( const struct xdr_stream *xdr, diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 41a9b6b58fb9..2613b7e36eb9 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2817,7 +2817,6 @@ int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *hdr) /* Resend all requests through the MDS */ nfs_pageio_init_write(&pgio, hdr->inode, FLUSH_STABLE, true, hdr->completion_ops); - set_bit(NFS_CONTEXT_RESEND_WRITES, &hdr->args.context->flags); return nfs_pageio_resend(&pgio, hdr); } EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 6ab5eeb000dc..82944e14fcea 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -149,7 +149,7 @@ int __init register_nfs_fs(void) ret = nfs_register_sysctl(); if (ret < 0) goto error_2; - ret = register_shrinker(&acl_shrinker); + ret = register_shrinker(&acl_shrinker, "nfs-acl"); if (ret < 0) goto error_3; #ifdef CONFIG_NFS_V4_2 diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 69569696dde0..1843fa235d9b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -592,7 +592,8 @@ nfs_lock_and_join_requests(struct page *page) static void nfs_write_error(struct nfs_page *req, int error) { - trace_nfs_write_error(req, error); + trace_nfs_write_error(page_file_mapping(req->wb_page)->host, req, + error); nfs_mapping_set_error(req->wb_page, error); nfs_inode_remove_request(req); nfs_end_page_writeback(req); @@ -1000,7 +1001,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) nfs_list_remove_request(req); if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes < bytes)) { - trace_nfs_comp_error(req, hdr->error); + trace_nfs_comp_error(hdr->inode, req, hdr->error); nfs_mapping_set_error(req->wb_page, hdr->error); goto remove_req; } @@ -1419,10 +1420,12 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, */ static void nfs_redirty_request(struct nfs_page *req) { + struct nfs_inode *nfsi = NFS_I(page_file_mapping(req->wb_page)->host); + /* Bump the transmission count */ req->wb_nio++; nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&nfsi->redirtied_pages); nfs_end_page_writeback(req); nfs_release_request(req); } @@ -1444,8 +1447,6 @@ static void nfs_async_write_error(struct list_head *head, int error) static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr) { nfs_async_write_error(&hdr->pages, 0); - filemap_fdatawrite_range(hdr->inode->i_mapping, hdr->args.offset, - hdr->args.offset + hdr->args.count - 1); } static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { @@ -1576,25 +1577,37 @@ static int nfs_writeback_done(struct rpc_task *task, nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, hdr->res.count); trace_nfs_writeback_done(task, hdr); - if (hdr->res.verf->committed < hdr->args.stable && - task->tk_status >= 0) { - /* We tried a write call, but the server did not - * commit data to stable storage even though we - * requested it. - * Note: There is a known bug in Tru64 < 5.0 in which - * the server reports NFS_DATA_SYNC, but performs - * NFS_FILE_SYNC. We therefore implement this checking - * as a dprintk() in order to avoid filling syslog. - */ - static unsigned long complain; + if (task->tk_status >= 0) { + enum nfs3_stable_how committed = hdr->res.verf->committed; + + if (committed == NFS_UNSTABLE) { + /* + * We have some uncommitted data on the server at + * this point, so ensure that we keep track of that + * fact irrespective of what later writes do. + */ + set_bit(NFS_IOHDR_UNSTABLE_WRITES, &hdr->flags); + } - /* Note this will print the MDS for a DS write */ - if (time_before(complain, jiffies)) { - dprintk("NFS: faulty NFS server %s:" - " (committed = %d) != (stable = %d)\n", - NFS_SERVER(inode)->nfs_client->cl_hostname, - hdr->res.verf->committed, hdr->args.stable); - complain = jiffies + 300 * HZ; + if (committed < hdr->args.stable) { + /* We tried a write call, but the server did not + * commit data to stable storage even though we + * requested it. + * Note: There is a known bug in Tru64 < 5.0 in which + * the server reports NFS_DATA_SYNC, but performs + * NFS_FILE_SYNC. We therefore implement this checking + * as a dprintk() in order to avoid filling syslog. + */ + static unsigned long complain; + + /* Note this will print the MDS for a DS write */ + if (time_before(complain, jiffies)) { + dprintk("NFS: faulty NFS server %s:" + " (committed = %d) != (stable = %d)\n", + NFS_SERVER(inode)->nfs_client->cl_hostname, + committed, hdr->args.stable); + complain = jiffies + 300 * HZ; + } } } @@ -1872,7 +1885,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) (long long)req_offset(req)); if (status < 0) { if (req->wb_page) { - trace_nfs_commit_error(req, status); + trace_nfs_commit_error(data->inode, req, + status); nfs_mapping_set_error(req->wb_page, status); nfs_inode_remove_request(req); } @@ -1892,7 +1906,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) /* We have a mismatch. Write the page again */ dprintk_cont(" mismatch\n"); nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&NFS_I(data->inode)->redirtied_pages); next: nfs_unlock_and_release_request(req); /* Latency breaker */ diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h index ba14d2f4b64f..4b7324458a94 100644 --- a/fs/nfsd/acl.h +++ b/fs/nfsd/acl.h @@ -38,6 +38,8 @@ struct nfs4_acl; struct svc_fh; struct svc_rqst; +struct nfsd_attrs; +enum nfs_ftype4; int nfs4_acl_bytes(int entries); int nfs4_acl_get_whotype(char *, u32); @@ -45,7 +47,7 @@ __be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who); int nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_acl **acl); -__be32 nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct nfs4_acl *acl); +__be32 nfsd4_acl_to_attr(enum nfs_ftype4 type, struct nfs4_acl *acl, + struct nfsd_attrs *attr); #endif /* LINUX_NFS4_ACL_H */ diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 9cb2d590c036..eeed4ae5b4ad 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -13,6 +13,7 @@ #include <linux/fsnotify_backend.h> #include <linux/fsnotify.h> #include <linux/seq_file.h> +#include <linux/rhashtable.h> #include "vfs.h" #include "nfsd.h" @@ -21,28 +22,19 @@ #include "filecache.h" #include "trace.h" -#define NFSDDBG_FACILITY NFSDDBG_FH - -/* FIXME: dynamically size this for the machine somehow? */ -#define NFSD_FILE_HASH_BITS 12 -#define NFSD_FILE_HASH_SIZE (1 << NFSD_FILE_HASH_BITS) #define NFSD_LAUNDRETTE_DELAY (2 * HZ) -#define NFSD_FILE_SHUTDOWN (1) -#define NFSD_FILE_LRU_THRESHOLD (4096UL) -#define NFSD_FILE_LRU_LIMIT (NFSD_FILE_LRU_THRESHOLD << 2) +#define NFSD_FILE_CACHE_UP (0) /* We only care about NFSD_MAY_READ/WRITE for this cache */ #define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE) -struct nfsd_fcache_bucket { - struct hlist_head nfb_head; - spinlock_t nfb_lock; - unsigned int nfb_count; - unsigned int nfb_maxcount; -}; - static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits); +static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions); +static DEFINE_PER_CPU(unsigned long, nfsd_file_releases); +static DEFINE_PER_CPU(unsigned long, nfsd_file_total_age); +static DEFINE_PER_CPU(unsigned long, nfsd_file_pages_flushed); +static DEFINE_PER_CPU(unsigned long, nfsd_file_evictions); struct nfsd_fcache_disposal { struct work_struct work; @@ -54,21 +46,146 @@ static struct workqueue_struct *nfsd_filecache_wq __read_mostly; static struct kmem_cache *nfsd_file_slab; static struct kmem_cache *nfsd_file_mark_slab; -static struct nfsd_fcache_bucket *nfsd_file_hashtbl; static struct list_lru nfsd_file_lru; -static long nfsd_file_lru_flags; +static unsigned long nfsd_file_flags; static struct fsnotify_group *nfsd_file_fsnotify_group; -static atomic_long_t nfsd_filecache_count; static struct delayed_work nfsd_filecache_laundrette; +static struct rhashtable nfsd_file_rhash_tbl + ____cacheline_aligned_in_smp; + +enum nfsd_file_lookup_type { + NFSD_FILE_KEY_INODE, + NFSD_FILE_KEY_FULL, +}; + +struct nfsd_file_lookup_key { + struct inode *inode; + struct net *net; + const struct cred *cred; + unsigned char need; + enum nfsd_file_lookup_type type; +}; + +/* + * The returned hash value is based solely on the address of an in-code + * inode, a pointer to a slab-allocated object. The entropy in such a + * pointer is concentrated in its middle bits. + */ +static u32 nfsd_file_inode_hash(const struct inode *inode, u32 seed) +{ + unsigned long ptr = (unsigned long)inode; + u32 k; + + k = ptr >> L1_CACHE_SHIFT; + k &= 0x00ffffff; + return jhash2(&k, 1, seed); +} + +/** + * nfsd_file_key_hashfn - Compute the hash value of a lookup key + * @data: key on which to compute the hash value + * @len: rhash table's key_len parameter (unused) + * @seed: rhash table's random seed of the day + * + * Return value: + * Computed 32-bit hash value + */ +static u32 nfsd_file_key_hashfn(const void *data, u32 len, u32 seed) +{ + const struct nfsd_file_lookup_key *key = data; + + return nfsd_file_inode_hash(key->inode, seed); +} + +/** + * nfsd_file_obj_hashfn - Compute the hash value of an nfsd_file + * @data: object on which to compute the hash value + * @len: rhash table's key_len parameter (unused) + * @seed: rhash table's random seed of the day + * + * Return value: + * Computed 32-bit hash value + */ +static u32 nfsd_file_obj_hashfn(const void *data, u32 len, u32 seed) +{ + const struct nfsd_file *nf = data; + + return nfsd_file_inode_hash(nf->nf_inode, seed); +} -static void nfsd_file_gc(void); +static bool +nfsd_match_cred(const struct cred *c1, const struct cred *c2) +{ + int i; + + if (!uid_eq(c1->fsuid, c2->fsuid)) + return false; + if (!gid_eq(c1->fsgid, c2->fsgid)) + return false; + if (c1->group_info == NULL || c2->group_info == NULL) + return c1->group_info == c2->group_info; + if (c1->group_info->ngroups != c2->group_info->ngroups) + return false; + for (i = 0; i < c1->group_info->ngroups; i++) { + if (!gid_eq(c1->group_info->gid[i], c2->group_info->gid[i])) + return false; + } + return true; +} + +/** + * nfsd_file_obj_cmpfn - Match a cache item against search criteria + * @arg: search criteria + * @ptr: cache item to check + * + * Return values: + * %0 - Item matches search criteria + * %1 - Item does not match search criteria + */ +static int nfsd_file_obj_cmpfn(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct nfsd_file_lookup_key *key = arg->key; + const struct nfsd_file *nf = ptr; + + switch (key->type) { + case NFSD_FILE_KEY_INODE: + if (nf->nf_inode != key->inode) + return 1; + break; + case NFSD_FILE_KEY_FULL: + if (nf->nf_inode != key->inode) + return 1; + if (nf->nf_may != key->need) + return 1; + if (nf->nf_net != key->net) + return 1; + if (!nfsd_match_cred(nf->nf_cred, key->cred)) + return 1; + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) + return 1; + break; + } + return 0; +} + +static const struct rhashtable_params nfsd_file_rhash_params = { + .key_len = sizeof_field(struct nfsd_file, nf_inode), + .key_offset = offsetof(struct nfsd_file, nf_inode), + .head_offset = offsetof(struct nfsd_file, nf_rhash), + .hashfn = nfsd_file_key_hashfn, + .obj_hashfn = nfsd_file_obj_hashfn, + .obj_cmpfn = nfsd_file_obj_cmpfn, + /* Reduce resizing churn on light workloads */ + .min_size = 512, /* buckets */ + .automatic_shrinking = true, +}; static void nfsd_file_schedule_laundrette(void) { - long count = atomic_long_read(&nfsd_filecache_count); - - if (count == 0 || test_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags)) + if ((atomic_read(&nfsd_file_rhash_tbl.nelems) == 0) || + test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0) return; queue_delayed_work(system_wq, &nfsd_filecache_laundrette, @@ -111,12 +228,11 @@ nfsd_file_mark_put(struct nfsd_file_mark *nfm) } static struct nfsd_file_mark * -nfsd_file_mark_find_or_create(struct nfsd_file *nf) +nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode) { int err; struct fsnotify_mark *mark; struct nfsd_file_mark *nfm = NULL, *new; - struct inode *inode = nf->nf_inode; do { fsnotify_group_lock(nfsd_file_fsnotify_group); @@ -167,31 +283,25 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf) } static struct nfsd_file * -nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval, - struct net *net) +nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may) { struct nfsd_file *nf; nf = kmem_cache_alloc(nfsd_file_slab, GFP_KERNEL); if (nf) { - INIT_HLIST_NODE(&nf->nf_node); INIT_LIST_HEAD(&nf->nf_lru); + nf->nf_birthtime = ktime_get(); nf->nf_file = NULL; nf->nf_cred = get_current_cred(); - nf->nf_net = net; + nf->nf_net = key->net; nf->nf_flags = 0; - nf->nf_inode = inode; - nf->nf_hashval = hashval; - refcount_set(&nf->nf_ref, 1); - nf->nf_may = may & NFSD_FILE_MAY_MASK; - if (may & NFSD_MAY_NOT_BREAK_LEASE) { - if (may & NFSD_MAY_WRITE) - __set_bit(NFSD_FILE_BREAK_WRITE, &nf->nf_flags); - if (may & NFSD_MAY_READ) - __set_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags); - } + __set_bit(NFSD_FILE_HASHED, &nf->nf_flags); + __set_bit(NFSD_FILE_PENDING, &nf->nf_flags); + nf->nf_inode = key->inode; + /* nf_ref is pre-incremented for hash table */ + refcount_set(&nf->nf_ref, 2); + nf->nf_may = key->need; nf->nf_mark = NULL; - trace_nfsd_file_alloc(nf); } return nf; } @@ -199,8 +309,12 @@ nfsd_file_alloc(struct inode *inode, unsigned int may, unsigned int hashval, static bool nfsd_file_free(struct nfsd_file *nf) { + s64 age = ktime_to_ms(ktime_sub(ktime_get(), nf->nf_birthtime)); bool flush = false; + this_cpu_inc(nfsd_file_releases); + this_cpu_add(nfsd_file_total_age, age); + trace_nfsd_file_put_final(nf); if (nf->nf_mark) nfsd_file_mark_put(nf->nf_mark); @@ -210,6 +324,14 @@ nfsd_file_free(struct nfsd_file *nf) fput(nf->nf_file); flush = true; } + + /* + * If this item is still linked via nf_lru, that's a bug. + * WARN and leak it to preserve system stability. + */ + if (WARN_ON_ONCE(!list_empty(&nf->nf_lru))) + return flush; + call_rcu(&nf->nf_rcu, nfsd_file_slab_free); return flush; } @@ -240,31 +362,44 @@ nfsd_file_check_write_error(struct nfsd_file *nf) static void nfsd_file_flush(struct nfsd_file *nf) { - if (nf->nf_file && vfs_fsync(nf->nf_file, 1) != 0) + struct file *file = nf->nf_file; + + if (!file || !(file->f_mode & FMODE_WRITE)) + return; + this_cpu_add(nfsd_file_pages_flushed, file->f_mapping->nrpages); + if (vfs_fsync(file, 1) != 0) nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); } -static void -nfsd_file_do_unhash(struct nfsd_file *nf) +static void nfsd_file_lru_add(struct nfsd_file *nf) { - lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); + set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); + if (list_lru_add(&nfsd_file_lru, &nf->nf_lru)) + trace_nfsd_file_lru_add(nf); +} +static void nfsd_file_lru_remove(struct nfsd_file *nf) +{ + if (list_lru_del(&nfsd_file_lru, &nf->nf_lru)) + trace_nfsd_file_lru_del(nf); +} + +static void +nfsd_file_hash_remove(struct nfsd_file *nf) +{ trace_nfsd_file_unhash(nf); if (nfsd_file_check_write_error(nf)) nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); - --nfsd_file_hashtbl[nf->nf_hashval].nfb_count; - hlist_del_rcu(&nf->nf_node); - atomic_long_dec(&nfsd_filecache_count); + rhashtable_remove_fast(&nfsd_file_rhash_tbl, &nf->nf_rhash, + nfsd_file_rhash_params); } static bool nfsd_file_unhash(struct nfsd_file *nf) { if (test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { - nfsd_file_do_unhash(nf); - if (!list_empty(&nf->nf_lru)) - list_lru_del(&nfsd_file_lru, &nf->nf_lru); + nfsd_file_hash_remove(nf); return true; } return false; @@ -274,17 +409,16 @@ nfsd_file_unhash(struct nfsd_file *nf) * Return true if the file was unhashed. */ static bool -nfsd_file_unhash_and_release_locked(struct nfsd_file *nf, struct list_head *dispose) +nfsd_file_unhash_and_dispose(struct nfsd_file *nf, struct list_head *dispose) { - lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); - - trace_nfsd_file_unhash_and_release_locked(nf); + trace_nfsd_file_unhash_and_dispose(nf); if (!nfsd_file_unhash(nf)) return false; /* keep final reference for nfsd_file_lru_dispose */ if (refcount_dec_not_one(&nf->nf_ref)) return true; + nfsd_file_lru_remove(nf); list_add(&nf->nf_lru, dispose); return true; } @@ -296,6 +430,7 @@ nfsd_file_put_noref(struct nfsd_file *nf) if (refcount_dec_and_test(&nf->nf_ref)) { WARN_ON(test_bit(NFSD_FILE_HASHED, &nf->nf_flags)); + nfsd_file_lru_remove(nf); nfsd_file_free(nf); } } @@ -305,7 +440,7 @@ nfsd_file_put(struct nfsd_file *nf) { might_sleep(); - set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); + nfsd_file_lru_add(nf); if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) { nfsd_file_flush(nf); nfsd_file_put_noref(nf); @@ -314,9 +449,24 @@ nfsd_file_put(struct nfsd_file *nf) nfsd_file_schedule_laundrette(); } else nfsd_file_put_noref(nf); +} - if (atomic_long_read(&nfsd_filecache_count) >= NFSD_FILE_LRU_LIMIT) - nfsd_file_gc(); +/** + * nfsd_file_close - Close an nfsd_file + * @nf: nfsd_file to close + * + * If this is the final reference for @nf, free it immediately. + * This reflects an on-the-wire CLOSE or DELEGRETURN into the + * VFS and exported filesystem. + */ +void nfsd_file_close(struct nfsd_file *nf) +{ + nfsd_file_put(nf); + if (refcount_dec_if_one(&nf->nf_ref)) { + nfsd_file_unhash(nf); + nfsd_file_lru_remove(nf); + nfsd_file_free(nf); + } } struct nfsd_file * @@ -334,7 +484,7 @@ nfsd_file_dispose_list(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - list_del(&nf->nf_lru); + list_del_init(&nf->nf_lru); nfsd_file_flush(nf); nfsd_file_put_noref(nf); } @@ -348,7 +498,7 @@ nfsd_file_dispose_list_sync(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - list_del(&nf->nf_lru); + list_del_init(&nf->nf_lru); nfsd_file_flush(nf); if (!refcount_dec_and_test(&nf->nf_ref)) continue; @@ -405,8 +555,19 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose) } } -/* +/** + * nfsd_file_lru_cb - Examine an entry on the LRU list + * @item: LRU entry to examine + * @lru: controlling LRU + * @lock: LRU list lock (unused) + * @arg: dispose list + * * Note this can deadlock with nfsd_file_cache_purge. + * + * Return values: + * %LRU_REMOVED: @item was removed from the LRU + * %LRU_ROTATE: @item is to be moved to the LRU tail + * %LRU_SKIP: @item cannot be evicted */ static enum lru_status nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, @@ -427,55 +588,65 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, * counter. Here we check the counter and then test and clear the flag. * That order is deliberate to ensure that we can do this locklessly. */ - if (refcount_read(&nf->nf_ref) > 1) - goto out_skip; + if (refcount_read(&nf->nf_ref) > 1) { + list_lru_isolate(lru, &nf->nf_lru); + trace_nfsd_file_gc_in_use(nf); + return LRU_REMOVED; + } /* * Don't throw out files that are still undergoing I/O or * that have uncleared errors pending. */ - if (nfsd_file_check_writeback(nf)) - goto out_skip; + if (nfsd_file_check_writeback(nf)) { + trace_nfsd_file_gc_writeback(nf); + return LRU_SKIP; + } - if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags)) - goto out_skip; + if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags)) { + trace_nfsd_file_gc_referenced(nf); + return LRU_ROTATE; + } - if (!test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) - goto out_skip; + if (!test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { + trace_nfsd_file_gc_hashed(nf); + return LRU_SKIP; + } list_lru_isolate_move(lru, &nf->nf_lru, head); + this_cpu_inc(nfsd_file_evictions); + trace_nfsd_file_gc_disposed(nf); return LRU_REMOVED; -out_skip: - return LRU_SKIP; } -static unsigned long -nfsd_file_lru_walk_list(struct shrink_control *sc) +/* + * Unhash items on @dispose immediately, then queue them on the + * disposal workqueue to finish releasing them in the background. + * + * cel: Note that between the time list_lru_shrink_walk runs and + * now, these items are in the hash table but marked unhashed. + * Why release these outside of lru_cb ? There's no lock ordering + * problem since lru_cb currently takes no lock. + */ +static void nfsd_file_gc_dispose_list(struct list_head *dispose) { - LIST_HEAD(head); struct nfsd_file *nf; - unsigned long ret; - if (sc) - ret = list_lru_shrink_walk(&nfsd_file_lru, sc, - nfsd_file_lru_cb, &head); - else - ret = list_lru_walk(&nfsd_file_lru, - nfsd_file_lru_cb, - &head, LONG_MAX); - list_for_each_entry(nf, &head, nf_lru) { - spin_lock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); - nfsd_file_do_unhash(nf); - spin_unlock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); - } - nfsd_file_dispose_list_delayed(&head); - return ret; + list_for_each_entry(nf, dispose, nf_lru) + nfsd_file_hash_remove(nf); + nfsd_file_dispose_list_delayed(dispose); } static void nfsd_file_gc(void) { - nfsd_file_lru_walk_list(NULL); + LIST_HEAD(dispose); + unsigned long ret; + + ret = list_lru_walk(&nfsd_file_lru, nfsd_file_lru_cb, + &dispose, list_lru_count(&nfsd_file_lru)); + trace_nfsd_file_gc_removed(ret, list_lru_count(&nfsd_file_lru)); + nfsd_file_gc_dispose_list(&dispose); } static void @@ -494,7 +665,14 @@ nfsd_file_lru_count(struct shrinker *s, struct shrink_control *sc) static unsigned long nfsd_file_lru_scan(struct shrinker *s, struct shrink_control *sc) { - return nfsd_file_lru_walk_list(sc); + LIST_HEAD(dispose); + unsigned long ret; + + ret = list_lru_shrink_walk(&nfsd_file_lru, sc, + nfsd_file_lru_cb, &dispose); + trace_nfsd_file_shrinker_removed(ret, list_lru_count(&nfsd_file_lru)); + nfsd_file_gc_dispose_list(&dispose); + return ret; } static struct shrinker nfsd_file_shrinker = { @@ -503,39 +681,47 @@ static struct shrinker nfsd_file_shrinker = { .seeks = 1, }; -static void -__nfsd_file_close_inode(struct inode *inode, unsigned int hashval, - struct list_head *dispose) +/* + * Find all cache items across all net namespaces that match @inode and + * move them to @dispose. The lookup is atomic wrt nfsd_file_acquire(). + */ +static unsigned int +__nfsd_file_close_inode(struct inode *inode, struct list_head *dispose) { - struct nfsd_file *nf; - struct hlist_node *tmp; + struct nfsd_file_lookup_key key = { + .type = NFSD_FILE_KEY_INODE, + .inode = inode, + }; + unsigned int count = 0; + struct nfsd_file *nf; - spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock); - hlist_for_each_entry_safe(nf, tmp, &nfsd_file_hashtbl[hashval].nfb_head, nf_node) { - if (inode == nf->nf_inode) - nfsd_file_unhash_and_release_locked(nf, dispose); - } - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); + rcu_read_lock(); + do { + nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, + nfsd_file_rhash_params); + if (!nf) + break; + nfsd_file_unhash_and_dispose(nf, dispose); + count++; + } while (1); + rcu_read_unlock(); + return count; } /** * nfsd_file_close_inode_sync - attempt to forcibly close a nfsd_file * @inode: inode of the file to attempt to remove * - * Walk the whole hash bucket, looking for any files that correspond to "inode". - * If any do, then unhash them and put the hashtable reference to them and - * destroy any that had their last reference put. Also ensure that any of the - * fputs also have their final __fput done as well. + * Unhash and put, then flush and fput all cache items associated with @inode. */ void nfsd_file_close_inode_sync(struct inode *inode) { - unsigned int hashval = (unsigned int)hash_long(inode->i_ino, - NFSD_FILE_HASH_BITS); LIST_HEAD(dispose); + unsigned int count; - __nfsd_file_close_inode(inode, hashval, &dispose); - trace_nfsd_file_close_inode_sync(inode, hashval, !list_empty(&dispose)); + count = __nfsd_file_close_inode(inode, &dispose); + trace_nfsd_file_close_inode_sync(inode, count); nfsd_file_dispose_list_sync(&dispose); } @@ -543,19 +729,16 @@ nfsd_file_close_inode_sync(struct inode *inode) * nfsd_file_close_inode - attempt a delayed close of a nfsd_file * @inode: inode of the file to attempt to remove * - * Walk the whole hash bucket, looking for any files that correspond to "inode". - * If any do, then unhash them and put the hashtable reference to them and - * destroy any that had their last reference put. + * Unhash and put all cache item associated with @inode. */ static void nfsd_file_close_inode(struct inode *inode) { - unsigned int hashval = (unsigned int)hash_long(inode->i_ino, - NFSD_FILE_HASH_BITS); LIST_HEAD(dispose); + unsigned int count; - __nfsd_file_close_inode(inode, hashval, &dispose); - trace_nfsd_file_close_inode(inode, hashval, !list_empty(&dispose)); + count = __nfsd_file_close_inode(inode, &dispose); + trace_nfsd_file_close_inode(inode, count); nfsd_file_dispose_list_delayed(&dispose); } @@ -630,25 +813,21 @@ static const struct fsnotify_ops nfsd_file_fsnotify_ops = { int nfsd_file_cache_init(void) { - int ret = -ENOMEM; - unsigned int i; + int ret; - clear_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags); - - if (nfsd_file_hashtbl) + lockdep_assert_held(&nfsd_mutex); + if (test_and_set_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) return 0; + ret = rhashtable_init(&nfsd_file_rhash_tbl, &nfsd_file_rhash_params); + if (ret) + return ret; + + ret = -ENOMEM; nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0); if (!nfsd_filecache_wq) goto out; - nfsd_file_hashtbl = kvcalloc(NFSD_FILE_HASH_SIZE, - sizeof(*nfsd_file_hashtbl), GFP_KERNEL); - if (!nfsd_file_hashtbl) { - pr_err("nfsd: unable to allocate nfsd_file_hashtbl\n"); - goto out_err; - } - nfsd_file_slab = kmem_cache_create("nfsd_file", sizeof(struct nfsd_file), 0, 0, NULL); if (!nfsd_file_slab) { @@ -670,7 +849,7 @@ nfsd_file_cache_init(void) goto out_err; } - ret = register_shrinker(&nfsd_file_shrinker); + ret = register_shrinker(&nfsd_file_shrinker, "nfsd-filecache"); if (ret) { pr_err("nfsd: failed to register nfsd_file_shrinker: %d\n", ret); goto out_lru; @@ -692,11 +871,6 @@ nfsd_file_cache_init(void) goto out_notifier; } - for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) { - INIT_HLIST_HEAD(&nfsd_file_hashtbl[i].nfb_head); - spin_lock_init(&nfsd_file_hashtbl[i].nfb_lock); - } - INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker); out: return ret; @@ -711,46 +885,47 @@ out_err: nfsd_file_slab = NULL; kmem_cache_destroy(nfsd_file_mark_slab); nfsd_file_mark_slab = NULL; - kvfree(nfsd_file_hashtbl); - nfsd_file_hashtbl = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; + rhashtable_destroy(&nfsd_file_rhash_tbl); goto out; } /* * Note this can deadlock with nfsd_file_lru_cb. */ -void -nfsd_file_cache_purge(struct net *net) +static void +__nfsd_file_cache_purge(struct net *net) { - unsigned int i; - struct nfsd_file *nf; - struct hlist_node *next; + struct rhashtable_iter iter; + struct nfsd_file *nf; LIST_HEAD(dispose); bool del; - if (!nfsd_file_hashtbl) - return; - - for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) { - struct nfsd_fcache_bucket *nfb = &nfsd_file_hashtbl[i]; + rhashtable_walk_enter(&nfsd_file_rhash_tbl, &iter); + do { + rhashtable_walk_start(&iter); - spin_lock(&nfb->nfb_lock); - hlist_for_each_entry_safe(nf, next, &nfb->nfb_head, nf_node) { + nf = rhashtable_walk_next(&iter); + while (!IS_ERR_OR_NULL(nf)) { if (net && nf->nf_net != net) continue; - del = nfsd_file_unhash_and_release_locked(nf, &dispose); + del = nfsd_file_unhash_and_dispose(nf, &dispose); /* * Deadlock detected! Something marked this entry as * unhased, but hasn't removed it from the hash list. */ WARN_ON_ONCE(!del); + + nf = rhashtable_walk_next(&iter); } - spin_unlock(&nfb->nfb_lock); - nfsd_file_dispose_list(&dispose); - } + + rhashtable_walk_stop(&iter); + } while (nf == ERR_PTR(-EAGAIN)); + rhashtable_walk_exit(&iter); + + nfsd_file_dispose_list(&dispose); } static struct nfsd_fcache_disposal * @@ -793,6 +968,19 @@ nfsd_file_cache_start_net(struct net *net) return nn->fcache_disposal ? 0 : -ENOMEM; } +/** + * nfsd_file_cache_purge - Remove all cache items associated with @net + * @net: target net namespace + * + */ +void +nfsd_file_cache_purge(struct net *net) +{ + lockdep_assert_held(&nfsd_mutex); + if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) + __nfsd_file_cache_purge(net); +} + void nfsd_file_cache_shutdown_net(struct net *net) { @@ -803,7 +991,11 @@ nfsd_file_cache_shutdown_net(struct net *net) void nfsd_file_cache_shutdown(void) { - set_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags); + int i; + + lockdep_assert_held(&nfsd_mutex); + if (test_and_clear_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0) + return; lease_unregister_notifier(&nfsd_file_lease_notifier); unregister_shrinker(&nfsd_file_shrinker); @@ -812,7 +1004,7 @@ nfsd_file_cache_shutdown(void) * calling nfsd_file_cache_purge */ cancel_delayed_work_sync(&nfsd_filecache_laundrette); - nfsd_file_cache_purge(NULL); + __nfsd_file_cache_purge(NULL); list_lru_destroy(&nfsd_file_lru); rcu_barrier(); fsnotify_put_group(nfsd_file_fsnotify_group); @@ -822,124 +1014,96 @@ nfsd_file_cache_shutdown(void) fsnotify_wait_marks_destroyed(); kmem_cache_destroy(nfsd_file_mark_slab); nfsd_file_mark_slab = NULL; - kvfree(nfsd_file_hashtbl); - nfsd_file_hashtbl = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; -} - -static bool -nfsd_match_cred(const struct cred *c1, const struct cred *c2) -{ - int i; - - if (!uid_eq(c1->fsuid, c2->fsuid)) - return false; - if (!gid_eq(c1->fsgid, c2->fsgid)) - return false; - if (c1->group_info == NULL || c2->group_info == NULL) - return c1->group_info == c2->group_info; - if (c1->group_info->ngroups != c2->group_info->ngroups) - return false; - for (i = 0; i < c1->group_info->ngroups; i++) { - if (!gid_eq(c1->group_info->gid[i], c2->group_info->gid[i])) - return false; - } - return true; -} - -static struct nfsd_file * -nfsd_file_find_locked(struct inode *inode, unsigned int may_flags, - unsigned int hashval, struct net *net) -{ - struct nfsd_file *nf; - unsigned char need = may_flags & NFSD_FILE_MAY_MASK; - - hlist_for_each_entry_rcu(nf, &nfsd_file_hashtbl[hashval].nfb_head, - nf_node, lockdep_is_held(&nfsd_file_hashtbl[hashval].nfb_lock)) { - if (nf->nf_may != need) - continue; - if (nf->nf_inode != inode) - continue; - if (nf->nf_net != net) - continue; - if (!nfsd_match_cred(nf->nf_cred, current_cred())) - continue; - if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) - continue; - if (nfsd_file_get(nf) != NULL) - return nf; + rhashtable_destroy(&nfsd_file_rhash_tbl); + + for_each_possible_cpu(i) { + per_cpu(nfsd_file_cache_hits, i) = 0; + per_cpu(nfsd_file_acquisitions, i) = 0; + per_cpu(nfsd_file_releases, i) = 0; + per_cpu(nfsd_file_total_age, i) = 0; + per_cpu(nfsd_file_pages_flushed, i) = 0; + per_cpu(nfsd_file_evictions, i) = 0; } - return NULL; } /** - * nfsd_file_is_cached - are there any cached open files for this fh? - * @inode: inode of the file to check + * nfsd_file_is_cached - are there any cached open files for this inode? + * @inode: inode to check + * + * The lookup matches inodes in all net namespaces and is atomic wrt + * nfsd_file_acquire(). * - * Scan the hashtable for open files that match this fh. Returns true if there - * are any, and false if not. + * Return values: + * %true: filecache contains at least one file matching this inode + * %false: filecache contains no files matching this inode */ bool nfsd_file_is_cached(struct inode *inode) { - bool ret = false; - struct nfsd_file *nf; - unsigned int hashval; - - hashval = (unsigned int)hash_long(inode->i_ino, NFSD_FILE_HASH_BITS); - - rcu_read_lock(); - hlist_for_each_entry_rcu(nf, &nfsd_file_hashtbl[hashval].nfb_head, - nf_node) { - if (inode == nf->nf_inode) { - ret = true; - break; - } - } - rcu_read_unlock(); - trace_nfsd_file_is_cached(inode, hashval, (int)ret); + struct nfsd_file_lookup_key key = { + .type = NFSD_FILE_KEY_INODE, + .inode = inode, + }; + bool ret = false; + + if (rhashtable_lookup_fast(&nfsd_file_rhash_tbl, &key, + nfsd_file_rhash_params) != NULL) + ret = true; + trace_nfsd_file_is_cached(inode, (int)ret); return ret; } static __be32 -nfsd_do_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, +nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf, bool open) { - __be32 status; - struct net *net = SVC_NET(rqstp); + struct nfsd_file_lookup_key key = { + .type = NFSD_FILE_KEY_FULL, + .need = may_flags & NFSD_FILE_MAY_MASK, + .net = SVC_NET(rqstp), + }; struct nfsd_file *nf, *new; - struct inode *inode; - unsigned int hashval; bool retry = true; + __be32 status; - /* FIXME: skip this if fh_dentry is already set? */ status = fh_verify(rqstp, fhp, S_IFREG, may_flags|NFSD_MAY_OWNER_OVERRIDE); if (status != nfs_ok) return status; + key.inode = d_inode(fhp->fh_dentry); + key.cred = get_current_cred(); - inode = d_inode(fhp->fh_dentry); - hashval = (unsigned int)hash_long(inode->i_ino, NFSD_FILE_HASH_BITS); retry: - rcu_read_lock(); - nf = nfsd_file_find_locked(inode, may_flags, hashval, net); - rcu_read_unlock(); + /* Avoid allocation if the item is already in cache */ + nf = rhashtable_lookup_fast(&nfsd_file_rhash_tbl, &key, + nfsd_file_rhash_params); + if (nf) + nf = nfsd_file_get(nf); if (nf) goto wait_for_construction; - new = nfsd_file_alloc(inode, may_flags, hashval, net); + new = nfsd_file_alloc(&key, may_flags); if (!new) { - trace_nfsd_file_acquire(rqstp, hashval, inode, may_flags, - NULL, nfserr_jukebox); - return nfserr_jukebox; + status = nfserr_jukebox; + goto out_status; } - spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock); - nf = nfsd_file_find_locked(inode, may_flags, hashval, net); - if (nf == NULL) + nf = rhashtable_lookup_get_insert_key(&nfsd_file_rhash_tbl, + &key, &new->nf_rhash, + nfsd_file_rhash_params); + if (!nf) { + nf = new; goto open_file; - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); + } + if (IS_ERR(nf)) + goto insert_err; + nf = nfsd_file_get(nf); + if (nf == NULL) { + nf = new; + goto open_file; + } nfsd_file_slab_free(&new->nf_rcu); wait_for_construction: @@ -947,6 +1111,7 @@ wait_for_construction: /* Did construction of this file fail? */ if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { + trace_nfsd_file_cons_err(rqstp, key.inode, may_flags, nf); if (!retry) { status = nfserr_jukebox; goto out; @@ -956,49 +1121,29 @@ wait_for_construction: goto retry; } + nfsd_file_lru_remove(nf); this_cpu_inc(nfsd_file_cache_hits); - if (!(may_flags & NFSD_MAY_NOT_BREAK_LEASE)) { - bool write = (may_flags & NFSD_MAY_WRITE); - - if (test_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags) || - (test_bit(NFSD_FILE_BREAK_WRITE, &nf->nf_flags) && write)) { - status = nfserrno(nfsd_open_break_lease( - file_inode(nf->nf_file), may_flags)); - if (status == nfs_ok) { - clear_bit(NFSD_FILE_BREAK_READ, &nf->nf_flags); - if (write) - clear_bit(NFSD_FILE_BREAK_WRITE, - &nf->nf_flags); - } - } - } + status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags)); out: if (status == nfs_ok) { + if (open) + this_cpu_inc(nfsd_file_acquisitions); *pnf = nf; } else { nfsd_file_put(nf); nf = NULL; } - trace_nfsd_file_acquire(rqstp, hashval, inode, may_flags, nf, status); +out_status: + put_cred(key.cred); + if (open) + trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); return status; + open_file: - nf = new; - /* Take reference for the hashtable */ - refcount_inc(&nf->nf_ref); - __set_bit(NFSD_FILE_HASHED, &nf->nf_flags); - __set_bit(NFSD_FILE_PENDING, &nf->nf_flags); - list_lru_add(&nfsd_file_lru, &nf->nf_lru); - hlist_add_head_rcu(&nf->nf_node, &nfsd_file_hashtbl[hashval].nfb_head); - ++nfsd_file_hashtbl[hashval].nfb_count; - nfsd_file_hashtbl[hashval].nfb_maxcount = max(nfsd_file_hashtbl[hashval].nfb_maxcount, - nfsd_file_hashtbl[hashval].nfb_count); - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); - if (atomic_long_inc_return(&nfsd_filecache_count) >= NFSD_FILE_LRU_THRESHOLD) - nfsd_file_gc(); - - nf->nf_mark = nfsd_file_mark_find_or_create(nf); + trace_nfsd_file_alloc(nf); + nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode); if (nf->nf_mark) { if (open) { status = nfsd_open_verified(rqstp, fhp, may_flags, @@ -1012,18 +1157,20 @@ open_file: * If construction failed, or we raced with a call to unlink() * then unhash. */ - if (status != nfs_ok || inode->i_nlink == 0) { - bool do_free; - spin_lock(&nfsd_file_hashtbl[hashval].nfb_lock); - do_free = nfsd_file_unhash(nf); - spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); - if (do_free) + if (status != nfs_ok || key.inode->i_nlink == 0) + if (nfsd_file_unhash(nf)) nfsd_file_put_noref(nf); - } clear_bit_unlock(NFSD_FILE_PENDING, &nf->nf_flags); smp_mb__after_atomic(); wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING); goto out; + +insert_err: + nfsd_file_slab_free(&new->nf_rcu); + trace_nfsd_file_insert_err(rqstp, key.inode, may_flags, PTR_ERR(nf)); + nf = NULL; + status = nfserr_jukebox; + goto out_status; } /** @@ -1040,7 +1187,7 @@ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_do_file_acquire(rqstp, fhp, may_flags, pnf, true); + return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true); } /** @@ -1057,7 +1204,7 @@ __be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_do_file_acquire(rqstp, fhp, may_flags, pnf, false); + return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, false); } /* @@ -1067,29 +1214,49 @@ nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp, */ static int nfsd_file_cache_stats_show(struct seq_file *m, void *v) { - unsigned int i, count = 0, longest = 0; - unsigned long hits = 0; + unsigned long releases = 0, pages_flushed = 0, evictions = 0; + unsigned long hits = 0, acquisitions = 0; + unsigned int i, count = 0, buckets = 0; + unsigned long lru = 0, total_age = 0; - /* - * No need for spinlocks here since we're not terribly interested in - * accuracy. We do take the nfsd_mutex simply to ensure that we - * don't end up racing with server shutdown - */ + /* Serialize with server shutdown */ mutex_lock(&nfsd_mutex); - if (nfsd_file_hashtbl) { - for (i = 0; i < NFSD_FILE_HASH_SIZE; i++) { - count += nfsd_file_hashtbl[i].nfb_count; - longest = max(longest, nfsd_file_hashtbl[i].nfb_count); - } + if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) { + struct bucket_table *tbl; + struct rhashtable *ht; + + lru = list_lru_count(&nfsd_file_lru); + + rcu_read_lock(); + ht = &nfsd_file_rhash_tbl; + count = atomic_read(&ht->nelems); + tbl = rht_dereference_rcu(ht->tbl, ht); + buckets = tbl->size; + rcu_read_unlock(); } mutex_unlock(&nfsd_mutex); - for_each_possible_cpu(i) + for_each_possible_cpu(i) { hits += per_cpu(nfsd_file_cache_hits, i); + acquisitions += per_cpu(nfsd_file_acquisitions, i); + releases += per_cpu(nfsd_file_releases, i); + total_age += per_cpu(nfsd_file_total_age, i); + evictions += per_cpu(nfsd_file_evictions, i); + pages_flushed += per_cpu(nfsd_file_pages_flushed, i); + } seq_printf(m, "total entries: %u\n", count); - seq_printf(m, "longest chain: %u\n", longest); + seq_printf(m, "hash buckets: %u\n", buckets); + seq_printf(m, "lru entries: %lu\n", lru); seq_printf(m, "cache hits: %lu\n", hits); + seq_printf(m, "acquisitions: %lu\n", acquisitions); + seq_printf(m, "releases: %lu\n", releases); + seq_printf(m, "evictions: %lu\n", evictions); + if (releases) + seq_printf(m, "mean age (ms): %ld\n", total_age / releases); + else + seq_printf(m, "mean age (ms): -\n"); + seq_printf(m, "pages flushed: %lu\n", pages_flushed); return 0; } diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index 1da0c79a5580..8e8c0c47d67d 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -29,7 +29,7 @@ struct nfsd_file_mark { * never be dereferenced, only used for comparison. */ struct nfsd_file { - struct hlist_node nf_node; + struct rhash_head nf_rhash; struct list_head nf_lru; struct rcu_head nf_rcu; struct file *nf_file; @@ -37,15 +37,13 @@ struct nfsd_file { struct net *nf_net; #define NFSD_FILE_HASHED (0) #define NFSD_FILE_PENDING (1) -#define NFSD_FILE_BREAK_READ (2) -#define NFSD_FILE_BREAK_WRITE (3) -#define NFSD_FILE_REFERENCED (4) +#define NFSD_FILE_REFERENCED (2) unsigned long nf_flags; - struct inode *nf_inode; - unsigned int nf_hashval; + struct inode *nf_inode; /* don't deref */ refcount_t nf_ref; unsigned char nf_may; struct nfsd_file_mark *nf_mark; + ktime_t nf_birthtime; }; int nfsd_file_cache_init(void); @@ -54,6 +52,7 @@ void nfsd_file_cache_shutdown(void); int nfsd_file_cache_start_net(struct net *net); void nfsd_file_cache_shutdown_net(struct net *net); void nfsd_file_put(struct nfsd_file *nf); +void nfsd_file_close(struct nfsd_file *nf); struct nfsd_file *nfsd_file_get(struct nfsd_file *nf); void nfsd_file_close_inode_sync(struct inode *inode); bool nfsd_file_is_cached(struct inode *inode); diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 1b1a962a1804..ffe17743cc74 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -189,6 +189,9 @@ struct nfsd_net { struct nfsd_fcache_disposal *fcache_disposal; siphash_key_t siphash_key; + + atomic_t nfs4_client_count; + int nfs4_max_clients; }; /* Simple check to find out if a given net was properly initialized */ diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index b5760801d377..9edd3c1a30fb 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -111,7 +111,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) if (error) goto out_errno; - fh_lock(fh); + inode_lock(inode); error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, argp->acl_access); @@ -122,7 +122,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) if (error) goto out_drop_lock; - fh_unlock(fh); + inode_unlock(inode); fh_drop_write(fh); @@ -136,7 +136,7 @@ out: return rpc_success; out_drop_lock: - fh_unlock(fh); + inode_unlock(inode); fh_drop_write(fh); out_errno: resp->status = nfserrno(error); diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 35b2ebda14da..9446c6743664 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -101,7 +101,7 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) if (error) goto out_errno; - fh_lock(fh); + inode_lock(inode); error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, argp->acl_access); @@ -111,7 +111,7 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) argp->acl_default); out_drop_lock: - fh_unlock(fh); + inode_unlock(inode); fh_drop_write(fh); out_errno: resp->status = nfserrno(error); diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 981a3a7a6e16..a41cca619338 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -67,12 +67,15 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp) { struct nfsd3_sattrargs *argp = rqstp->rq_argp; struct nfsd3_attrstat *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; dprintk("nfsd: SETATTR(3) %s\n", SVCFH_fmt(&argp->fh)); fh_copy(&resp->fh, &argp->fh); - resp->status = nfsd_setattr(rqstp, &resp->fh, &argp->attrs, + resp->status = nfsd_setattr(rqstp, &resp->fh, &attrs, argp->check_guard, argp->guardtime); return rpc_success; } @@ -233,6 +236,9 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, { struct iattr *iap = &argp->attrs; struct dentry *parent, *child; + struct nfsd_attrs attrs = { + .na_iattr = iap, + }; __u32 v_mtime, v_atime; struct inode *inode; __be32 status; @@ -254,7 +260,7 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err) return nfserrno(host_err); - fh_lock_nested(fhp, I_MUTEX_PARENT); + inode_lock_nested(inode, I_MUTEX_PARENT); child = lookup_one_len(argp->name, parent, argp->len); if (IS_ERR(child)) { @@ -312,11 +318,13 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (!IS_POSIXACL(inode)) iap->ia_mode &= ~current_umask(); + fh_fill_pre_attrs(fhp); host_err = vfs_create(&init_user_ns, inode, child, iap->ia_mode, true); if (host_err < 0) { status = nfserrno(host_err); goto out; } + fh_fill_post_attrs(fhp); /* A newly created file already has a file size of zero. */ if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0)) @@ -331,10 +339,10 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, } set_attr: - status = nfsd_create_setattr(rqstp, fhp, resfhp, iap); + status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs); out: - fh_unlock(fhp); + inode_unlock(inode); if (child && !IS_ERR(child)) dput(child); fh_drop_write(fhp); @@ -368,6 +376,9 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp) { struct nfsd3_createargs *argp = rqstp->rq_argp; struct nfsd3_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; dprintk("nfsd: MKDIR(3) %s %.*s\n", SVCFH_fmt(&argp->fh), @@ -378,8 +389,7 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp) fh_copy(&resp->dirfh, &argp->fh); fh_init(&resp->fh, NFS3_FHSIZE); resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, - &argp->attrs, S_IFDIR, 0, &resp->fh); - fh_unlock(&resp->dirfh); + &attrs, S_IFDIR, 0, &resp->fh); return rpc_success; } @@ -388,6 +398,9 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp) { struct nfsd3_symlinkargs *argp = rqstp->rq_argp; struct nfsd3_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; if (argp->tlen == 0) { resp->status = nfserr_inval; @@ -414,7 +427,7 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp) fh_copy(&resp->dirfh, &argp->ffh); fh_init(&resp->fh, NFS3_FHSIZE); resp->status = nfsd_symlink(rqstp, &resp->dirfh, argp->fname, - argp->flen, argp->tname, &resp->fh); + argp->flen, argp->tname, &attrs, &resp->fh); kfree(argp->tname); out: return rpc_success; @@ -428,6 +441,9 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) { struct nfsd3_mknodargs *argp = rqstp->rq_argp; struct nfsd3_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; int type; dev_t rdev = 0; @@ -453,8 +469,7 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) type = nfs3_ftypes[argp->ftype]; resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, - &argp->attrs, type, rdev, &resp->fh); - fh_unlock(&resp->dirfh); + &attrs, type, rdev, &resp->fh); out: return rpc_success; } @@ -477,7 +492,6 @@ nfsd3_proc_remove(struct svc_rqst *rqstp) fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_unlink(rqstp, &resp->fh, -S_IFDIR, argp->name, argp->len); - fh_unlock(&resp->fh); return rpc_success; } @@ -498,7 +512,6 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp) fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_unlink(rqstp, &resp->fh, S_IFDIR, argp->name, argp->len); - fh_unlock(&resp->fh); return rpc_success; } diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index eaa3a0cf38f1..bb8e2f6d7d03 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -751,58 +751,26 @@ out_estate: return ret; } -__be32 -nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct nfs4_acl *acl) +__be32 nfsd4_acl_to_attr(enum nfs_ftype4 type, struct nfs4_acl *acl, + struct nfsd_attrs *attr) { - __be32 error; int host_error; - struct dentry *dentry; - struct inode *inode; - struct posix_acl *pacl = NULL, *dpacl = NULL; unsigned int flags = 0; - /* Get inode */ - error = fh_verify(rqstp, fhp, 0, NFSD_MAY_SATTR); - if (error) - return error; - - dentry = fhp->fh_dentry; - inode = d_inode(dentry); + if (!acl) + return nfs_ok; - if (S_ISDIR(inode->i_mode)) + if (type == NF4DIR) flags = NFS4_ACL_DIR; - host_error = nfs4_acl_nfsv4_to_posix(acl, &pacl, &dpacl, flags); + host_error = nfs4_acl_nfsv4_to_posix(acl, &attr->na_pacl, + &attr->na_dpacl, flags); if (host_error == -EINVAL) return nfserr_attrnotsupp; - if (host_error < 0) - goto out_nfserr; - - fh_lock(fhp); - - host_error = set_posix_acl(&init_user_ns, inode, ACL_TYPE_ACCESS, pacl); - if (host_error < 0) - goto out_drop_lock; - - if (S_ISDIR(inode->i_mode)) { - host_error = set_posix_acl(&init_user_ns, inode, - ACL_TYPE_DEFAULT, dpacl); - } - -out_drop_lock: - fh_unlock(fhp); - - posix_acl_release(pacl); - posix_acl_release(dpacl); -out_nfserr: - if (host_error == -EOPNOTSUPP) - return nfserr_attrnotsupp; else return nfserrno(host_error); } - static short ace2type(struct nfs4_ace *ace) { diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 11f8715d92d6..4ce328209f61 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -679,7 +679,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, * case NFS4_OK: * write_response4 coa_resok4; * default: - * length4 coa_bytes_copied; + * length4 coa_bytes_copied; * }; * struct CB_OFFLOAD4args { * nfs_fh4 coa_fh; @@ -688,21 +688,22 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, * }; */ static void encode_offload_info4(struct xdr_stream *xdr, - __be32 nfserr, - const struct nfsd4_copy *cp) + const struct nfsd4_cb_offload *cbo) { __be32 *p; p = xdr_reserve_space(xdr, 4); - *p++ = nfserr; - if (!nfserr) { + *p = cbo->co_nfserr; + switch (cbo->co_nfserr) { + case nfs_ok: p = xdr_reserve_space(xdr, 4 + 8 + 4 + NFS4_VERIFIER_SIZE); p = xdr_encode_empty_array(p); - p = xdr_encode_hyper(p, cp->cp_res.wr_bytes_written); - *p++ = cpu_to_be32(cp->cp_res.wr_stable_how); - p = xdr_encode_opaque_fixed(p, cp->cp_res.wr_verifier.data, + p = xdr_encode_hyper(p, cbo->co_res.wr_bytes_written); + *p++ = cpu_to_be32(cbo->co_res.wr_stable_how); + p = xdr_encode_opaque_fixed(p, cbo->co_res.wr_verifier.data, NFS4_VERIFIER_SIZE); - } else { + break; + default: p = xdr_reserve_space(xdr, 8); /* We always return success if bytes were written */ p = xdr_encode_hyper(p, 0); @@ -710,18 +711,16 @@ static void encode_offload_info4(struct xdr_stream *xdr, } static void encode_cb_offload4args(struct xdr_stream *xdr, - __be32 nfserr, - const struct knfsd_fh *fh, - const struct nfsd4_copy *cp, + const struct nfsd4_cb_offload *cbo, struct nfs4_cb_compound_hdr *hdr) { __be32 *p; p = xdr_reserve_space(xdr, 4); - *p++ = cpu_to_be32(OP_CB_OFFLOAD); - encode_nfs_fh4(xdr, fh); - encode_stateid4(xdr, &cp->cp_res.cb_stateid); - encode_offload_info4(xdr, nfserr, cp); + *p = cpu_to_be32(OP_CB_OFFLOAD); + encode_nfs_fh4(xdr, &cbo->co_fh); + encode_stateid4(xdr, &cbo->co_res.cb_stateid); + encode_offload_info4(xdr, cbo); hdr->nops++; } @@ -731,8 +730,8 @@ static void nfs4_xdr_enc_cb_offload(struct rpc_rqst *req, const void *data) { const struct nfsd4_callback *cb = data; - const struct nfsd4_copy *cp = - container_of(cb, struct nfsd4_copy, cp_cb); + const struct nfsd4_cb_offload *cbo = + container_of(cb, struct nfsd4_cb_offload, co_cb); struct nfs4_cb_compound_hdr hdr = { .ident = 0, .minorversion = cb->cb_clp->cl_minorversion, @@ -740,7 +739,7 @@ static void nfs4_xdr_enc_cb_offload(struct rpc_rqst *req, encode_cb_compound4args(xdr, &hdr); encode_cb_sequence4args(xdr, cb, &hdr); - encode_cb_offload4args(xdr, cp->nfserr, &cp->fh, cp, &hdr); + encode_cb_offload4args(xdr, cbo, &hdr); encode_cb_nops(&hdr); } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 3895eb52d2b1..a72ab97f77ef 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -64,36 +64,6 @@ MODULE_PARM_DESC(nfsd4_ssc_umount_timeout, "idle msecs before unmount export from source server"); #endif -#ifdef CONFIG_NFSD_V4_SECURITY_LABEL -#include <linux/security.h> - -static inline void -nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval) -{ - struct inode *inode = d_inode(resfh->fh_dentry); - int status; - - inode_lock(inode); - status = security_inode_setsecctx(resfh->fh_dentry, - label->data, label->len); - inode_unlock(inode); - - if (status) - /* - * XXX: We should really fail the whole open, but we may - * already have created a new file, so it may be too - * late. For now this seems the least of evils: - */ - bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL; - - return; -} -#else -static inline void -nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval) -{ } -#endif - #define NFSDDBG_FACILITY NFSDDBG_PROC static u32 nfsd_attrmask[] = { @@ -158,26 +128,6 @@ is_create_with_attrs(struct nfsd4_open *open) || open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1); } -/* - * if error occurs when setting the acl, just clear the acl bit - * in the returned attr bitmap. - */ -static void -do_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct nfs4_acl *acl, u32 *bmval) -{ - __be32 status; - - status = nfsd4_set_nfs4_acl(rqstp, fhp, acl); - if (status) - /* - * We should probably fail the whole open at this point, - * but we've already created the file, so it's too late; - * So this seems the least of evils: - */ - bmval[0] &= ~FATTR4_WORD0_ACL; -} - static inline void fh_dup2(struct svc_fh *dst, struct svc_fh *src) { @@ -286,6 +236,10 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct svc_fh *resfhp, struct nfsd4_open *open) { struct iattr *iap = &open->op_iattr; + struct nfsd_attrs attrs = { + .na_iattr = iap, + .na_seclabel = &open->op_label, + }; struct dentry *parent, *child; __u32 v_mtime, v_atime; struct inode *inode; @@ -307,7 +261,10 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err) return nfserrno(host_err); - fh_lock_nested(fhp, I_MUTEX_PARENT); + if (is_create_with_attrs(open)) + nfsd4_acl_to_attr(NF4REG, open->op_acl, &attrs); + + inode_lock_nested(inode, I_MUTEX_PARENT); child = lookup_one_len(open->op_fname, parent, open->op_fnamelen); if (IS_ERR(child)) { @@ -345,6 +302,11 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (d_really_is_positive(child)) { status = nfs_ok; + /* NFSv4 protocol requires change attributes even though + * no change happened. + */ + fh_fill_both_attrs(fhp); + switch (open->op_createmode) { case NFS4_CREATE_UNCHECKED: if (!d_is_reg(child)) @@ -386,10 +348,12 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (!IS_POSIXACL(inode)) iap->ia_mode &= ~current_umask(); + fh_fill_pre_attrs(fhp); status = nfsd4_vfs_create(fhp, child, open); if (status != nfs_ok) goto out; open->op_created = true; + fh_fill_post_attrs(fhp); /* A newly created file already has a file size of zero. */ if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0)) @@ -404,10 +368,15 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, } set_attr: - status = nfsd_create_setattr(rqstp, fhp, resfhp, iap); + status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs); + if (attrs.na_labelerr) + open->op_bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + if (attrs.na_aclerr) + open->op_bmval[0] &= ~FATTR4_WORD0_ACL; out: - fh_unlock(fhp); + inode_unlock(inode); + nfsd_attrs_free(&attrs); if (child && !IS_ERR(child)) dput(child); fh_drop_write(fhp); @@ -447,9 +416,6 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru status = nfsd4_create_file(rqstp, current_fh, *resfh, open); current->fs->umask = 0; - if (!status && open->op_label.len) - nfsd4_security_inode_setsecctx(*resfh, &open->op_label, open->op_bmval); - /* * Following rfc 3530 14.2.16, and rfc 5661 18.16.4 * use the returned bitmask to indicate which attributes @@ -458,24 +424,21 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru if (nfsd4_create_is_exclusive(open->op_createmode) && status == 0) open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS | FATTR4_WORD1_TIME_MODIFY); - } else - /* - * Note this may exit with the parent still locked. - * We will hold the lock until nfsd4_open's final - * lookup, to prevent renames or unlinks until we've had - * a chance to an acquire a delegation if appropriate. - */ + } else { status = nfsd_lookup(rqstp, current_fh, open->op_fname, open->op_fnamelen, *resfh); + if (!status) + /* NFSv4 protocol requires change attributes even though + * no change happened. + */ + fh_fill_both_attrs(current_fh); + } if (status) goto out; status = nfsd_check_obj_isreg(*resfh); if (status) goto out; - if (is_create_with_attrs(open) && open->op_acl != NULL) - do_set_nfs4_acl(rqstp, *resfh, open->op_acl, open->op_bmval); - nfsd4_set_open_owner_reply_cache(cstate, open, *resfh); accmode = NFSD_MAY_NOP; if (open->op_created || @@ -547,6 +510,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, open->op_openowner); open->op_filp = NULL; + open->op_rqstp = rqstp; /* This check required by spec. */ if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL) @@ -630,9 +594,9 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } status = nfsd4_process_open2(rqstp, resfh, open); - WARN(status && open->op_created, - "nfsd4_process_open2 failed to open newly-created file! status=%u\n", - be32_to_cpu(status)); + if (status && open->op_created) + pr_warn("nfsd4_process_open2 failed to open newly-created file: status=%u\n", + be32_to_cpu(status)); if (reclaim && !status) nn->somebody_reclaimed = true; out: @@ -786,6 +750,10 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_create *create = &u->create; + struct nfsd_attrs attrs = { + .na_iattr = &create->cr_iattr, + .na_seclabel = &create->cr_label, + }; struct svc_fh resfh; __be32 status; dev_t rdev; @@ -801,12 +769,13 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) return status; + status = nfsd4_acl_to_attr(create->cr_type, create->cr_acl, &attrs); current->fs->umask = create->cr_umask; switch (create->cr_type) { case NF4LNK: status = nfsd_symlink(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - create->cr_data, &resfh); + create->cr_data, &attrs, &resfh); break; case NF4BLK: @@ -817,7 +786,7 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out_umask; status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFBLK, rdev, &resfh); + &attrs, S_IFBLK, rdev, &resfh); break; case NF4CHR: @@ -828,26 +797,26 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out_umask; status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr,S_IFCHR, rdev, &resfh); + &attrs, S_IFCHR, rdev, &resfh); break; case NF4SOCK: status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFSOCK, 0, &resfh); + &attrs, S_IFSOCK, 0, &resfh); break; case NF4FIFO: status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFIFO, 0, &resfh); + &attrs, S_IFIFO, 0, &resfh); break; case NF4DIR: create->cr_iattr.ia_valid &= ~ATTR_SIZE; status = nfsd_create(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, - &create->cr_iattr, S_IFDIR, 0, &resfh); + &attrs, S_IFDIR, 0, &resfh); break; default: @@ -857,20 +826,17 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - if (create->cr_label.len) - nfsd4_security_inode_setsecctx(&resfh, &create->cr_label, create->cr_bmval); - - if (create->cr_acl != NULL) - do_set_nfs4_acl(rqstp, &resfh, create->cr_acl, - create->cr_bmval); - - fh_unlock(&cstate->current_fh); + if (attrs.na_labelerr) + create->cr_bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + if (attrs.na_aclerr) + create->cr_bmval[0] &= ~FATTR4_WORD0_ACL; set_change_info(&create->cr_cinfo, &cstate->current_fh); fh_dup2(&cstate->current_fh, &resfh); out: fh_put(&resfh); out_umask: current->fs->umask = 0; + nfsd_attrs_free(&attrs); return status; } @@ -1043,10 +1009,8 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_grace; status = nfsd_unlink(rqstp, &cstate->current_fh, 0, remove->rm_name, remove->rm_namelen); - if (!status) { - fh_unlock(&cstate->current_fh); + if (!status) set_change_info(&remove->rm_cinfo, &cstate->current_fh); - } return status; } @@ -1086,7 +1050,6 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &exp, &dentry); if (err) return err; - fh_unlock(&cstate->current_fh); if (d_really_is_negative(dentry)) { exp_put(exp); err = nfserr_noent; @@ -1141,6 +1104,11 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_setattr *setattr = &u->setattr; + struct nfsd_attrs attrs = { + .na_iattr = &setattr->sa_iattr, + .na_seclabel = &setattr->sa_label, + }; + struct inode *inode; __be32 status = nfs_ok; int err; @@ -1163,19 +1131,18 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - if (setattr->sa_acl != NULL) - status = nfsd4_set_nfs4_acl(rqstp, &cstate->current_fh, - setattr->sa_acl); - if (status) - goto out; - if (setattr->sa_label.len) - status = nfsd4_set_nfs4_label(rqstp, &cstate->current_fh, - &setattr->sa_label); + inode = cstate->current_fh.fh_dentry->d_inode; + status = nfsd4_acl_to_attr(S_ISDIR(inode->i_mode) ? NF4DIR : NF4REG, + setattr->sa_acl, &attrs); + if (status) goto out; - status = nfsd_setattr(rqstp, &cstate->current_fh, &setattr->sa_iattr, + status = nfsd_setattr(rqstp, &cstate->current_fh, &attrs, 0, (time64_t)0); + if (!status) + status = nfserrno(attrs.na_labelerr); out: + nfsd_attrs_free(&attrs); fh_drop_write(&cstate->current_fh); return status; } @@ -1285,30 +1252,17 @@ out: return status; } -void nfs4_put_copy(struct nfsd4_copy *copy) +static void nfs4_put_copy(struct nfsd4_copy *copy) { if (!refcount_dec_and_test(©->refcount)) return; + kfree(copy->cp_src); kfree(copy); } -static bool -check_and_set_stop_copy(struct nfsd4_copy *copy) -{ - bool value; - - spin_lock(©->cp_clp->async_lock); - value = copy->stopped; - if (!copy->stopped) - copy->stopped = true; - spin_unlock(©->cp_clp->async_lock); - return value; -} - static void nfsd4_stop_copy(struct nfsd4_copy *copy) { - /* only 1 thread should stop the copy */ - if (!check_and_set_stop_copy(copy)) + if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, ©->cp_flags)) kthread_stop(copy->copy_task); nfs4_put_copy(copy); } @@ -1389,7 +1343,7 @@ try_again: return 0; } if (work) { - strncpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr)); + strlcpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr) - 1); refcount_set(&work->nsui_refcnt, 2); work->nsui_busy = true; list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list); @@ -1549,7 +1503,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, if (status) goto out; - status = nfsd4_interssc_connect(©->cp_src, rqstp, mount); + status = nfsd4_interssc_connect(copy->cp_src, rqstp, mount); if (status) goto out; @@ -1567,7 +1521,7 @@ out: } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, +nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, struct nfsd_file *dst) { bool found = false; @@ -1576,9 +1530,9 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd_net *nn = net_generic(dst->nf_net, nfsd_net_id); - nfs42_ssc_close(src->nf_file); + nfs42_ssc_close(filp); nfsd_file_put(dst); - fput(src->nf_file); + fput(filp); if (!nn) { mntput(ss_mnt); @@ -1621,7 +1575,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, +nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, struct nfsd_file *dst) { } @@ -1658,9 +1612,10 @@ nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst) static void nfsd4_cb_offload_release(struct nfsd4_callback *cb) { - struct nfsd4_copy *copy = container_of(cb, struct nfsd4_copy, cp_cb); + struct nfsd4_cb_offload *cbo = + container_of(cb, struct nfsd4_cb_offload, co_cb); - nfs4_put_copy(copy); + kfree(cbo); } static int nfsd4_cb_offload_done(struct nfsd4_callback *cb, @@ -1677,15 +1632,16 @@ static const struct nfsd4_callback_ops nfsd4_cb_offload_ops = { static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync) { copy->cp_res.wr_stable_how = - copy->committed ? NFS_FILE_SYNC : NFS_UNSTABLE; - copy->cp_synchronous = sync; + test_bit(NFSD4_COPY_F_COMMITTED, ©->cp_flags) ? + NFS_FILE_SYNC : NFS_UNSTABLE; + nfsd4_copy_set_sync(copy, sync); gen_boot_verifier(©->cp_res.wr_verifier, copy->cp_clp->net); } -static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy) +static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, + struct file *dst, + struct file *src) { - struct file *dst = copy->nf_dst->nf_file; - struct file *src = copy->nf_src->nf_file; errseq_t since; ssize_t bytes_copied = 0; u64 bytes_total = copy->cp_count; @@ -1707,26 +1663,29 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy) copy->cp_res.wr_bytes_written += bytes_copied; src_pos += bytes_copied; dst_pos += bytes_copied; - } while (bytes_total > 0 && !copy->cp_synchronous); + } while (bytes_total > 0 && nfsd4_copy_is_async(copy)); /* for a non-zero asynchronous copy do a commit of data */ - if (!copy->cp_synchronous && copy->cp_res.wr_bytes_written > 0) { + if (nfsd4_copy_is_async(copy) && copy->cp_res.wr_bytes_written > 0) { since = READ_ONCE(dst->f_wb_err); status = vfs_fsync_range(dst, copy->cp_dst_pos, copy->cp_res.wr_bytes_written, 0); if (!status) status = filemap_check_wb_err(dst->f_mapping, since); if (!status) - copy->committed = true; + set_bit(NFSD4_COPY_F_COMMITTED, ©->cp_flags); } return bytes_copied; } -static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync) +static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, + struct file *src, struct file *dst, + bool sync) { __be32 status; ssize_t bytes; - bytes = _nfsd_copy_file_range(copy); + bytes = _nfsd_copy_file_range(copy, dst, src); + /* for async copy, we ignore the error, client can always retry * to get the error */ @@ -1736,13 +1695,6 @@ static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync) nfsd4_init_copy_res(copy, sync); status = nfs_ok; } - - if (!copy->cp_intra) /* Inter server SSC */ - nfsd4_cleanup_inter_ssc(copy->ss_mnt, copy->nf_src, - copy->nf_dst); - else - nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst); - return status; } @@ -1751,17 +1703,17 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst) dst->cp_src_pos = src->cp_src_pos; dst->cp_dst_pos = src->cp_dst_pos; dst->cp_count = src->cp_count; - dst->cp_synchronous = src->cp_synchronous; + dst->cp_flags = src->cp_flags; memcpy(&dst->cp_res, &src->cp_res, sizeof(src->cp_res)); memcpy(&dst->fh, &src->fh, sizeof(src->fh)); dst->cp_clp = src->cp_clp; dst->nf_dst = nfsd_file_get(src->nf_dst); - dst->cp_intra = src->cp_intra; - if (src->cp_intra) /* for inter, file_src doesn't exist yet */ + /* for inter, nf_src doesn't exist yet */ + if (!nfsd4_ssc_is_inter(src)) dst->nf_src = nfsd_file_get(src->nf_src); memcpy(&dst->cp_stateid, &src->cp_stateid, sizeof(src->cp_stateid)); - memcpy(&dst->cp_src, &src->cp_src, sizeof(struct nl4_server)); + memcpy(dst->cp_src, src->cp_src, sizeof(struct nl4_server)); memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid)); memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh)); dst->ss_mnt = src->ss_mnt; @@ -1771,7 +1723,7 @@ static void cleanup_async_copy(struct nfsd4_copy *copy) { nfs4_free_copy_state(copy); nfsd_file_put(copy->nf_dst); - if (copy->cp_intra) + if (!nfsd4_ssc_is_inter(copy)) nfsd_file_put(copy->nf_src); spin_lock(©->cp_clp->async_lock); list_del(©->copies); @@ -1779,45 +1731,58 @@ static void cleanup_async_copy(struct nfsd4_copy *copy) nfs4_put_copy(copy); } +static void nfsd4_send_cb_offload(struct nfsd4_copy *copy, __be32 nfserr) +{ + struct nfsd4_cb_offload *cbo; + + cbo = kzalloc(sizeof(*cbo), GFP_KERNEL); + if (!cbo) + return; + + memcpy(&cbo->co_res, ©->cp_res, sizeof(copy->cp_res)); + memcpy(&cbo->co_fh, ©->fh, sizeof(copy->fh)); + cbo->co_nfserr = nfserr; + + nfsd4_init_cb(&cbo->co_cb, copy->cp_clp, &nfsd4_cb_offload_ops, + NFSPROC4_CLNT_CB_OFFLOAD); + trace_nfsd_cb_offload(copy->cp_clp, &cbo->co_res.cb_stateid, + &cbo->co_fh, copy->cp_count, nfserr); + nfsd4_run_cb(&cbo->co_cb); +} + +/** + * nfsd4_do_async_copy - kthread function for background server-side COPY + * @data: arguments for COPY operation + * + * Return values: + * %0: Copy operation is done. + */ static int nfsd4_do_async_copy(void *data) { struct nfsd4_copy *copy = (struct nfsd4_copy *)data; - struct nfsd4_copy *cb_copy; + __be32 nfserr; - if (!copy->cp_intra) { /* Inter server SSC */ - copy->nf_src = kzalloc(sizeof(struct nfsd_file), GFP_KERNEL); - if (!copy->nf_src) { - copy->nfserr = nfserr_serverfault; - nfsd4_interssc_disconnect(copy->ss_mnt); - goto do_callback; - } - copy->nf_src->nf_file = nfs42_ssc_open(copy->ss_mnt, ©->c_fh, - ©->stateid); - if (IS_ERR(copy->nf_src->nf_file)) { - copy->nfserr = nfserr_offload_denied; + if (nfsd4_ssc_is_inter(copy)) { + struct file *filp; + + filp = nfs42_ssc_open(copy->ss_mnt, ©->c_fh, + ©->stateid); + if (IS_ERR(filp)) { + nfserr = nfserr_offload_denied; nfsd4_interssc_disconnect(copy->ss_mnt); goto do_callback; } + nfserr = nfsd4_do_copy(copy, filp, copy->nf_dst->nf_file, + false); + nfsd4_cleanup_inter_ssc(copy->ss_mnt, filp, copy->nf_dst); + } else { + nfserr = nfsd4_do_copy(copy, copy->nf_src->nf_file, + copy->nf_dst->nf_file, false); + nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst); } - copy->nfserr = nfsd4_do_copy(copy, 0); do_callback: - cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); - if (!cb_copy) - goto out; - refcount_set(&cb_copy->refcount, 1); - memcpy(&cb_copy->cp_res, ©->cp_res, sizeof(copy->cp_res)); - cb_copy->cp_clp = copy->cp_clp; - cb_copy->nfserr = copy->nfserr; - memcpy(&cb_copy->fh, ©->fh, sizeof(copy->fh)); - nfsd4_init_cb(&cb_copy->cp_cb, cb_copy->cp_clp, - &nfsd4_cb_offload_ops, NFSPROC4_CLNT_CB_OFFLOAD); - trace_nfsd_cb_offload(copy->cp_clp, ©->cp_res.cb_stateid, - ©->fh, copy->cp_count, copy->nfserr); - nfsd4_run_cb(&cb_copy->cp_cb); -out: - if (!copy->cp_intra) - kfree(copy->nf_src); + nfsd4_send_cb_offload(copy, nfserr); cleanup_async_copy(copy); return 0; } @@ -1830,8 +1795,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd4_copy *async_copy = NULL; - if (!copy->cp_intra) { /* Inter server SSC */ - if (!inter_copy_offload_enable || copy->cp_synchronous) { + if (nfsd4_ssc_is_inter(copy)) { + if (!inter_copy_offload_enable || nfsd4_copy_is_sync(copy)) { status = nfserr_notsupp; goto out; } @@ -1848,13 +1813,16 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, copy->cp_clp = cstate->clp; memcpy(©->fh, &cstate->current_fh.fh_handle, sizeof(struct knfsd_fh)); - if (!copy->cp_synchronous) { + if (nfsd4_copy_is_async(copy)) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); status = nfserrno(-ENOMEM); async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!async_copy) goto out_err; + async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); + if (!async_copy->cp_src) + goto out_err; if (!nfs4_init_copy_state(nn, copy)) goto out_err; refcount_set(&async_copy->refcount, 1); @@ -1872,7 +1840,9 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, wake_up_process(async_copy->copy_task); status = nfs_ok; } else { - status = nfsd4_do_copy(copy, 1); + status = nfsd4_do_copy(copy, copy->nf_src->nf_file, + copy->nf_dst->nf_file, true); + nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst); } out: return status; @@ -1880,7 +1850,7 @@ out_err: if (async_copy) cleanup_async_copy(async_copy); status = nfserrno(-ENOMEM); - if (!copy->cp_intra) + if (nfsd4_ssc_is_inter(copy)) nfsd4_interssc_disconnect(copy->ss_mnt); goto out; } @@ -1953,9 +1923,9 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* For now, only return one server address in cpn_src, the * address used by the client to connect to this server. */ - cn->cpn_src.nl4_type = NL4_NETADDR; + cn->cpn_src->nl4_type = NL4_NETADDR; status = nfsd4_set_netaddr((struct sockaddr *)&rqstp->rq_daddr, - &cn->cpn_src.u.nl4_addr); + &cn->cpn_src->u.nl4_addr); WARN_ON_ONCE(status); if (status) { nfs4_put_cpntf_state(nn, cps); @@ -2609,7 +2579,7 @@ check_if_stalefh_allowed(struct nfsd4_compoundargs *args) return; } putfh = (struct nfsd4_putfh *)&saved_op->u; - if (!copy->cp_intra) + if (nfsd4_ssc_is_inter(copy)) putfh->no_verify = true; } } @@ -2711,7 +2681,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) if (op->opdesc->op_flags & OP_MODIFIES_SOMETHING) { /* * Don't execute this op if we couldn't encode a - * succesful reply: + * successful reply: */ u32 plen = op->opdesc->op_rsize_bop(rqstp, op); /* diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 9409a0dc1b76..c5d199d7e6b4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -820,9 +820,9 @@ static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag) swap(f2, fp->fi_fds[O_RDWR]); spin_unlock(&fp->fi_lock); if (f1) - nfsd_file_put(f1); + nfsd_file_close(f1); if (f2) - nfsd_file_put(f2); + nfsd_file_close(f2); } } @@ -1131,7 +1131,6 @@ static void block_delegations(struct knfsd_fh *fh) static struct nfs4_delegation * alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, - struct svc_fh *current_fh, struct nfs4_clnt_odstate *odstate) { struct nfs4_delegation *dp; @@ -1141,7 +1140,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, n = atomic_long_inc_return(&num_delegations); if (n < 0 || n > max_delegations) goto out_dec; - if (delegation_blocked(¤t_fh->fh_handle)) + if (delegation_blocked(&fp->fi_fhandle)) goto out_dec; dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg)); if (dp == NULL) @@ -2053,11 +2052,16 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) * This type of memory management is somewhat inefficient, but we use it * anyway since SETCLIENTID is not a common operation. */ -static struct nfs4_client *alloc_client(struct xdr_netobj name) +static struct nfs4_client *alloc_client(struct xdr_netobj name, + struct nfsd_net *nn) { struct nfs4_client *clp; int i; + if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) { + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + return NULL; + } clp = kmem_cache_zalloc(client_slab, GFP_KERNEL); if (clp == NULL) return NULL; @@ -2076,6 +2080,7 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) atomic_set(&clp->cl_rpc_users, 0); clp->cl_cb_state = NFSD4_CB_UNKNOWN; clp->cl_state = NFSD4_ACTIVE; + atomic_inc(&nn->nfs4_client_count); atomic_set(&clp->cl_delegs_in_recall, 0); INIT_LIST_HEAD(&clp->cl_idhash); INIT_LIST_HEAD(&clp->cl_openowners); @@ -2183,6 +2188,7 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp) static void __destroy_client(struct nfs4_client *clp) { + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); int i; struct nfs4_openowner *oo; struct nfs4_delegation *dp; @@ -2226,6 +2232,7 @@ __destroy_client(struct nfs4_client *clp) nfsd4_shutdown_callback(clp); if (clp->cl_cb_conn.cb_xprt) svc_xprt_put(clp->cl_cb_conn.cb_xprt); + atomic_add_unless(&nn->nfs4_client_count, -1, 0); free_client(clp); wake_up_all(&expiry_wq); } @@ -2564,7 +2571,7 @@ static void nfs4_show_fname(struct seq_file *s, struct nfsd_file *f) static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f) { - struct inode *inode = f->nf_inode; + struct inode *inode = file_inode(f->nf_file); seq_printf(s, "superblock: \"%02x:%02x:%ld\"", MAJOR(inode->i_sb->s_dev), @@ -2848,7 +2855,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name, struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct dentry *dentries[ARRAY_SIZE(client_files)]; - clp = alloc_client(name); + clp = alloc_client(name, nn); if (clp == NULL) return NULL; @@ -4330,6 +4337,27 @@ out: return -ENOMEM; } +void nfsd4_init_leases_net(struct nfsd_net *nn) +{ + struct sysinfo si; + u64 max_clients; + + nn->nfsd4_lease = 90; /* default lease time */ + nn->nfsd4_grace = 90; + nn->somebody_reclaimed = false; + nn->track_reclaim_completes = false; + nn->clverifier_counter = prandom_u32(); + nn->clientid_base = prandom_u32(); + nn->clientid_counter = nn->clientid_base + 1; + nn->s2s_cp_cl_id = nn->clientid_counter++; + + atomic_set(&nn->nfs4_client_count, 0); + si_meminfo(&si); + max_clients = (u64)si.totalram * si.mem_unit / (1024 * 1024 * 1024); + max_clients *= NFS4_CLIENTS_PER_GB; + nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB); +} + static void init_nfs4_replay(struct nfs4_replay *rp) { rp->rp_status = nfserr_serverfault; @@ -5032,11 +5060,14 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, .ia_valid = ATTR_SIZE, .ia_size = 0, }; + struct nfsd_attrs attrs = { + .na_iattr = &iattr, + }; if (!open->op_truncate) return 0; if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) return nfserr_inval; - return nfsd_setattr(rqstp, fh, &iattr, 0, (time64_t)0); + return nfsd_setattr(rqstp, fh, &attrs, 0, (time64_t)0); } static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, @@ -5104,6 +5135,7 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, goto out_put_access; nf->nf_file = open->op_filp; open->op_filp = NULL; + trace_nfsd_file_create(rqstp, access, nf); } spin_lock(&fp->fi_lock); @@ -5259,11 +5291,41 @@ static int nfsd4_check_conflicting_opens(struct nfs4_client *clp, return 0; } +/* + * It's possible that between opening the dentry and setting the delegation, + * that it has been renamed or unlinked. Redo the lookup to verify that this + * hasn't happened. + */ +static int +nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp, + struct svc_fh *parent) +{ + struct svc_export *exp; + struct dentry *child; + __be32 err; + + err = nfsd_lookup_dentry(open->op_rqstp, parent, + open->op_fname, open->op_fnamelen, + &exp, &child); + + if (err) + return -EAGAIN; + + dput(child); + if (child != file_dentry(fp->fi_deleg_file->nf_file)) + return -EAGAIN; + + return 0; +} + static struct nfs4_delegation * -nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, - struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate) +nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, + struct svc_fh *parent) { int status = 0; + struct nfs4_client *clp = stp->st_stid.sc_client; + struct nfs4_file *fp = stp->st_stid.sc_file; + struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate; struct nfs4_delegation *dp; struct nfsd_file *nf; struct file_lock *fl; @@ -5305,7 +5367,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, return ERR_PTR(status); status = -ENOMEM; - dp = alloc_init_deleg(clp, fp, fh, odstate); + dp = alloc_init_deleg(clp, fp, odstate); if (!dp) goto out_delegees; @@ -5318,6 +5380,13 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, locks_free_lock(fl); if (status) goto out_clnt_odstate; + + if (parent) { + status = nfsd4_verify_deleg_dentry(open, fp, parent); + if (status) + goto out_unlock; + } + status = nfsd4_check_conflicting_opens(clp, fp); if (status) goto out_unlock; @@ -5373,12 +5442,13 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) * proper support for them. */ static void -nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, - struct nfs4_ol_stateid *stp) +nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, + struct svc_fh *currentfh) { struct nfs4_delegation *dp; struct nfs4_openowner *oo = openowner(stp->st_stateowner); struct nfs4_client *clp = stp->st_stid.sc_client; + struct svc_fh *parent = NULL; int cb_up; int status = 0; @@ -5392,6 +5462,8 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, goto out_no_deleg; break; case NFS4_OPEN_CLAIM_NULL: + parent = currentfh; + fallthrough; case NFS4_OPEN_CLAIM_FH: /* * Let's not give out any delegations till everyone's @@ -5406,7 +5478,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, default: goto out_no_deleg; } - dp = nfs4_set_delegation(clp, fh, stp->st_stid.sc_file, stp->st_clnt_odstate); + dp = nfs4_set_delegation(open, stp, parent); if (IS_ERR(dp)) goto out_no_deleg; @@ -5538,7 +5610,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf * Attempt to hand out a delegation. No error return, because the * OPEN succeeds even if we fail. */ - nfs4_open_delegation(current_fh, open, stp); + nfs4_open_delegation(open, stp, &resp->cstate.current_fh); nodeleg: status = nfs_ok; trace_nfsd_open(&stp->st_stid.sc_stateid); @@ -5792,9 +5864,12 @@ static void nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist, struct laundry_time *lt) { + unsigned int maxreap, reapcnt = 0; struct list_head *pos, *next; struct nfs4_client *clp; + maxreap = (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) ? + NFSD_CLIENT_MAX_TRIM_PER_RUN : 0; INIT_LIST_HEAD(reaplist); spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { @@ -5805,14 +5880,15 @@ nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist, break; if (!atomic_read(&clp->cl_rpc_users)) clp->cl_state = NFSD4_COURTESY; - if (!client_has_state(clp) || - ktime_get_boottime_seconds() >= - (clp->cl_time + NFSD_COURTESY_CLIENT_TIMEOUT)) + if (!client_has_state(clp)) goto exp_client; - if (nfs4_anylock_blockers(clp)) { + if (!nfs4_anylock_blockers(clp)) + if (reapcnt >= maxreap) + continue; exp_client: - if (!mark_client_expired_locked(clp)) - list_add(&clp->cl_lru, reaplist); + if (!mark_client_expired_locked(clp)) { + list_add(&clp->cl_lru, reaplist); + reapcnt++; } } spin_unlock(&nn->client_lock); @@ -7321,21 +7397,22 @@ out: static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock) { struct nfsd_file *nf; + struct inode *inode; __be32 err; err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf); if (err) return err; - fh_lock(fhp); /* to block new leases till after test_lock: */ - err = nfserrno(nfsd_open_break_lease(fhp->fh_dentry->d_inode, - NFSD_MAY_READ)); + inode = fhp->fh_dentry->d_inode; + inode_lock(inode); /* to block new leases till after test_lock: */ + err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (err) goto out; lock->fl_file = nf->nf_file; err = nfserrno(vfs_test_lock(nf->nf_file, lock)); lock->fl_file = NULL; out: - fh_unlock(fhp); + inode_unlock(inode); nfsd_file_put(nf); return err; } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 2acea7792bb2..1e9690a061ec 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1810,7 +1810,7 @@ nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_sta for (i = 0; i < test_stateid->ts_num_ids; i++) { stateid = svcxdr_tmpalloc(argp, sizeof(*stateid)); if (!stateid) - return nfserrno(-ENOMEM); /* XXX: not jukebox? */ + return nfserr_jukebox; INIT_LIST_HEAD(&stateid->ts_id_list); list_add_tail(&stateid->ts_id_list, &test_stateid->ts_stateid_list); status = nfsd4_decode_stateid4(argp, &stateid->ts_id_stateid); @@ -1896,8 +1896,8 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) { + u32 consecutive, i, count, sync; struct nl4_server *ns_dummy; - u32 consecutive, i, count; __be32 status; status = nfsd4_decode_stateid4(argp, ©->cp_src_stateid); @@ -1915,25 +1915,28 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) /* ca_consecutive: we always do consecutive copies */ if (xdr_stream_decode_u32(argp->xdr, &consecutive) < 0) return nfserr_bad_xdr; - if (xdr_stream_decode_u32(argp->xdr, ©->cp_synchronous) < 0) + if (xdr_stream_decode_bool(argp->xdr, &sync) < 0) return nfserr_bad_xdr; + nfsd4_copy_set_sync(copy, sync); if (xdr_stream_decode_u32(argp->xdr, &count) < 0) return nfserr_bad_xdr; - copy->cp_intra = false; + copy->cp_src = svcxdr_tmpalloc(argp, sizeof(*copy->cp_src)); + if (copy->cp_src == NULL) + return nfserr_jukebox; if (count == 0) { /* intra-server copy */ - copy->cp_intra = true; + __set_bit(NFSD4_COPY_F_INTRA, ©->cp_flags); return nfs_ok; } /* decode all the supplied server addresses but use only the first */ - status = nfsd4_decode_nl4_server(argp, ©->cp_src); + status = nfsd4_decode_nl4_server(argp, copy->cp_src); if (status) return status; ns_dummy = kmalloc(sizeof(struct nl4_server), GFP_KERNEL); if (ns_dummy == NULL) - return nfserrno(-ENOMEM); /* XXX: jukebox? */ + return nfserr_jukebox; for (i = 0; i < count - 1; i++) { status = nfsd4_decode_nl4_server(argp, ns_dummy); if (status) { @@ -1952,10 +1955,17 @@ nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp, { __be32 status; + cn->cpn_src = svcxdr_tmpalloc(argp, sizeof(*cn->cpn_src)); + if (cn->cpn_src == NULL) + return nfserr_jukebox; + cn->cpn_dst = svcxdr_tmpalloc(argp, sizeof(*cn->cpn_dst)); + if (cn->cpn_dst == NULL) + return nfserr_jukebox; + status = nfsd4_decode_stateid4(argp, &cn->cpn_src_stateid); if (status) return status; - return nfsd4_decode_nl4_server(argp, &cn->cpn_dst); + return nfsd4_decode_nl4_server(argp, cn->cpn_dst); } static __be32 @@ -2828,10 +2838,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, struct kstat stat; struct svc_fh *tempfh = NULL; struct kstatfs statfs; - __be32 *p; + __be32 *p, *attrlen_p; int starting_len = xdr->buf->len; int attrlen_offset; - __be32 attrlen; u32 dummy; u64 dummy64; u32 rdattr_err = 0; @@ -2919,10 +2928,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, goto out; attrlen_offset = xdr->buf->len; - p = xdr_reserve_space(xdr, 4); - if (!p) + attrlen_p = xdr_reserve_space(xdr, XDR_UNIT); + if (!attrlen_p) goto out_resource; - p++; /* to be backfilled later */ if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { u32 supp[3]; @@ -3344,8 +3352,7 @@ out_acl: *p++ = cpu_to_be32(err == 0); } - attrlen = htonl(xdr->buf->len - attrlen_offset - 4); - write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4); + *attrlen_p = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT); status = nfs_ok; out: @@ -3882,16 +3889,15 @@ static __be32 nfsd4_encode_splice_read( struct xdr_stream *xdr = resp->xdr; struct xdr_buf *buf = xdr->buf; int status, space_left; - u32 eof; __be32 nfserr; - __be32 *p = xdr->p - 2; /* Make sure there will be room for padding if needed */ if (xdr->end - xdr->p < 1) return nfserr_resource; nfserr = nfsd_splice_read(read->rd_rqstp, read->rd_fhp, - file, read->rd_offset, &maxcount, &eof); + file, read->rd_offset, &maxcount, + &read->rd_eof); read->rd_length = maxcount; if (nfserr) goto out_err; @@ -3902,9 +3908,6 @@ static __be32 nfsd4_encode_splice_read( goto out_err; } - *(p++) = htonl(eof); - *(p++) = htonl(maxcount); - buf->page_len = maxcount; buf->len += maxcount; xdr->page_ptr += (buf->page_base + maxcount + PAGE_SIZE - 1) @@ -3946,11 +3949,9 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, struct file *file, unsigned long maxcount) { struct xdr_stream *xdr = resp->xdr; - u32 eof; - int starting_len = xdr->buf->len - 8; + unsigned int starting_len = xdr->buf->len; + __be32 zero = xdr_zero; __be32 nfserr; - __be32 tmp; - int pad; read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, maxcount); if (read->rd_vlen < 0) @@ -3958,31 +3959,24 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset, resp->rqstp->rq_vec, read->rd_vlen, &maxcount, - &eof); + &read->rd_eof); read->rd_length = maxcount; if (nfserr) return nfserr; - if (svc_encode_result_payload(resp->rqstp, starting_len + 8, maxcount)) + if (svc_encode_result_payload(resp->rqstp, starting_len, maxcount)) return nfserr_io; - xdr_truncate_encode(xdr, starting_len + 8 + xdr_align_size(maxcount)); - - tmp = htonl(eof); - write_bytes_to_xdr_buf(xdr->buf, starting_len , &tmp, 4); - tmp = htonl(maxcount); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); - - tmp = xdr_zero; - pad = (maxcount&3) ? 4 - (maxcount&3) : 0; - write_bytes_to_xdr_buf(xdr->buf, starting_len + 8 + maxcount, - &tmp, pad); - return 0; + xdr_truncate_encode(xdr, starting_len + xdr_align_size(maxcount)); + write_bytes_to_xdr_buf(xdr->buf, starting_len + maxcount, &zero, + xdr_pad_size(maxcount)); + return nfs_ok; } static __be32 nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_read *read) { + bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); unsigned long maxcount; struct xdr_stream *xdr = resp->xdr; struct file *file; @@ -3995,11 +3989,10 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */ if (!p) { - WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)); + WARN_ON_ONCE(splice_ok); return nfserr_resource; } - if (resp->xdr->buf->page_len && - test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) { + if (resp->xdr->buf->page_len && splice_ok) { WARN_ON_ONCE(1); return nfserr_resource; } @@ -4008,31 +4001,30 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, maxcount = min_t(unsigned long, read->rd_length, (xdr->buf->buflen - xdr->buf->len)); - if (file->f_op->splice_read && - test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) + if (file->f_op->splice_read && splice_ok) nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount); else nfserr = nfsd4_encode_readv(resp, read, file, maxcount); - - if (nfserr) + if (nfserr) { xdr_truncate_encode(xdr, starting_len); + return nfserr; + } - return nfserr; + p = xdr_encode_bool(p, read->rd_eof); + *p = cpu_to_be32(read->rd_length); + return nfs_ok; } static __be32 nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink) { - int maxcount; - __be32 wire_count; - int zero = 0; + __be32 *p, *maxcount_p, zero = xdr_zero; struct xdr_stream *xdr = resp->xdr; int length_offset = xdr->buf->len; - int status; - __be32 *p; + int maxcount, status; - p = xdr_reserve_space(xdr, 4); - if (!p) + maxcount_p = xdr_reserve_space(xdr, XDR_UNIT); + if (!maxcount_p) return nfserr_resource; maxcount = PAGE_SIZE; @@ -4057,14 +4049,11 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd nfserr = nfserrno(status); goto out_err; } - - wire_count = htonl(maxcount); - write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, 4); - xdr_truncate_encode(xdr, length_offset + 4 + ALIGN(maxcount, 4)); - if (maxcount & 3) - write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, - &zero, 4 - (maxcount&3)); - return 0; + *maxcount_p = cpu_to_be32(maxcount); + xdr_truncate_encode(xdr, length_offset + 4 + xdr_align_size(maxcount)); + write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, &zero, + xdr_pad_size(maxcount)); + return nfs_ok; out_err: xdr_truncate_encode(xdr, length_offset); @@ -4715,13 +4704,13 @@ nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, __be32 *p; nfserr = nfsd42_encode_write_res(resp, ©->cp_res, - !!copy->cp_synchronous); + nfsd4_copy_is_sync(copy)); if (nfserr) return nfserr; p = xdr_reserve_space(resp->xdr, 4 + 4); *p++ = xdr_one; /* cr_consecutive */ - *p++ = cpu_to_be32(copy->cp_synchronous); + *p = nfsd4_copy_is_sync(copy) ? xdr_one : xdr_zero; return 0; } @@ -4919,7 +4908,8 @@ nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, *p++ = cpu_to_be32(1); - return nfsd42_encode_nl4_server(resp, &cn->cpn_src); + nfserr = nfsd42_encode_nl4_server(resp, cn->cpn_src); + return nfserr; } static __be32 @@ -5373,8 +5363,7 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) so->so_replay.rp_buf, len); } status: - /* Note that op->status is already in network byte order: */ - write_bytes_to_xdr_buf(xdr->buf, post_err_offset - 4, &op->status, 4); + *p = op->status; } /* diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 7da88bdc0d6c..9b31e1103e7b 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -176,7 +176,8 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) nn->nfsd_reply_cache_shrinker.scan_objects = nfsd_reply_cache_scan; nn->nfsd_reply_cache_shrinker.count_objects = nfsd_reply_cache_count; nn->nfsd_reply_cache_shrinker.seeks = 1; - status = register_shrinker(&nn->nfsd_reply_cache_shrinker); + status = register_shrinker(&nn->nfsd_reply_cache_shrinker, + "nfsd-reply:%s", nn->nfsd_name); if (status) goto out_stats_destroy; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 0621c2faf242..917fa1892fd2 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -25,6 +25,7 @@ #include "state.h" #include "netns.h" #include "pnfs.h" +#include "filecache.h" /* * We have a single directory with several nodes in it. @@ -45,6 +46,7 @@ enum { NFSD_Ports, NFSD_MaxBlkSize, NFSD_MaxConnections, + NFSD_Filecache, NFSD_SupportedEnctypes, /* * The below MUST come last. Otherwise we leave a hole in nfsd_files[] @@ -229,6 +231,13 @@ static const struct file_operations reply_cache_stats_operations = { .release = single_release, }; +static const struct file_operations filecache_ops = { + .open = nfsd_file_cache_stats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + /*----------------------------------------------------------------------------*/ /* * payload - write methods @@ -633,7 +642,6 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) } /* Now write current state into reply buffer */ - len = 0; sep = ""; remaining = SIMPLE_TRANSACTION_LIMIT; for (num=2 ; num <= 4 ; num++) { @@ -1371,6 +1379,7 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) [NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_MaxConnections] = {"max_connections", &transaction_ops, S_IWUSR|S_IRUGO}, + [NFSD_Filecache] = {"filecache", &filecache_ops, S_IRUGO}, #if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE) [NFSD_SupportedEnctypes] = {"supported_krb5_enctypes", &supported_enctypes_ops, S_IRUGO}, #endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ @@ -1475,14 +1484,7 @@ static __net_init int nfsd_init_net(struct net *net) retval = nfsd_reply_cache_init(nn); if (retval) goto out_drc_error; - nn->nfsd4_lease = 90; /* default lease time */ - nn->nfsd4_grace = 90; - nn->somebody_reclaimed = false; - nn->track_reclaim_completes = false; - nn->clverifier_counter = prandom_u32(); - nn->clientid_base = prandom_u32(); - nn->clientid_counter = nn->clientid_base + 1; - nn->s2s_cp_cl_id = nn->clientid_counter++; + nfsd4_init_leases_net(nn); get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key)); seqlock_init(&nn->writeverf_lock); @@ -1517,7 +1519,6 @@ static struct pernet_operations nfsd_net_ops = { static int __init init_nfsd(void) { int retval; - printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n"); retval = nfsd4_init_slabs(); if (retval) diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 9a8b09afc173..57a468ed85c3 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -341,6 +341,8 @@ void nfsd_lockd_shutdown(void); #define NFSD_LAUNDROMAT_MINTIMEOUT 1 /* seconds */ #define NFSD_COURTESY_CLIENT_TIMEOUT (24 * 60 * 60) /* seconds */ +#define NFSD_CLIENT_MAX_TRIM_PER_RUN 128 +#define NFS4_CLIENTS_PER_GB 1024 /* * The following attributes are currently not supported by the NFSv4 server: @@ -496,12 +498,16 @@ extern void unregister_cld_notifier(void); extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn); #endif +extern void nfsd4_init_leases_net(struct nfsd_net *nn); + #else /* CONFIG_NFSD_V4 */ static inline int nfsd4_is_junction(struct dentry *dentry) { return 0; } +static inline void nfsd4_init_leases_net(struct nfsd_net *nn) {}; + #define register_cld_notifier() 0 #define unregister_cld_notifier() do { } while(0) diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index c29baa03dfaf..a5b71526cee0 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -331,8 +331,6 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) struct dentry *dentry; __be32 error; - dprintk("nfsd: fh_verify(%s)\n", SVCFH_fmt(fhp)); - if (!fhp->fh_dentry) { error = nfsd_set_fh_dentry(rqstp, fhp); if (error) @@ -340,6 +338,9 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) } dentry = fhp->fh_dentry; exp = fhp->fh_export; + + trace_nfsd_fh_verify(rqstp, fhp, type, access); + /* * We still have to do all these permission checks, even when * fh_dentry is already set: @@ -548,7 +549,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, if (ref_fh == fhp) fh_put(ref_fh); - if (fhp->fh_locked || fhp->fh_dentry) { + if (fhp->fh_dentry) { printk(KERN_ERR "fh_compose: fh %pd2 not initialized!\n", dentry); } @@ -671,6 +672,25 @@ void fh_fill_post_attrs(struct svc_fh *fhp) nfsd4_change_attribute(&fhp->fh_post_attr, inode); } +/** + * fh_fill_both_attrs - Fill pre-op and post-op attributes + * @fhp: file handle to be updated + * + * This is used when the directory wasn't changed, but wcc attributes + * are needed anyway. + */ +void fh_fill_both_attrs(struct svc_fh *fhp) +{ + fh_fill_post_attrs(fhp); + if (!fhp->fh_post_saved) + return; + fhp->fh_pre_change = fhp->fh_post_change; + fhp->fh_pre_mtime = fhp->fh_post_attr.mtime; + fhp->fh_pre_ctime = fhp->fh_post_attr.ctime; + fhp->fh_pre_size = fhp->fh_post_attr.size; + fhp->fh_pre_saved = true; +} + /* * Release a file handle. */ @@ -680,7 +700,6 @@ fh_put(struct svc_fh *fhp) struct dentry * dentry = fhp->fh_dentry; struct svc_export * exp = fhp->fh_export; if (dentry) { - fh_unlock(fhp); fhp->fh_dentry = NULL; dput(dentry); fh_clear_pre_post_attrs(fhp); diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index fb9d358a267e..c3ae6414fc5c 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -81,7 +81,6 @@ typedef struct svc_fh { struct dentry * fh_dentry; /* validated dentry */ struct svc_export * fh_export; /* export pointer */ - bool fh_locked; /* inode locked by us */ bool fh_want_write; /* remount protection taken */ bool fh_no_wcc; /* no wcc data needed */ bool fh_no_atomic_attr; @@ -93,7 +92,7 @@ typedef struct svc_fh { bool fh_post_saved; /* post-op attrs saved */ bool fh_pre_saved; /* pre-op attrs saved */ - /* Pre-op attributes saved during fh_lock */ + /* Pre-op attributes saved when inode is locked */ __u64 fh_pre_size; /* size before operation */ struct timespec64 fh_pre_mtime; /* mtime before oper */ struct timespec64 fh_pre_ctime; /* ctime before oper */ @@ -103,7 +102,7 @@ typedef struct svc_fh { */ u64 fh_pre_change; - /* Post-op attributes saved in fh_unlock */ + /* Post-op attributes saved in fh_fill_post_attrs() */ struct kstat fh_post_attr; /* full attrs after operation */ u64 fh_post_change; /* nfsv4 change; see above */ } svc_fh; @@ -223,8 +222,8 @@ void fh_put(struct svc_fh *); static __inline__ struct svc_fh * fh_copy(struct svc_fh *dst, struct svc_fh *src) { - WARN_ON(src->fh_dentry || src->fh_locked); - + WARN_ON(src->fh_dentry); + *dst = *src; return dst; } @@ -322,52 +321,5 @@ static inline u64 nfsd4_change_attribute(struct kstat *stat, extern void fh_fill_pre_attrs(struct svc_fh *fhp); extern void fh_fill_post_attrs(struct svc_fh *fhp); - - -/* - * Lock a file handle/inode - * NOTE: both fh_lock and fh_unlock are done "by hand" in - * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once - * so, any changes here should be reflected there. - */ - -static inline void -fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) -{ - struct dentry *dentry = fhp->fh_dentry; - struct inode *inode; - - BUG_ON(!dentry); - - if (fhp->fh_locked) { - printk(KERN_WARNING "fh_lock: %pd2 already locked!\n", - dentry); - return; - } - - inode = d_inode(dentry); - inode_lock_nested(inode, subclass); - fh_fill_pre_attrs(fhp); - fhp->fh_locked = true; -} - -static inline void -fh_lock(struct svc_fh *fhp) -{ - fh_lock_nested(fhp, I_MUTEX_NORMAL); -} - -/* - * Unlock a file handle/inode - */ -static inline void -fh_unlock(struct svc_fh *fhp) -{ - if (fhp->fh_locked) { - fh_fill_post_attrs(fhp); - inode_unlock(d_inode(fhp->fh_dentry)); - fhp->fh_locked = false; - } -} - +extern void fh_fill_both_attrs(struct svc_fh *fhp); #endif /* _LINUX_NFSD_NFSFH_H */ diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index fcdab8a8a41f..7381972f1677 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -51,6 +51,9 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) struct nfsd_sattrargs *argp = rqstp->rq_argp; struct nfsd_attrstat *resp = rqstp->rq_resp; struct iattr *iap = &argp->attrs; + struct nfsd_attrs attrs = { + .na_iattr = iap, + }; struct svc_fh *fhp; dprintk("nfsd: SETATTR %s, valid=%x, size=%ld\n", @@ -100,7 +103,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) } } - resp->status = nfsd_setattr(rqstp, fhp, iap, 0, (time64_t)0); + resp->status = nfsd_setattr(rqstp, fhp, &attrs, 0, (time64_t)0); if (resp->status != nfs_ok) goto out; @@ -260,6 +263,9 @@ nfsd_proc_create(struct svc_rqst *rqstp) svc_fh *dirfhp = &argp->fh; svc_fh *newfhp = &resp->fh; struct iattr *attr = &argp->attrs; + struct nfsd_attrs attrs = { + .na_iattr = attr, + }; struct inode *inode; struct dentry *dchild; int type, mode; @@ -285,7 +291,7 @@ nfsd_proc_create(struct svc_rqst *rqstp) goto done; } - fh_lock_nested(dirfhp, I_MUTEX_PARENT); + inode_lock_nested(dirfhp->fh_dentry->d_inode, I_MUTEX_PARENT); dchild = lookup_one_len(argp->name, dirfhp->fh_dentry, argp->len); if (IS_ERR(dchild)) { resp->status = nfserrno(PTR_ERR(dchild)); @@ -385,7 +391,7 @@ nfsd_proc_create(struct svc_rqst *rqstp) if (!inode) { /* File doesn't exist. Create it and set attrs */ resp->status = nfsd_create_locked(rqstp, dirfhp, argp->name, - argp->len, attr, type, rdev, + argp->len, &attrs, type, rdev, newfhp); } else if (type == S_IFREG) { dprintk("nfsd: existing %s, valid=%x, size=%ld\n", @@ -396,13 +402,12 @@ nfsd_proc_create(struct svc_rqst *rqstp) */ attr->ia_valid &= ATTR_SIZE; if (attr->ia_valid) - resp->status = nfsd_setattr(rqstp, newfhp, attr, 0, + resp->status = nfsd_setattr(rqstp, newfhp, &attrs, 0, (time64_t)0); } out_unlock: - /* We don't really need to unlock, as fh_put does it. */ - fh_unlock(dirfhp); + inode_unlock(dirfhp->fh_dentry->d_inode); fh_drop_write(dirfhp); done: fh_put(dirfhp); @@ -472,6 +477,9 @@ nfsd_proc_symlink(struct svc_rqst *rqstp) { struct nfsd_symlinkargs *argp = rqstp->rq_argp; struct nfsd_stat *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; struct svc_fh newfh; if (argp->tlen > NFS_MAXPATHLEN) { @@ -493,7 +501,7 @@ nfsd_proc_symlink(struct svc_rqst *rqstp) fh_init(&newfh, NFS_FHSIZE); resp->status = nfsd_symlink(rqstp, &argp->ffh, argp->fname, argp->flen, - argp->tname, &newfh); + argp->tname, &attrs, &newfh); kfree(argp->tname); fh_put(&argp->ffh); @@ -511,6 +519,9 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp) { struct nfsd_createargs *argp = rqstp->rq_argp; struct nfsd_diropres *resp = rqstp->rq_resp; + struct nfsd_attrs attrs = { + .na_iattr = &argp->attrs, + }; dprintk("nfsd: MKDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name); @@ -522,7 +533,7 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp) argp->attrs.ia_valid &= ~ATTR_SIZE; fh_init(&resp->fh, NFS_FHSIZE); resp->status = nfsd_create(rqstp, &argp->fh, argp->name, argp->len, - &argp->attrs, S_IFDIR, 0, &resp->fh); + &attrs, S_IFDIR, 0, &resp->fh); fh_put(&argp->fh); if (resp->status != nfs_ok) goto out; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index f3d6313914ed..ae596dbf8667 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -703,7 +703,6 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn); void put_nfs4_file(struct nfs4_file *fi); -extern void nfs4_put_copy(struct nfsd4_copy *copy); extern struct nfsd4_copy * find_async_copy(struct nfs4_client *clp, stateid_t *staetid); extern void nfs4_put_cpntf_state(struct nfsd_net *nn, diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index a60ead3b227a..9ebd67d461f9 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -171,6 +171,52 @@ TRACE_EVENT(nfsd_compound_encode_err, __entry->opnum, __entry->status) ); +#define show_fs_file_type(x) \ + __print_symbolic(x, \ + { S_IFLNK, "LNK" }, \ + { S_IFREG, "REG" }, \ + { S_IFDIR, "DIR" }, \ + { S_IFCHR, "CHR" }, \ + { S_IFBLK, "BLK" }, \ + { S_IFIFO, "FIFO" }, \ + { S_IFSOCK, "SOCK" }) + +TRACE_EVENT(nfsd_fh_verify, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct svc_fh *fhp, + umode_t type, + int access + ), + TP_ARGS(rqstp, fhp, type, access), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) + __sockaddr(client, rqstp->rq_xprt->xpt_remotelen) + __field(u32, xid) + __field(u32, fh_hash) + __field(void *, inode) + __field(unsigned long, type) + __field(unsigned long, access) + ), + TP_fast_assign( + __entry->netns_ino = SVC_NET(rqstp)->ns.inum; + __assign_sockaddr(server, &rqstp->rq_xprt->xpt_local, + rqstp->rq_xprt->xpt_locallen); + __assign_sockaddr(client, &rqstp->rq_xprt->xpt_remote, + rqstp->rq_xprt->xpt_remotelen); + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + __entry->inode = d_inode(fhp->fh_dentry); + __entry->type = type; + __entry->access = access; + ), + TP_printk("xid=0x%08x fh_hash=0x%08x inode=%p type=%s access=%s", + __entry->xid, __entry->fh_hash, __entry->inode, + show_fs_file_type(__entry->type), + show_nfsd_may_flags(__entry->access) + ) +); DECLARE_EVENT_CLASS(nfsd_fh_err_class, TP_PROTO(struct svc_rqst *rqstp, @@ -696,15 +742,12 @@ DEFINE_CLID_EVENT(confirmed_r); __print_flags(val, "|", \ { 1 << NFSD_FILE_HASHED, "HASHED" }, \ { 1 << NFSD_FILE_PENDING, "PENDING" }, \ - { 1 << NFSD_FILE_BREAK_READ, "BREAK_READ" }, \ - { 1 << NFSD_FILE_BREAK_WRITE, "BREAK_WRITE" }, \ { 1 << NFSD_FILE_REFERENCED, "REFERENCED"}) DECLARE_EVENT_CLASS(nfsd_file_class, TP_PROTO(struct nfsd_file *nf), TP_ARGS(nf), TP_STRUCT__entry( - __field(unsigned int, nf_hashval) __field(void *, nf_inode) __field(int, nf_ref) __field(unsigned long, nf_flags) @@ -712,15 +755,13 @@ DECLARE_EVENT_CLASS(nfsd_file_class, __field(struct file *, nf_file) ), TP_fast_assign( - __entry->nf_hashval = nf->nf_hashval; __entry->nf_inode = nf->nf_inode; __entry->nf_ref = refcount_read(&nf->nf_ref); __entry->nf_flags = nf->nf_flags; __entry->nf_may = nf->nf_may; __entry->nf_file = nf->nf_file; ), - TP_printk("hash=0x%x inode=%p ref=%d flags=%s may=%s file=%p", - __entry->nf_hashval, + TP_printk("inode=%p ref=%d flags=%s may=%s nf_file=%p", __entry->nf_inode, __entry->nf_ref, show_nf_flags(__entry->nf_flags), @@ -733,34 +774,59 @@ DEFINE_EVENT(nfsd_file_class, name, \ TP_PROTO(struct nfsd_file *nf), \ TP_ARGS(nf)) -DEFINE_NFSD_FILE_EVENT(nfsd_file_alloc); DEFINE_NFSD_FILE_EVENT(nfsd_file_put_final); DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash); DEFINE_NFSD_FILE_EVENT(nfsd_file_put); -DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_release_locked); +DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_dispose); + +TRACE_EVENT(nfsd_file_alloc, + TP_PROTO( + const struct nfsd_file *nf + ), + TP_ARGS(nf), + TP_STRUCT__entry( + __field(const void *, nf_inode) + __field(unsigned long, nf_flags) + __field(unsigned long, nf_may) + __field(unsigned int, nf_ref) + ), + TP_fast_assign( + __entry->nf_inode = nf->nf_inode; + __entry->nf_flags = nf->nf_flags; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->nf_may = nf->nf_may; + ), + TP_printk("inode=%p ref=%u flags=%s may=%s", + __entry->nf_inode, __entry->nf_ref, + show_nf_flags(__entry->nf_flags), + show_nfsd_may_flags(__entry->nf_may) + ) +); TRACE_EVENT(nfsd_file_acquire, - TP_PROTO(struct svc_rqst *rqstp, unsigned int hash, - struct inode *inode, unsigned int may_flags, - struct nfsd_file *nf, __be32 status), + TP_PROTO( + const struct svc_rqst *rqstp, + const struct inode *inode, + unsigned int may_flags, + const struct nfsd_file *nf, + __be32 status + ), - TP_ARGS(rqstp, hash, inode, may_flags, nf, status), + TP_ARGS(rqstp, inode, may_flags, nf, status), TP_STRUCT__entry( __field(u32, xid) - __field(unsigned int, hash) - __field(void *, inode) + __field(const void *, inode) __field(unsigned long, may_flags) - __field(int, nf_ref) + __field(unsigned int, nf_ref) __field(unsigned long, nf_flags) __field(unsigned long, nf_may) - __field(struct file *, nf_file) + __field(const void *, nf_file) __field(u32, status) ), TP_fast_assign( __entry->xid = be32_to_cpu(rqstp->rq_xid); - __entry->hash = hash; __entry->inode = inode; __entry->may_flags = may_flags; __entry->nf_ref = nf ? refcount_read(&nf->nf_ref) : 0; @@ -770,19 +836,117 @@ TRACE_EVENT(nfsd_file_acquire, __entry->status = be32_to_cpu(status); ), - TP_printk("xid=0x%x hash=0x%x inode=%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=%p status=%u", - __entry->xid, __entry->hash, __entry->inode, + TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p status=%u", + __entry->xid, __entry->inode, show_nfsd_may_flags(__entry->may_flags), __entry->nf_ref, show_nf_flags(__entry->nf_flags), show_nfsd_may_flags(__entry->nf_may), - __entry->nf_file, __entry->status) + __entry->nf_file, __entry->status + ) +); + +TRACE_EVENT(nfsd_file_create, + TP_PROTO( + const struct svc_rqst *rqstp, + unsigned int may_flags, + const struct nfsd_file *nf + ), + + TP_ARGS(rqstp, may_flags, nf), + + TP_STRUCT__entry( + __field(const void *, nf_inode) + __field(const void *, nf_file) + __field(unsigned long, may_flags) + __field(unsigned long, nf_flags) + __field(unsigned long, nf_may) + __field(unsigned int, nf_ref) + __field(u32, xid) + ), + + TP_fast_assign( + __entry->nf_inode = nf->nf_inode; + __entry->nf_file = nf->nf_file; + __entry->may_flags = may_flags; + __entry->nf_flags = nf->nf_flags; + __entry->nf_may = nf->nf_may; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->xid = be32_to_cpu(rqstp->rq_xid); + ), + + TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p", + __entry->xid, __entry->nf_inode, + show_nfsd_may_flags(__entry->may_flags), + __entry->nf_ref, show_nf_flags(__entry->nf_flags), + show_nfsd_may_flags(__entry->nf_may), __entry->nf_file + ) +); + +TRACE_EVENT(nfsd_file_insert_err, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct inode *inode, + unsigned int may_flags, + long error + ), + TP_ARGS(rqstp, inode, may_flags, error), + TP_STRUCT__entry( + __field(u32, xid) + __field(const void *, inode) + __field(unsigned long, may_flags) + __field(long, error) + ), + TP_fast_assign( + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->inode = inode; + __entry->may_flags = may_flags; + __entry->error = error; + ), + TP_printk("xid=0x%x inode=%p may_flags=%s error=%ld", + __entry->xid, __entry->inode, + show_nfsd_may_flags(__entry->may_flags), + __entry->error + ) +); + +TRACE_EVENT(nfsd_file_cons_err, + TP_PROTO( + const struct svc_rqst *rqstp, + const struct inode *inode, + unsigned int may_flags, + const struct nfsd_file *nf + ), + TP_ARGS(rqstp, inode, may_flags, nf), + TP_STRUCT__entry( + __field(u32, xid) + __field(const void *, inode) + __field(unsigned long, may_flags) + __field(unsigned int, nf_ref) + __field(unsigned long, nf_flags) + __field(unsigned long, nf_may) + __field(const void *, nf_file) + ), + TP_fast_assign( + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->inode = inode; + __entry->may_flags = may_flags; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->nf_flags = nf->nf_flags; + __entry->nf_may = nf->nf_may; + __entry->nf_file = nf->nf_file; + ), + TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p", + __entry->xid, __entry->inode, + show_nfsd_may_flags(__entry->may_flags), __entry->nf_ref, + show_nf_flags(__entry->nf_flags), + show_nfsd_may_flags(__entry->nf_may), __entry->nf_file + ) ); TRACE_EVENT(nfsd_file_open, TP_PROTO(struct nfsd_file *nf, __be32 status), TP_ARGS(nf, status), TP_STRUCT__entry( - __field(unsigned int, nf_hashval) __field(void *, nf_inode) /* cannot be dereferenced */ __field(int, nf_ref) __field(unsigned long, nf_flags) @@ -790,15 +954,13 @@ TRACE_EVENT(nfsd_file_open, __field(void *, nf_file) /* cannot be dereferenced */ ), TP_fast_assign( - __entry->nf_hashval = nf->nf_hashval; __entry->nf_inode = nf->nf_inode; __entry->nf_ref = refcount_read(&nf->nf_ref); __entry->nf_flags = nf->nf_flags; __entry->nf_may = nf->nf_may; __entry->nf_file = nf->nf_file; ), - TP_printk("hash=0x%x inode=%p ref=%d flags=%s may=%s file=%p", - __entry->nf_hashval, + TP_printk("inode=%p ref=%d flags=%s may=%s file=%p", __entry->nf_inode, __entry->nf_ref, show_nf_flags(__entry->nf_flags), @@ -807,30 +969,53 @@ TRACE_EVENT(nfsd_file_open, ) DECLARE_EVENT_CLASS(nfsd_file_search_class, - TP_PROTO(struct inode *inode, unsigned int hash, int found), - TP_ARGS(inode, hash, found), + TP_PROTO( + const struct inode *inode, + unsigned int count + ), + TP_ARGS(inode, count), TP_STRUCT__entry( - __field(struct inode *, inode) - __field(unsigned int, hash) - __field(int, found) + __field(const struct inode *, inode) + __field(unsigned int, count) ), TP_fast_assign( __entry->inode = inode; - __entry->hash = hash; - __entry->found = found; + __entry->count = count; ), - TP_printk("hash=0x%x inode=%p found=%d", __entry->hash, - __entry->inode, __entry->found) + TP_printk("inode=%p count=%u", + __entry->inode, __entry->count) ); #define DEFINE_NFSD_FILE_SEARCH_EVENT(name) \ DEFINE_EVENT(nfsd_file_search_class, name, \ - TP_PROTO(struct inode *inode, unsigned int hash, int found), \ - TP_ARGS(inode, hash, found)) + TP_PROTO( \ + const struct inode *inode, \ + unsigned int count \ + ), \ + TP_ARGS(inode, count)) DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode_sync); DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode); -DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_is_cached); + +TRACE_EVENT(nfsd_file_is_cached, + TP_PROTO( + const struct inode *inode, + int found + ), + TP_ARGS(inode, found), + TP_STRUCT__entry( + __field(const struct inode *, inode) + __field(int, found) + ), + TP_fast_assign( + __entry->inode = inode; + __entry->found = found; + ), + TP_printk("inode=%p is %scached", + __entry->inode, + __entry->found ? "" : "not " + ) +); TRACE_EVENT(nfsd_file_fsnotify_handle_event, TP_PROTO(struct inode *inode, u32 mask), @@ -851,6 +1036,76 @@ TRACE_EVENT(nfsd_file_fsnotify_handle_event, __entry->nlink, __entry->mode, __entry->mask) ); +DECLARE_EVENT_CLASS(nfsd_file_gc_class, + TP_PROTO( + const struct nfsd_file *nf + ), + TP_ARGS(nf), + TP_STRUCT__entry( + __field(void *, nf_inode) + __field(void *, nf_file) + __field(int, nf_ref) + __field(unsigned long, nf_flags) + ), + TP_fast_assign( + __entry->nf_inode = nf->nf_inode; + __entry->nf_file = nf->nf_file; + __entry->nf_ref = refcount_read(&nf->nf_ref); + __entry->nf_flags = nf->nf_flags; + ), + TP_printk("inode=%p ref=%d nf_flags=%s nf_file=%p", + __entry->nf_inode, __entry->nf_ref, + show_nf_flags(__entry->nf_flags), + __entry->nf_file + ) +); + +#define DEFINE_NFSD_FILE_GC_EVENT(name) \ +DEFINE_EVENT(nfsd_file_gc_class, name, \ + TP_PROTO( \ + const struct nfsd_file *nf \ + ), \ + TP_ARGS(nf)) + +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_add); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_add_disposed); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_del); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_del_disposed); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_in_use); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_writeback); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_referenced); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_hashed); +DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_disposed); + +DECLARE_EVENT_CLASS(nfsd_file_lruwalk_class, + TP_PROTO( + unsigned long removed, + unsigned long remaining + ), + TP_ARGS(removed, remaining), + TP_STRUCT__entry( + __field(unsigned long, removed) + __field(unsigned long, remaining) + ), + TP_fast_assign( + __entry->removed = removed; + __entry->remaining = remaining; + ), + TP_printk("%lu entries removed, %lu remaining", + __entry->removed, __entry->remaining) +); + +#define DEFINE_NFSD_FILE_LRUWALK_EVENT(name) \ +DEFINE_EVENT(nfsd_file_lruwalk_class, name, \ + TP_PROTO( \ + unsigned long removed, \ + unsigned long remaining \ + ), \ + TP_ARGS(removed, remaining)) + +DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_gc_removed); +DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_shrinker_removed); + #include "cache.h" TRACE_DEFINE_ENUM(RC_DROPIT); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index d79db56475d4..9f486b788ed0 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -199,27 +199,13 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_nfserr; } } else { - /* - * In the nfsd4_open() case, this may be held across - * subsequent open and delegation acquisition which may - * need to take the child's i_mutex: - */ - fh_lock_nested(fhp, I_MUTEX_PARENT); - dentry = lookup_one_len(name, dparent, len); + dentry = lookup_one_len_unlocked(name, dparent, len); host_err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_nfserr; if (nfsd_mountpoint(dentry, exp)) { - /* - * We don't need the i_mutex after all. It's - * still possible we could open this (regular - * files can be mountpoints too), but the - * i_mutex is just there to prevent renames of - * something that we might be about to delegate, - * and a mountpoint won't be renamed: - */ - fh_unlock(fhp); - if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) { + host_err = nfsd_cross_mnt(rqstp, &dentry, &exp); + if (host_err) { dput(dentry); goto out_nfserr; } @@ -234,7 +220,15 @@ out_nfserr: return nfserrno(host_err); } -/* +/** + * nfsd_lookup - look up a single path component for nfsd + * + * @rqstp: the request context + * @fhp: the file handle of the directory + * @name: the component name, or %NULL to look up parent + * @len: length of name to examine + * @resfh: pointer to pre-initialised filehandle to hold result. + * * Look up one component of a pathname. * N.B. After this call _both_ fhp and resfh need an fh_put * @@ -244,11 +238,11 @@ out_nfserr: * returned. Otherwise the covered directory is returned. * NOTE: this mountpoint crossing is not supported properly by all * clients and is explicitly disallowed for NFSv3 - * NeilBrown <neilb@cse.unsw.edu.au> + * */ __be32 nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, - unsigned int len, struct svc_fh *resfh) + unsigned int len, struct svc_fh *resfh) { struct svc_export *exp; struct dentry *dentry; @@ -349,11 +343,13 @@ nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp, * Set various file attributes. After this call fhp needs an fh_put. */ __be32 -nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, +nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct nfsd_attrs *attr, int check_guard, time64_t guardtime) { struct dentry *dentry; struct inode *inode; + struct iattr *iap = attr->na_iattr; int accmode = NFSD_MAY_SATTR; umode_t ftype = 0; __be32 err; @@ -420,7 +416,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, return err; } - fh_lock(fhp); + inode_lock(inode); if (size_change) { /* * RFC5661, Section 18.30.4: @@ -456,7 +452,19 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, host_err = notify_change(&init_user_ns, dentry, iap, NULL); out_unlock: - fh_unlock(fhp); + if (attr->na_seclabel && attr->na_seclabel->len) + attr->na_labelerr = security_inode_setsecctx(dentry, + attr->na_seclabel->data, attr->na_seclabel->len); + if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && attr->na_pacl) + attr->na_aclerr = set_posix_acl(&init_user_ns, + inode, ACL_TYPE_ACCESS, + attr->na_pacl); + if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && + !attr->na_aclerr && attr->na_dpacl && S_ISDIR(inode->i_mode)) + attr->na_aclerr = set_posix_acl(&init_user_ns, + inode, ACL_TYPE_DEFAULT, + attr->na_dpacl); + inode_unlock(inode); if (size_change) put_write_access(inode); out: @@ -494,32 +502,6 @@ int nfsd4_is_junction(struct dentry *dentry) return 0; return 1; } -#ifdef CONFIG_NFSD_V4_SECURITY_LABEL -__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct xdr_netobj *label) -{ - __be32 error; - int host_error; - struct dentry *dentry; - - error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, NFSD_MAY_SATTR); - if (error) - return error; - - dentry = fhp->fh_dentry; - - inode_lock(d_inode(dentry)); - host_error = security_inode_setsecctx(dentry, label->data, label->len); - inode_unlock(d_inode(dentry)); - return nfserrno(host_error); -} -#else -__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct xdr_netobj *label) -{ - return nfserr_notsupp; -} -#endif static struct nfsd4_compound_state *nfsd4_get_cstate(struct svc_rqst *rqstp) { @@ -1202,14 +1184,15 @@ out: * @rqstp: RPC transaction being executed * @fhp: NFS filehandle of parent directory * @resfhp: NFS filehandle of new object - * @iap: requested attributes of new object + * @attrs: requested attributes of new object * * Returns nfs_ok on success, or an nfsstat in network byte order. */ __be32 nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct svc_fh *resfhp, struct iattr *iap) + struct svc_fh *resfhp, struct nfsd_attrs *attrs) { + struct iattr *iap = attrs->na_iattr; __be32 status; /* @@ -1230,7 +1213,7 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, * if the attributes have not changed. */ if (iap->ia_valid) - status = nfsd_setattr(rqstp, resfhp, iap, 0, (time64_t)0); + status = nfsd_setattr(rqstp, resfhp, attrs, 0, (time64_t)0); else status = nfserrno(commit_metadata(resfhp)); @@ -1269,11 +1252,12 @@ nfsd_check_ignore_resizing(struct iattr *iap) /* The parent directory should already be locked: */ __be32 nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, - char *fname, int flen, struct iattr *iap, - int type, dev_t rdev, struct svc_fh *resfhp) + char *fname, int flen, struct nfsd_attrs *attrs, + int type, dev_t rdev, struct svc_fh *resfhp) { struct dentry *dentry, *dchild; struct inode *dirp; + struct iattr *iap = attrs->na_iattr; __be32 err; int host_err; @@ -1281,13 +1265,6 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, dirp = d_inode(dentry); dchild = dget(resfhp->fh_dentry); - if (!fhp->fh_locked) { - WARN_ONCE(1, "nfsd_create: parent %pd2 not locked!\n", - dentry); - err = nfserr_io; - goto out; - } - err = nfsd_permission(rqstp, fhp->fh_export, dentry, NFSD_MAY_CREATE); if (err) goto out; @@ -1347,7 +1324,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err < 0) goto out_nfserr; - err = nfsd_create_setattr(rqstp, fhp, resfhp, iap); + err = nfsd_create_setattr(rqstp, fhp, resfhp, attrs); out: dput(dchild); @@ -1366,8 +1343,8 @@ out_nfserr: */ __be32 nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, - char *fname, int flen, struct iattr *iap, - int type, dev_t rdev, struct svc_fh *resfhp) + char *fname, int flen, struct nfsd_attrs *attrs, + int type, dev_t rdev, struct svc_fh *resfhp) { struct dentry *dentry, *dchild = NULL; __be32 err; @@ -1386,11 +1363,13 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (host_err) return nfserrno(host_err); - fh_lock_nested(fhp, I_MUTEX_PARENT); + inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); dchild = lookup_one_len(fname, dentry, flen); host_err = PTR_ERR(dchild); - if (IS_ERR(dchild)) - return nfserrno(host_err); + if (IS_ERR(dchild)) { + err = nfserrno(host_err); + goto out_unlock; + } err = fh_compose(resfhp, fhp->fh_export, dchild, fhp); /* * We unconditionally drop our ref to dchild as fh_compose will have @@ -1398,9 +1377,14 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, */ dput(dchild); if (err) - return err; - return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type, - rdev, resfhp); + goto out_unlock; + fh_fill_pre_attrs(fhp); + err = nfsd_create_locked(rqstp, fhp, fname, flen, attrs, type, + rdev, resfhp); + fh_fill_post_attrs(fhp); +out_unlock: + inode_unlock(dentry->d_inode); + return err; } /* @@ -1441,15 +1425,25 @@ nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp) return 0; } -/* - * Create a symlink and look up its inode +/** + * nfsd_symlink - Create a symlink and look up its inode + * @rqstp: RPC transaction being executed + * @fhp: NFS filehandle of parent directory + * @fname: filename of the new symlink + * @flen: length of @fname + * @path: content of the new symlink (NUL-terminated) + * @attrs: requested attributes of new object + * @resfhp: NFS filehandle of new object + * * N.B. After this call _both_ fhp and resfhp need an fh_put + * + * Returns nfs_ok on success, or an nfsstat in network byte order. */ __be32 nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, - char *fname, int flen, - char *path, - struct svc_fh *resfhp) + char *fname, int flen, + char *path, struct nfsd_attrs *attrs, + struct svc_fh *resfhp) { struct dentry *dentry, *dnew; __be32 err, cerr; @@ -1467,33 +1461,35 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; host_err = fh_want_write(fhp); - if (host_err) - goto out_nfserr; + if (host_err) { + err = nfserrno(host_err); + goto out; + } - fh_lock(fhp); dentry = fhp->fh_dentry; + inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); dnew = lookup_one_len(fname, dentry, flen); - host_err = PTR_ERR(dnew); - if (IS_ERR(dnew)) - goto out_nfserr; - + if (IS_ERR(dnew)) { + err = nfserrno(PTR_ERR(dnew)); + inode_unlock(dentry->d_inode); + goto out_drop_write; + } + fh_fill_pre_attrs(fhp); host_err = vfs_symlink(&init_user_ns, d_inode(dentry), dnew, path); err = nfserrno(host_err); - fh_unlock(fhp); + cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp); + if (!err) + nfsd_create_setattr(rqstp, fhp, resfhp, attrs); + fh_fill_post_attrs(fhp); + inode_unlock(dentry->d_inode); if (!err) err = nfserrno(commit_metadata(fhp)); - - fh_drop_write(fhp); - - cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp); dput(dnew); if (err==0) err = cerr; +out_drop_write: + fh_drop_write(fhp); out: return err; - -out_nfserr: - err = nfserrno(host_err); - goto out; } /* @@ -1531,22 +1527,25 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, goto out; } - fh_lock_nested(ffhp, I_MUTEX_PARENT); ddir = ffhp->fh_dentry; dirp = d_inode(ddir); + inode_lock_nested(dirp, I_MUTEX_PARENT); dnew = lookup_one_len(name, ddir, len); - host_err = PTR_ERR(dnew); - if (IS_ERR(dnew)) - goto out_nfserr; + if (IS_ERR(dnew)) { + err = nfserrno(PTR_ERR(dnew)); + goto out_unlock; + } dold = tfhp->fh_dentry; err = nfserr_noent; if (d_really_is_negative(dold)) goto out_dput; + fh_fill_pre_attrs(ffhp); host_err = vfs_link(dold, &init_user_ns, dirp, dnew, NULL); - fh_unlock(ffhp); + fh_fill_post_attrs(ffhp); + inode_unlock(dirp); if (!host_err) { err = nfserrno(commit_metadata(ffhp)); if (!err) @@ -1557,17 +1556,17 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, else err = nfserrno(host_err); } -out_dput: dput(dnew); -out_unlock: - fh_unlock(ffhp); +out_drop_write: fh_drop_write(tfhp); out: return err; -out_nfserr: - err = nfserrno(host_err); - goto out_unlock; +out_dput: + dput(dnew); +out_unlock: + inode_unlock(dirp); + goto out_drop_write; } static void @@ -1628,10 +1627,7 @@ retry: goto out; } - /* cannot use fh_lock as we need deadlock protective ordering - * so do it by hand */ trap = lock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = true; fh_fill_pre_attrs(ffhp); fh_fill_pre_attrs(tfhp); @@ -1687,17 +1683,12 @@ retry: dput(odentry); out_nfserr: err = nfserrno(host_err); - /* - * We cannot rely on fh_unlock on the two filehandles, - * as that would do the wrong thing if the two directories - * were the same, so again we do it by hand. - */ + if (!close_cached) { fh_fill_post_attrs(ffhp); fh_fill_post_attrs(tfhp); } unlock_rename(tdentry, fdentry); - ffhp->fh_locked = tfhp->fh_locked = false; fh_drop_write(ffhp); /* @@ -1741,19 +1732,19 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (host_err) goto out_nfserr; - fh_lock_nested(fhp, I_MUTEX_PARENT); dentry = fhp->fh_dentry; dirp = d_inode(dentry); + inode_lock_nested(dirp, I_MUTEX_PARENT); rdentry = lookup_one_len(fname, dentry, flen); host_err = PTR_ERR(rdentry); if (IS_ERR(rdentry)) - goto out_drop_write; + goto out_unlock; if (d_really_is_negative(rdentry)) { dput(rdentry); host_err = -ENOENT; - goto out_drop_write; + goto out_unlock; } rinode = d_inode(rdentry); ihold(rinode); @@ -1761,6 +1752,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (!type) type = d_inode(rdentry)->i_mode & S_IFMT; + fh_fill_pre_attrs(fhp); if (type != S_IFDIR) { if (rdentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) nfsd_close_cached_files(rdentry); @@ -1768,8 +1760,9 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, } else { host_err = vfs_rmdir(&init_user_ns, dirp, rdentry); } + fh_fill_post_attrs(fhp); - fh_unlock(fhp); + inode_unlock(dirp); if (!host_err) host_err = commit_metadata(fhp); dput(rdentry); @@ -1791,6 +1784,9 @@ out_nfserr: } out: return err; +out_unlock: + inode_unlock(dirp); + goto out_drop_write; } /* @@ -2144,13 +2140,16 @@ out: return err; } -/* - * Removexattr and setxattr need to call fh_lock to both lock the inode - * and set the change attribute. Since the top-level vfs_removexattr - * and vfs_setxattr calls already do their own inode_lock calls, call - * the _locked variant. Pass in a NULL pointer for delegated_inode, - * and let the client deal with NFS4ERR_DELAY (same as with e.g. - * setattr and remove). +/** + * nfsd_removexattr - Remove an extended attribute + * @rqstp: RPC transaction being executed + * @fhp: NFS filehandle of object with xattr to remove + * @name: name of xattr to remove (NUL-terminate) + * + * Pass in a NULL pointer for delegated_inode, and let the client deal + * with NFS4ERR_DELAY (same as with e.g. setattr and remove). + * + * Returns nfs_ok on success, or an nfsstat in network byte order. */ __be32 nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) @@ -2166,12 +2165,14 @@ nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) if (ret) return nfserrno(ret); - fh_lock(fhp); + inode_lock(fhp->fh_dentry->d_inode); + fh_fill_pre_attrs(fhp); ret = __vfs_removexattr_locked(&init_user_ns, fhp->fh_dentry, name, NULL); - fh_unlock(fhp); + fh_fill_post_attrs(fhp); + inode_unlock(fhp->fh_dentry->d_inode); fh_drop_write(fhp); return nfsd_xattr_errno(ret); @@ -2191,12 +2192,13 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, ret = fh_want_write(fhp); if (ret) return nfserrno(ret); - fh_lock(fhp); + inode_lock(fhp->fh_dentry->d_inode); + fh_fill_pre_attrs(fhp); ret = __vfs_setxattr_locked(&init_user_ns, fhp->fh_dentry, name, buf, len, flags, NULL); - - fh_unlock(fhp); + fh_fill_post_attrs(fhp); + inode_unlock(fhp->fh_dentry->d_inode); fh_drop_write(fhp); return nfsd_xattr_errno(ret); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 26347d76f44a..c95cd414b4bb 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -6,6 +6,8 @@ #ifndef LINUX_NFSD_VFS_H #define LINUX_NFSD_VFS_H +#include <linux/fs.h> +#include <linux/posix_acl.h> #include "nfsfh.h" #include "nfsd.h" @@ -42,6 +44,22 @@ struct nfsd_file; typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned); /* nfsd/vfs.c */ +struct nfsd_attrs { + struct iattr *na_iattr; /* input */ + struct xdr_netobj *na_seclabel; /* input */ + struct posix_acl *na_pacl; /* input */ + struct posix_acl *na_dpacl; /* input */ + + int na_labelerr; /* output */ + int na_aclerr; /* output */ +}; + +static inline void nfsd_attrs_free(struct nfsd_attrs *attrs) +{ + posix_acl_release(attrs->na_pacl); + posix_acl_release(attrs->na_dpacl); +} + int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct svc_export **expp); __be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *, @@ -50,11 +68,9 @@ __be32 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *, const char *, unsigned int, struct svc_export **, struct dentry **); __be32 nfsd_setattr(struct svc_rqst *, struct svc_fh *, - struct iattr *, int, time64_t); + struct nfsd_attrs *, int, time64_t); int nfsd_mountpoint(struct dentry *, struct svc_export *); #ifdef CONFIG_NFSD_V4 -__be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *, - struct xdr_netobj *); __be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *, struct file *, loff_t, loff_t, int); __be32 nfsd4_clone_file_range(struct svc_rqst *rqstp, @@ -63,14 +79,14 @@ __be32 nfsd4_clone_file_range(struct svc_rqst *rqstp, u64 count, bool sync); #endif /* CONFIG_NFSD_V4 */ __be32 nfsd_create_locked(struct svc_rqst *, struct svc_fh *, - char *name, int len, struct iattr *attrs, + char *name, int len, struct nfsd_attrs *attrs, int type, dev_t rdev, struct svc_fh *res); __be32 nfsd_create(struct svc_rqst *, struct svc_fh *, - char *name, int len, struct iattr *attrs, + char *name, int len, struct nfsd_attrs *attrs, int type, dev_t rdev, struct svc_fh *res); __be32 nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *); __be32 nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct svc_fh *resfhp, struct iattr *iap); + struct svc_fh *resfhp, struct nfsd_attrs *iap); __be32 nfsd_commit(struct svc_rqst *rqst, struct svc_fh *fhp, u64 offset, u32 count, __be32 *verf); #ifdef CONFIG_NFSD_V4 @@ -110,8 +126,9 @@ __be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *, char *, int *); __be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *, - char *name, int len, char *path, - struct svc_fh *res); + char *name, int len, char *path, + struct nfsd_attrs *attrs, + struct svc_fh *res); __be32 nfsd_link(struct svc_rqst *, struct svc_fh *, char *, int, struct svc_fh *); ssize_t nfsd_copy_file_range(struct file *, u64, diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 7b744011f2d3..96267258e629 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -279,6 +279,7 @@ struct nfsd4_open { struct nfs4_clnt_odstate *op_odstate; /* used during processing */ struct nfs4_acl *op_acl; struct xdr_netobj op_label; + struct svc_rqst *op_rqstp; }; struct nfsd4_open_confirm { @@ -302,9 +303,10 @@ struct nfsd4_read { u32 rd_length; /* request */ int rd_vlen; struct nfsd_file *rd_nf; - + struct svc_rqst *rd_rqstp; /* response */ - struct svc_fh *rd_fhp; /* response */ + struct svc_fh *rd_fhp; /* response */ + u32 rd_eof; /* response */ }; struct nfsd4_readdir { @@ -532,6 +534,13 @@ struct nfsd42_write_res { stateid_t cb_stateid; }; +struct nfsd4_cb_offload { + struct nfsd4_callback co_cb; + struct nfsd42_write_res co_res; + __be32 co_nfserr; + struct knfsd_fh co_fh; +}; + struct nfsd4_copy { /* request */ stateid_t cp_src_stateid; @@ -539,18 +548,16 @@ struct nfsd4_copy { u64 cp_src_pos; u64 cp_dst_pos; u64 cp_count; - struct nl4_server cp_src; - bool cp_intra; + struct nl4_server *cp_src; - /* both */ - u32 cp_synchronous; + unsigned long cp_flags; +#define NFSD4_COPY_F_STOPPED (0) +#define NFSD4_COPY_F_INTRA (1) +#define NFSD4_COPY_F_SYNCHRONOUS (2) +#define NFSD4_COPY_F_COMMITTED (3) /* response */ struct nfsd42_write_res cp_res; - - /* for cb_offload */ - struct nfsd4_callback cp_cb; - __be32 nfserr; struct knfsd_fh fh; struct nfs4_client *cp_clp; @@ -563,14 +570,35 @@ struct nfsd4_copy { struct list_head copies; struct task_struct *copy_task; refcount_t refcount; - bool stopped; struct vfsmount *ss_mnt; struct nfs_fh c_fh; nfs4_stateid stateid; - bool committed; }; +static inline void nfsd4_copy_set_sync(struct nfsd4_copy *copy, bool sync) +{ + if (sync) + set_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); + else + clear_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); +} + +static inline bool nfsd4_copy_is_sync(const struct nfsd4_copy *copy) +{ + return test_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); +} + +static inline bool nfsd4_copy_is_async(const struct nfsd4_copy *copy) +{ + return !test_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); +} + +static inline bool nfsd4_ssc_is_inter(const struct nfsd4_copy *copy) +{ + return !test_bit(NFSD4_COPY_F_INTRA, ©->cp_flags); +} + struct nfsd4_seek { /* request */ stateid_t seek_stateid; @@ -594,19 +622,20 @@ struct nfsd4_offload_status { struct nfsd4_copy_notify { /* request */ stateid_t cpn_src_stateid; - struct nl4_server cpn_dst; + struct nl4_server *cpn_dst; /* response */ stateid_t cpn_cnr_stateid; u64 cpn_sec; u32 cpn_nsec; - struct nl4_server cpn_src; + struct nl4_server *cpn_src; }; struct nfsd4_op { u32 opnum; - const struct nfsd4_operation * opdesc; __be32 status; + const struct nfsd4_operation *opdesc; + struct nfs4_replay *replay; union nfsd4_op_u { struct nfsd4_access access; struct nfsd4_close close; @@ -670,7 +699,6 @@ struct nfsd4_op { struct nfsd4_listxattrs listxattrs; struct nfsd4_removexattr removexattr; } u; - struct nfs4_replay * replay; }; bool nfsd4_cache_this_op(struct nfsd4_op *); diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index e8c00dda42ad..71f870d497ae 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -84,8 +84,8 @@ static inline bool attr_must_be_resident(struct ntfs_sb_info *sbi, /* * attr_load_runs - Load all runs stored in @attr. */ -int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni, - struct runs_tree *run, const CLST *vcn) +static int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni, + struct runs_tree *run, const CLST *vcn) { int err; CLST svcn = le64_to_cpu(attr->nres.svcn); @@ -140,7 +140,10 @@ failed: } if (lcn != SPARSE_LCN) { - mark_as_free_ex(sbi, lcn, clen, trim); + if (sbi) { + /* mark bitmap range [lcn + clen) as free and trim clusters. */ + mark_as_free_ex(sbi, lcn, clen, trim); + } dn += clen; } @@ -173,7 +176,6 @@ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, { int err; CLST flen, vcn0 = vcn, pre = pre_alloc ? *pre_alloc : 0; - struct wnd_bitmap *wnd = &sbi->used.bitmap; size_t cnt = run->count; for (;;) { @@ -196,9 +198,7 @@ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, /* Add new fragment into run storage. */ if (!run_add_entry(run, vcn, lcn, flen, opt == ALLOCATE_MFT)) { /* Undo last 'ntfs_look_for_free_space' */ - down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); - wnd_set_free(wnd, lcn, flen); - up_write(&wnd->rw_lock); + mark_as_free_ex(sbi, lcn, len, false); err = -ENOMEM; goto out; } @@ -320,7 +320,7 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, err = ni_insert_nonresident(ni, attr_s->type, attr_name(attr_s), attr_s->name_len, run, 0, alen, - attr_s->flags, &attr, NULL); + attr_s->flags, &attr, NULL, NULL); if (err) goto out3; @@ -419,40 +419,44 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, struct mft_inode *mi, *mi_b; CLST alen, vcn, lcn, new_alen, old_alen, svcn, evcn; CLST next_svcn, pre_alloc = -1, done = 0; - bool is_ext; + bool is_ext, is_bad = false; u32 align; struct MFT_REC *rec; again: + alen = 0; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, NULL, &mi_b); if (!attr_b) { err = -ENOENT; - goto out; + goto bad_inode; } if (!attr_b->non_res) { err = attr_set_size_res(ni, attr_b, le_b, mi_b, new_size, run, &attr_b); - if (err || !attr_b->non_res) - goto out; + if (err) + return err; + + /* Return if file is still resident. */ + if (!attr_b->non_res) + goto ok1; /* Layout of records may be changed, so do a full search. */ goto again; } is_ext = is_attr_ext(attr_b); - -again_1: align = sbi->cluster_size; - if (is_ext) align <<= attr_b->nres.c_unit; old_valid = le64_to_cpu(attr_b->nres.valid_size); old_size = le64_to_cpu(attr_b->nres.data_size); old_alloc = le64_to_cpu(attr_b->nres.alloc_size); + +again_1: old_alen = old_alloc >> cluster_bits; new_alloc = (new_size + align - 1) & ~(u64)(align - 1); @@ -475,24 +479,27 @@ again_1: mi = mi_b; } else if (!le_b) { err = -EINVAL; - goto out; + goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, type, name, name_len, &vcn, &mi); if (!attr) { err = -EINVAL; - goto out; + goto bad_inode; } next_le_1: svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); } - + /* + * Here we have: + * attr,mi,le - last attribute segment (containing 'vcn'). + * attr_b,mi_b,le_b - base (primary) attribute segment. + */ next_le: rec = mi->mrec; - err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; @@ -507,6 +514,13 @@ next_le: goto ok; } + /* + * Add clusters. In simple case we have to: + * - allocate space (vcn, lcn, len) + * - update packed run in 'mi' + * - update attr->nres.evcn + * - update attr_b->nres.data_size/attr_b->nres.alloc_size + */ to_allocate = new_alen - old_alen; add_alloc_in_same_attr_seg: lcn = 0; @@ -520,9 +534,11 @@ add_alloc_in_same_attr_seg: pre_alloc = 0; if (type == ATTR_DATA && !name_len && sbi->options->prealloc) { - CLST new_alen2 = bytes_to_cluster( - sbi, get_pre_allocated(new_size)); - pre_alloc = new_alen2 - new_alen; + pre_alloc = + bytes_to_cluster( + sbi, + get_pre_allocated(new_size)) - + new_alen; } /* Get the last LCN to allocate from. */ @@ -580,7 +596,7 @@ add_alloc_in_same_attr_seg: pack_runs: err = mi_pack_runs(mi, attr, run, vcn - svcn); if (err) - goto out; + goto undo_1; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; new_alloc_tmp = (u64)next_svcn << cluster_bits; @@ -614,7 +630,7 @@ pack_runs: if (type == ATTR_LIST) { err = ni_expand_list(ni); if (err) - goto out; + goto undo_2; if (next_svcn < vcn) goto pack_runs; @@ -624,8 +640,9 @@ pack_runs: if (!ni->attr_list.size) { err = ni_create_attr_list(ni); + /* In case of error layout of records is not changed. */ if (err) - goto out; + goto undo_2; /* Layout of records is changed. */ } @@ -637,48 +654,57 @@ pack_runs: /* Insert new attribute segment. */ err = ni_insert_nonresident(ni, type, name, name_len, run, next_svcn, vcn - next_svcn, - attr_b->flags, &attr, &mi); - if (err) - goto out; - - if (!is_mft) - run_truncate_head(run, evcn + 1); - - svcn = le64_to_cpu(attr->nres.svcn); - evcn = le64_to_cpu(attr->nres.evcn); + attr_b->flags, &attr, &mi, NULL); - le_b = NULL; /* * Layout of records maybe changed. * Find base attribute to update. */ + le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, NULL, &mi_b); if (!attr_b) { - err = -ENOENT; - goto out; + err = -EINVAL; + goto bad_inode; } - attr_b->nres.alloc_size = cpu_to_le64((u64)vcn << cluster_bits); - attr_b->nres.data_size = attr_b->nres.alloc_size; - attr_b->nres.valid_size = attr_b->nres.alloc_size; + if (err) { + /* ni_insert_nonresident failed. */ + attr = NULL; + goto undo_2; + } + + if (!is_mft) + run_truncate_head(run, evcn + 1); + + svcn = le64_to_cpu(attr->nres.svcn); + evcn = le64_to_cpu(attr->nres.evcn); + + /* + * Attribute is in consistency state. + * Save this point to restore to if next steps fail. + */ + old_valid = old_size = old_alloc = (u64)vcn << cluster_bits; + attr_b->nres.valid_size = attr_b->nres.data_size = + attr_b->nres.alloc_size = cpu_to_le64(old_size); mi_b->dirty = true; goto again_1; } if (new_size != old_size || (new_alloc != old_alloc && !keep_prealloc)) { + /* + * Truncate clusters. In simple case we have to: + * - update packed run in 'mi' + * - update attr->nres.evcn + * - update attr_b->nres.data_size/attr_b->nres.alloc_size + * - mark and trim clusters as free (vcn, lcn, len) + */ + CLST dlen = 0; + vcn = max(svcn, new_alen); new_alloc_tmp = (u64)vcn << cluster_bits; - alen = 0; - err = run_deallocate_ex(sbi, run, vcn, evcn - vcn + 1, &alen, - true); - if (err) - goto out; - - run_truncate(run, vcn); - if (vcn > svcn) { err = mi_pack_runs(mi, attr, run, vcn - svcn); if (err) @@ -697,7 +723,7 @@ pack_runs: if (!al_remove_le(ni, le)) { err = -EINVAL; - goto out; + goto bad_inode; } le = (struct ATTR_LIST_ENTRY *)((u8 *)le - le_sz); @@ -723,12 +749,20 @@ pack_runs: attr_b->nres.valid_size = attr_b->nres.alloc_size; } + mi_b->dirty = true; - if (is_ext) + err = run_deallocate_ex(sbi, run, vcn, evcn - vcn + 1, &dlen, + true); + if (err) + goto out; + + if (is_ext) { + /* dlen - really deallocated clusters. */ le64_sub_cpu(&attr_b->nres.total_size, - ((u64)alen << cluster_bits)); + ((u64)dlen << cluster_bits)); + } - mi_b->dirty = true; + run_truncate(run, vcn); if (new_alloc_tmp <= new_alloc) goto ok; @@ -747,7 +781,7 @@ pack_runs: if (le->type != type || le->name_len != name_len || memcmp(le_name(le), name, name_len * sizeof(short))) { err = -EINVAL; - goto out; + goto bad_inode; } err = ni_load_mi(ni, le, &mi); @@ -757,7 +791,7 @@ pack_runs: attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id); if (!attr) { err = -EINVAL; - goto out; + goto bad_inode; } goto next_le_1; } @@ -772,13 +806,13 @@ ok: } } -out: - if (!err && attr_b && ret) +ok1: + if (ret) *ret = attr_b; /* Update inode_set_bytes. */ - if (!err && ((type == ATTR_DATA && !name_len) || - (type == ATTR_ALLOC && name == I30_NAME))) { + if (((type == ATTR_DATA && !name_len) || + (type == ATTR_ALLOC && name == I30_NAME))) { bool dirty = false; if (ni->vfs_inode.i_size != new_size) { @@ -786,7 +820,7 @@ out: dirty = true; } - if (attr_b && attr_b->non_res) { + if (attr_b->non_res) { new_alloc = le64_to_cpu(attr_b->nres.alloc_size); if (inode_get_bytes(&ni->vfs_inode) != new_alloc) { inode_set_bytes(&ni->vfs_inode, new_alloc); @@ -800,6 +834,47 @@ out: } } + return 0; + +undo_2: + vcn -= alen; + attr_b->nres.data_size = cpu_to_le64(old_size); + attr_b->nres.valid_size = cpu_to_le64(old_valid); + attr_b->nres.alloc_size = cpu_to_le64(old_alloc); + + /* Restore 'attr' and 'mi'. */ + if (attr) + goto restore_run; + + if (le64_to_cpu(attr_b->nres.svcn) <= svcn && + svcn <= le64_to_cpu(attr_b->nres.evcn)) { + attr = attr_b; + le = le_b; + mi = mi_b; + } else if (!le_b) { + err = -EINVAL; + goto bad_inode; + } else { + le = le_b; + attr = ni_find_attr(ni, attr_b, &le, type, name, name_len, + &svcn, &mi); + if (!attr) + goto bad_inode; + } + +restore_run: + if (mi_pack_runs(mi, attr, run, evcn - svcn + 1)) + is_bad = true; + +undo_1: + run_deallocate_ex(sbi, run, vcn, alen, NULL, false); + + run_truncate(run, vcn); +out: + if (is_bad) { +bad_inode: + _ntfs_bad_inode(&ni->vfs_inode); + } return err; } @@ -855,7 +930,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, goto out; } - asize = le64_to_cpu(attr_b->nres.alloc_size) >> sbi->cluster_bits; + asize = le64_to_cpu(attr_b->nres.alloc_size) >> cluster_bits; if (vcn >= asize) { err = -EINVAL; goto out; @@ -1047,7 +1122,7 @@ ins_ext: if (evcn1 > next_svcn) { err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - next_svcn, - attr_b->flags, &attr, &mi); + attr_b->flags, &attr, &mi, NULL); if (err) goto out; } @@ -1173,7 +1248,7 @@ int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type, { struct ntfs_sb_info *sbi = ni->mi.sbi; u8 cluster_bits = sbi->cluster_bits; - CLST vcn = from >> cluster_bits; + CLST vcn; CLST vcn_last = (to - 1) >> cluster_bits; CLST lcn, clen; int err; @@ -1647,7 +1722,7 @@ ins_ext: if (evcn1 > next_svcn) { err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - next_svcn, - attr_b->flags, &attr, &mi); + attr_b->flags, &attr, &mi, NULL); if (err) goto out; } @@ -1812,18 +1887,12 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) err = ni_insert_nonresident( ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - eat - next_svcn, a_flags, &attr, - &mi); + &mi, &le); if (err) goto out; /* Layout of records maybe changed. */ attr_b = NULL; - le = al_find_ex(ni, NULL, ATTR_DATA, NULL, 0, - &next_svcn); - if (!le) { - err = -EINVAL; - goto out; - } } /* Free all allocated memory. */ @@ -1918,7 +1987,7 @@ next_attr: out: up_write(&ni->file.run_lock); if (err) - make_bad_inode(&ni->vfs_inode); + _ntfs_bad_inode(&ni->vfs_inode); return err; } @@ -1936,9 +2005,11 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; - CLST svcn, evcn1, vcn, len, end, alen, dealloc; + CLST svcn, evcn1, vcn, len, end, alen, hole, next_svcn; u64 total_size, alloc_size; u32 mask; + __le16 a_flags; + struct runs_tree run2; if (!bytes) return 0; @@ -1990,6 +2061,9 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) } down_write(&ni->file.run_lock); + run_init(&run2); + run_truncate(run, 0); + /* * Enumerate all attribute segments and punch hole where necessary. */ @@ -1997,10 +2071,11 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) vcn = vbo >> sbi->cluster_bits; len = bytes >> sbi->cluster_bits; end = vcn + len; - dealloc = 0; + hole = 0; svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; + a_flags = attr_b->flags; if (svcn <= vcn && vcn < evcn1) { attr = attr_b; @@ -2008,14 +2083,14 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) mi = mi_b; } else if (!le_b) { err = -EINVAL; - goto out; + goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; - goto out; + goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); @@ -2023,49 +2098,91 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) } while (svcn < end) { - CLST vcn1, zero, dealloc2; + CLST vcn1, zero, hole2 = hole; err = attr_load_runs(attr, ni, run, &svcn); if (err) - goto out; + goto done; vcn1 = max(vcn, svcn); zero = min(end, evcn1) - vcn1; - dealloc2 = dealloc; - err = run_deallocate_ex(sbi, run, vcn1, zero, &dealloc, true); + /* + * Check range [vcn1 + zero). + * Calculate how many clusters there are. + * Don't do any destructive actions. + */ + err = run_deallocate_ex(NULL, run, vcn1, zero, &hole2, false); if (err) - goto out; + goto done; - if (dealloc2 == dealloc) { - /* Looks like the required range is already sparsed. */ - } else { - if (!run_add_entry(run, vcn1, SPARSE_LCN, zero, - false)) { - err = -ENOMEM; - goto out; - } + /* Check if required range is already hole. */ + if (hole2 == hole) + goto next_attr; + + /* Make a clone of run to undo. */ + err = run_clone(run, &run2); + if (err) + goto done; + + /* Make a hole range (sparse) [vcn1 + zero). */ + if (!run_add_entry(run, vcn1, SPARSE_LCN, zero, false)) { + err = -ENOMEM; + goto done; + } - err = mi_pack_runs(mi, attr, run, evcn1 - svcn); + /* Update run in attribute segment. */ + err = mi_pack_runs(mi, attr, run, evcn1 - svcn); + if (err) + goto done; + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + if (next_svcn < evcn1) { + /* Insert new attribute segment. */ + err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, + next_svcn, + evcn1 - next_svcn, a_flags, + &attr, &mi, &le); if (err) - goto out; + goto undo_punch; + + /* Layout of records maybe changed. */ + attr_b = NULL; } + + /* Real deallocate. Should not fail. */ + run_deallocate_ex(sbi, &run2, vcn1, zero, &hole, true); + +next_attr: /* Free all allocated memory. */ run_truncate(run, 0); if (evcn1 >= alen) break; + /* Get next attribute segment. */ attr = ni_enum_attr_ex(ni, attr, &le, &mi); if (!attr) { err = -EINVAL; - goto out; + goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } - total_size -= (u64)dealloc << sbi->cluster_bits; +done: + if (!hole) + goto out; + + if (!attr_b) { + attr_b = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, + &mi_b); + if (!attr_b) { + err = -EINVAL; + goto bad_inode; + } + } + + total_size -= (u64)hole << sbi->cluster_bits; attr_b->nres.total_size = cpu_to_le64(total_size); mi_b->dirty = true; @@ -2075,9 +2192,263 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) mark_inode_dirty(&ni->vfs_inode); out: + run_close(&run2); up_write(&ni->file.run_lock); + return err; + +bad_inode: + _ntfs_bad_inode(&ni->vfs_inode); + goto out; + +undo_punch: + /* + * Restore packed runs. + * 'mi_pack_runs' should not fail, cause we restore original. + */ + if (mi_pack_runs(mi, attr, &run2, evcn1 - svcn)) + goto bad_inode; + + goto done; +} + +/* + * attr_insert_range - Insert range (hole) in file. + * Not for normal files. + */ +int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) +{ + int err = 0; + struct runs_tree *run = &ni->file.run; + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct ATTRIB *attr = NULL, *attr_b; + struct ATTR_LIST_ENTRY *le, *le_b; + struct mft_inode *mi, *mi_b; + CLST vcn, svcn, evcn1, len, next_svcn; + u64 data_size, alloc_size; + u32 mask; + __le16 a_flags; + + if (!bytes) + return 0; + + le_b = NULL; + attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); + if (!attr_b) + return -ENOENT; + + if (!is_attr_ext(attr_b)) { + /* It was checked above. See fallocate. */ + return -EOPNOTSUPP; + } + + if (!attr_b->non_res) { + data_size = le32_to_cpu(attr_b->res.data_size); + alloc_size = data_size; + mask = sbi->cluster_mask; /* cluster_size - 1 */ + } else { + data_size = le64_to_cpu(attr_b->nres.data_size); + alloc_size = le64_to_cpu(attr_b->nres.alloc_size); + mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1; + } + + if (vbo > data_size) { + /* Insert range after the file size is not allowed. */ + return -EINVAL; + } + + if ((vbo & mask) || (bytes & mask)) { + /* Allow to insert only frame aligned ranges. */ + return -EINVAL; + } + + /* + * valid_size <= data_size <= alloc_size + * Check alloc_size for maximum possible. + */ + if (bytes > sbi->maxbytes_sparse - alloc_size) + return -EFBIG; + + vcn = vbo >> sbi->cluster_bits; + len = bytes >> sbi->cluster_bits; + + down_write(&ni->file.run_lock); + + if (!attr_b->non_res) { + err = attr_set_size(ni, ATTR_DATA, NULL, 0, run, + data_size + bytes, NULL, false, NULL); + + le_b = NULL; + attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, + &mi_b); + if (!attr_b) { + err = -EINVAL; + goto bad_inode; + } + + if (err) + goto out; + + if (!attr_b->non_res) { + /* Still resident. */ + char *data = Add2Ptr(attr_b, attr_b->res.data_off); + + memmove(data + bytes, data, bytes); + memset(data, 0, bytes); + goto done; + } + + /* Resident files becomes nonresident. */ + data_size = le64_to_cpu(attr_b->nres.data_size); + alloc_size = le64_to_cpu(attr_b->nres.alloc_size); + } + + /* + * Enumerate all attribute segments and shift start vcn. + */ + a_flags = attr_b->flags; + svcn = le64_to_cpu(attr_b->nres.svcn); + evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; + + if (svcn <= vcn && vcn < evcn1) { + attr = attr_b; + le = le_b; + mi = mi_b; + } else if (!le_b) { + err = -EINVAL; + goto bad_inode; + } else { + le = le_b; + attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, + &mi); + if (!attr) { + err = -EINVAL; + goto bad_inode; + } + + svcn = le64_to_cpu(attr->nres.svcn); + evcn1 = le64_to_cpu(attr->nres.evcn) + 1; + } + + run_truncate(run, 0); /* clear cached values. */ + err = attr_load_runs(attr, ni, run, NULL); + if (err) + goto out; + + if (!run_insert_range(run, vcn, len)) { + err = -ENOMEM; + goto out; + } + + /* Try to pack in current record as much as possible. */ + err = mi_pack_runs(mi, attr, run, evcn1 + len - svcn); if (err) - make_bad_inode(&ni->vfs_inode); + goto out; + + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + + while ((attr = ni_enum_attr_ex(ni, attr, &le, &mi)) && + attr->type == ATTR_DATA && !attr->name_len) { + le64_add_cpu(&attr->nres.svcn, len); + le64_add_cpu(&attr->nres.evcn, len); + if (le) { + le->vcn = attr->nres.svcn; + ni->attr_list.dirty = true; + } + mi->dirty = true; + } + + if (next_svcn < evcn1 + len) { + err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, + next_svcn, evcn1 + len - next_svcn, + a_flags, NULL, NULL, NULL); + + le_b = NULL; + attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, + &mi_b); + if (!attr_b) { + err = -EINVAL; + goto bad_inode; + } + + if (err) { + /* ni_insert_nonresident failed. Try to undo. */ + goto undo_insert_range; + } + } + + /* + * Update primary attribute segment. + */ + if (vbo <= ni->i_valid) + ni->i_valid += bytes; + + attr_b->nres.data_size = le64_to_cpu(data_size + bytes); + attr_b->nres.alloc_size = le64_to_cpu(alloc_size + bytes); + + /* ni->valid may be not equal valid_size (temporary). */ + if (ni->i_valid > data_size + bytes) + attr_b->nres.valid_size = attr_b->nres.data_size; + else + attr_b->nres.valid_size = cpu_to_le64(ni->i_valid); + mi_b->dirty = true; + +done: + ni->vfs_inode.i_size += bytes; + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + mark_inode_dirty(&ni->vfs_inode); + +out: + run_truncate(run, 0); /* clear cached values. */ + + up_write(&ni->file.run_lock); return err; + +bad_inode: + _ntfs_bad_inode(&ni->vfs_inode); + goto out; + +undo_insert_range: + svcn = le64_to_cpu(attr_b->nres.svcn); + evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; + + if (svcn <= vcn && vcn < evcn1) { + attr = attr_b; + le = le_b; + mi = mi_b; + } else if (!le_b) { + goto bad_inode; + } else { + le = le_b; + attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, + &mi); + if (!attr) { + goto bad_inode; + } + + svcn = le64_to_cpu(attr->nres.svcn); + evcn1 = le64_to_cpu(attr->nres.evcn) + 1; + } + + if (attr_load_runs(attr, ni, run, NULL)) + goto bad_inode; + + if (!run_collapse_range(run, vcn, len)) + goto bad_inode; + + if (mi_pack_runs(mi, attr, run, evcn1 + len - svcn)) + goto bad_inode; + + while ((attr = ni_enum_attr_ex(ni, attr, &le, &mi)) && + attr->type == ATTR_DATA && !attr->name_len) { + le64_sub_cpu(&attr->nres.svcn, len); + le64_sub_cpu(&attr->nres.evcn, len); + if (le) { + le->vcn = attr->nres.svcn; + ni->attr_list.dirty = true; + } + mi->dirty = true; + } + + goto out; } diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index aa184407520f..5d44ceac855b 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -51,11 +51,6 @@ void ntfs3_exit_bitmap(void) kmem_cache_destroy(ntfs_enode_cachep); } -static inline u32 wnd_bits(const struct wnd_bitmap *wnd, size_t i) -{ - return i + 1 == wnd->nwnd ? wnd->bits_last : wnd->sb->s_blocksize * 8; -} - /* * wnd_scan * @@ -1333,9 +1328,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits) if (!new_free) return -ENOMEM; - if (new_free != wnd->free_bits) - memcpy(new_free, wnd->free_bits, - wnd->nwnd * sizeof(short)); + memcpy(new_free, wnd->free_bits, wnd->nwnd * sizeof(short)); memset(new_free + wnd->nwnd, 0, (new_wnd - wnd->nwnd) * sizeof(short)); kfree(wnd->free_bits); @@ -1395,9 +1388,8 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits) void wnd_zone_set(struct wnd_bitmap *wnd, size_t lcn, size_t len) { - size_t zlen; + size_t zlen = wnd->zone_end - wnd->zone_bit; - zlen = wnd->zone_end - wnd->zone_bit; if (zlen) wnd_add_free_ext(wnd, wnd->zone_bit, zlen, false); diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 4a21745711fe..4f2ffc7ef296 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -530,21 +530,35 @@ static int ntfs_truncate(struct inode *inode, loff_t new_size) static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) { struct inode *inode = file->f_mapping->host; + struct address_space *mapping = inode->i_mapping; struct super_block *sb = inode->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; struct ntfs_inode *ni = ntfs_i(inode); loff_t end = vbo + len; loff_t vbo_down = round_down(vbo, PAGE_SIZE); - loff_t i_size; + bool is_supported_holes = is_sparsed(ni) || is_compressed(ni); + loff_t i_size, new_size; + bool map_locked; int err; /* No support for dir. */ if (!S_ISREG(inode->i_mode)) return -EOPNOTSUPP; - /* Return error if mode is not supported. */ - if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | - FALLOC_FL_COLLAPSE_RANGE)) { + /* + * vfs_fallocate checks all possible combinations of mode. + * Do additional checks here before ntfs_set_state(dirty). + */ + if (mode & FALLOC_FL_PUNCH_HOLE) { + if (!is_supported_holes) + return -EOPNOTSUPP; + } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { + } else if (mode & FALLOC_FL_INSERT_RANGE) { + if (!is_supported_holes) + return -EOPNOTSUPP; + } else if (mode & + ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | + FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)) { ntfs_inode_warn(inode, "fallocate(0x%x) is not supported", mode); return -EOPNOTSUPP; @@ -554,6 +568,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) inode_lock(inode); i_size = inode->i_size; + new_size = max(end, i_size); + map_locked = false; if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) { /* Should never be here, see ntfs_file_open. */ @@ -561,38 +577,27 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) goto out; } + if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | + FALLOC_FL_INSERT_RANGE)) { + inode_dio_wait(inode); + filemap_invalidate_lock(mapping); + map_locked = true; + } + if (mode & FALLOC_FL_PUNCH_HOLE) { u32 frame_size; loff_t mask, vbo_a, end_a, tmp; - if (!(mode & FALLOC_FL_KEEP_SIZE)) { - err = -EINVAL; - goto out; - } - - err = filemap_write_and_wait_range(inode->i_mapping, vbo, - end - 1); + err = filemap_write_and_wait_range(mapping, vbo, end - 1); if (err) goto out; - err = filemap_write_and_wait_range(inode->i_mapping, end, - LLONG_MAX); + err = filemap_write_and_wait_range(mapping, end, LLONG_MAX); if (err) goto out; - inode_dio_wait(inode); - truncate_pagecache(inode, vbo_down); - if (!is_sparsed(ni) && !is_compressed(ni)) { - /* - * Normal file, can't make hole. - * TODO: Try to find way to save info about hole. - */ - err = -EOPNOTSUPP; - goto out; - } - ni_lock(ni); err = attr_punch_hole(ni, vbo, len, &frame_size); ni_unlock(ni); @@ -624,17 +629,11 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) ni_unlock(ni); } } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { - if (mode & ~FALLOC_FL_COLLAPSE_RANGE) { - err = -EINVAL; - goto out; - } - /* * Write tail of the last page before removed range since * it will get removed from the page cache below. */ - err = filemap_write_and_wait_range(inode->i_mapping, vbo_down, - vbo); + err = filemap_write_and_wait_range(mapping, vbo_down, vbo); if (err) goto out; @@ -642,34 +641,58 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) * Write data that will be shifted to preserve them * when discarding page cache below. */ - err = filemap_write_and_wait_range(inode->i_mapping, end, - LLONG_MAX); + err = filemap_write_and_wait_range(mapping, end, LLONG_MAX); if (err) goto out; - /* Wait for existing dio to complete. */ - inode_dio_wait(inode); - truncate_pagecache(inode, vbo_down); ni_lock(ni); err = attr_collapse_range(ni, vbo, len); ni_unlock(ni); + } else if (mode & FALLOC_FL_INSERT_RANGE) { + /* Check new size. */ + err = inode_newsize_ok(inode, new_size); + if (err) + goto out; + + /* Write out all dirty pages. */ + err = filemap_write_and_wait_range(mapping, vbo_down, + LLONG_MAX); + if (err) + goto out; + truncate_pagecache(inode, vbo_down); + + ni_lock(ni); + err = attr_insert_range(ni, vbo, len); + ni_unlock(ni); } else { - /* - * Normal file: Allocate clusters, do not change 'valid' size. - */ - loff_t new_size = max(end, i_size); + /* Check new size. */ + + /* generic/213: expected -ENOSPC instead of -EFBIG. */ + if (!is_supported_holes) { + loff_t to_alloc = new_size - inode_get_bytes(inode); + + if (to_alloc > 0 && + (to_alloc >> sbi->cluster_bits) > + wnd_zeroes(&sbi->used.bitmap)) { + err = -ENOSPC; + goto out; + } + } err = inode_newsize_ok(inode, new_size); if (err) goto out; + /* + * Allocate clusters, do not change 'valid' size. + */ err = ntfs_set_size(inode, new_size); if (err) goto out; - if (is_sparsed(ni) || is_compressed(ni)) { + if (is_supported_holes) { CLST vcn_v = ni->i_valid >> sbi->cluster_bits; CLST vcn = vbo >> sbi->cluster_bits; CLST cend = bytes_to_cluster(sbi, end); @@ -717,8 +740,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) } out: - if (err == -EFBIG) - err = -ENOSPC; + if (map_locked) + filemap_invalidate_unlock(mapping); if (!err) { inode->i_ctime = inode->i_mtime = current_time(inode); @@ -989,7 +1012,6 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from) if (bytes > count) bytes = count; - frame = pos >> frame_bits; frame_vbo = pos & ~(frame_size - 1); index = frame_vbo >> PAGE_SHIFT; diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 18842998c8fa..381a38a06ec2 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -7,6 +7,7 @@ #include <linux/fiemap.h> #include <linux/fs.h> +#include <linux/minmax.h> #include <linux/vmalloc.h> #include "debug.h" @@ -468,7 +469,7 @@ ni_ins_new_attr(struct ntfs_inode *ni, struct mft_inode *mi, &ref, &le); if (err) { /* No memory or no space. */ - return NULL; + return ERR_PTR(err); } le_added = true; @@ -649,6 +650,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) struct mft_inode *mi; u32 asize, free; struct MFT_REF ref; + struct MFT_REC *mrec; __le16 id; if (!ni->attr_list.dirty) @@ -692,11 +694,17 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) free -= asize; } + /* Make a copy of primary record to restore if error. */ + mrec = kmemdup(ni->mi.mrec, sbi->record_size, GFP_NOFS); + if (!mrec) + return 0; /* Not critical. */ + /* It seems that attribute list can be removed from primary record. */ mi_remove_attr(NULL, &ni->mi, attr_list); /* - * Repeat the cycle above and move all attributes to primary record. + * Repeat the cycle above and copy all attributes to primary record. + * Do not remove original attributes from subrecords! * It should be success! */ le = NULL; @@ -707,14 +715,14 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) mi = ni_find_mi(ni, ino_get(&le->ref)); if (!mi) { /* Should never happened, 'cause already checked. */ - goto bad; + goto out; } attr = mi_find_attr(mi, NULL, le->type, le_name(le), le->name_len, &le->id); if (!attr) { /* Should never happened, 'cause already checked. */ - goto bad; + goto out; } asize = le32_to_cpu(attr->size); @@ -724,18 +732,33 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) le16_to_cpu(attr->name_off)); if (!attr_ins) { /* - * Internal error. - * Either no space in primary record (already checked). - * Either tried to insert another - * non indexed attribute (logic error). + * No space in primary record (already checked). */ - goto bad; + goto out; } /* Copy all except id. */ id = attr_ins->id; memcpy(attr_ins, attr, asize); attr_ins->id = id; + } + + /* + * Repeat the cycle above and remove all attributes from subrecords. + */ + le = NULL; + while ((le = al_enumerate(ni, le))) { + if (!memcmp(&le->ref, &ref, sizeof(ref))) + continue; + + mi = ni_find_mi(ni, ino_get(&le->ref)); + if (!mi) + continue; + + attr = mi_find_attr(mi, NULL, le->type, le_name(le), + le->name_len, &le->id); + if (!attr) + continue; /* Remove from original record. */ mi_remove_attr(NULL, mi, attr); @@ -748,11 +771,13 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) ni->attr_list.le = NULL; ni->attr_list.dirty = false; + kfree(mrec); + return 0; +out: + /* Restore primary record. */ + swap(mrec, ni->mi.mrec); + kfree(mrec); return 0; -bad: - ntfs_inode_err(&ni->vfs_inode, "Internal error"); - make_bad_inode(&ni->vfs_inode); - return -EINVAL; } /* @@ -986,6 +1011,8 @@ static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, name_off, svcn, ins_le); if (!attr) continue; + if (IS_ERR(attr)) + return PTR_ERR(attr); if (ins_attr) *ins_attr = attr; @@ -1007,8 +1034,15 @@ insert_ext: attr = ni_ins_new_attr(ni, mi, le, type, name, name_len, asize, name_off, svcn, ins_le); - if (!attr) + if (!attr) { + err = -EINVAL; goto out2; + } + + if (IS_ERR(attr)) { + err = PTR_ERR(attr); + goto out2; + } if (ins_attr) *ins_attr = attr; @@ -1020,10 +1054,9 @@ insert_ext: out2: ni_remove_mi(ni, mi); mi_put(mi); - err = -EINVAL; out1: - ntfs_mark_rec_free(sbi, rno); + ntfs_mark_rec_free(sbi, rno, is_mft); out: return err; @@ -1076,6 +1109,11 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, if (asize <= free) { attr = ni_ins_new_attr(ni, &ni->mi, NULL, type, name, name_len, asize, name_off, svcn, ins_le); + if (IS_ERR(attr)) { + err = PTR_ERR(attr); + goto out; + } + if (attr) { if (ins_attr) *ins_attr = attr; @@ -1173,6 +1211,11 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, goto out; } + if (IS_ERR(attr)) { + err = PTR_ERR(attr); + goto out; + } + if (ins_attr) *ins_attr = attr; if (ins_mi) @@ -1218,7 +1261,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) mft_min = mft_new; mi_min = mi_new; } else { - ntfs_mark_rec_free(sbi, mft_new); + ntfs_mark_rec_free(sbi, mft_new, true); mft_new = 0; ni_remove_mi(ni, mi_new); } @@ -1262,7 +1305,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) done = asize - run_size - SIZEOF_NONRESIDENT; le32_sub_cpu(&ni->mi.mrec->used, done); - /* Estimate the size of second part: run_buf=NULL. */ + /* Estimate packed size (run_buf=NULL). */ err = run_pack(run, svcn, evcn + 1 - svcn, NULL, sbi->record_size, &plen); if (err < 0) @@ -1288,10 +1331,16 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) goto out; } + if (IS_ERR(attr)) { + err = PTR_ERR(attr); + goto out; + } + attr->non_res = 1; attr->name_off = SIZEOF_NONRESIDENT_LE; attr->flags = 0; + /* This function can't fail - cause already checked above. */ run_pack(run, svcn, evcn + 1 - svcn, Add2Ptr(attr, SIZEOF_NONRESIDENT), run_size, &plen); @@ -1301,7 +1350,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) out: if (mft_new) { - ntfs_mark_rec_free(sbi, mft_new); + ntfs_mark_rec_free(sbi, mft_new, true); ni_remove_mi(ni, mi_new); } @@ -1367,8 +1416,6 @@ int ni_expand_list(struct ntfs_inode *ni) /* Split MFT data as much as possible. */ err = ni_expand_mft_list(ni); - if (err) - goto out; out: return !err && !done ? -EOPNOTSUPP : err; @@ -1381,7 +1428,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, const struct runs_tree *run, CLST svcn, CLST len, __le16 flags, struct ATTRIB **new_attr, - struct mft_inode **mi) + struct mft_inode **mi, struct ATTR_LIST_ENTRY **le) { int err; CLST plen; @@ -1394,6 +1441,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, u32 run_size, asize; struct ntfs_sb_info *sbi = ni->mi.sbi; + /* Estimate packed size (run_buf=NULL). */ err = run_pack(run, svcn, len, NULL, sbi->max_bytes_per_attr - run_off, &plen); if (err < 0) @@ -1414,7 +1462,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, } err = ni_insert_attr(ni, type, name, name_len, asize, name_off, svcn, - &attr, mi, NULL); + &attr, mi, le); if (err) goto out; @@ -1423,12 +1471,12 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, attr->name_off = cpu_to_le16(name_off); attr->flags = flags; + /* This function can't fail - cause already checked above. */ run_pack(run, svcn, len, Add2Ptr(attr, run_off), run_size, &plen); attr->nres.svcn = cpu_to_le64(svcn); attr->nres.evcn = cpu_to_le64((u64)svcn + len - 1); - err = 0; if (new_attr) *new_attr = attr; @@ -1560,7 +1608,7 @@ int ni_delete_all(struct ntfs_inode *ni) mi->dirty = true; mi_write(mi, 0); - ntfs_mark_rec_free(sbi, mi->rno); + ntfs_mark_rec_free(sbi, mi->rno, false); ni_remove_mi(ni, mi); mi_put(mi); node = next; @@ -1571,7 +1619,7 @@ int ni_delete_all(struct ntfs_inode *ni) ni->mi.dirty = true; err = mi_write(&ni->mi, 0); - ntfs_mark_rec_free(sbi, ni->mi.rno); + ntfs_mark_rec_free(sbi, ni->mi.rno, false); return err; } @@ -1589,7 +1637,8 @@ struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni, struct ATTRIB *attr = NULL; struct ATTR_FILE_NAME *fname; - *le = NULL; + if (le) + *le = NULL; /* Enumerate all names. */ next: @@ -1605,7 +1654,7 @@ next: goto next; if (!uni) - goto next; + return fname; if (uni->len != fname->name_len) goto next; @@ -2302,10 +2351,8 @@ remove_wof: out: kfree(pages); - if (err) { - make_bad_inode(inode); - ntfs_set_state(sbi, NTFS_DIRTY_ERROR); - } + if (err) + _ntfs_bad_inode(inode); return err; } @@ -2944,7 +2991,7 @@ bool ni_remove_name_undo(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, } /* - * ni_add_name - Add new name in MFT and in directory. + * ni_add_name - Add new name into MFT and into directory. */ int ni_add_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, struct NTFS_DE *de) @@ -2953,13 +3000,20 @@ int ni_add_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, struct ATTRIB *attr; struct ATTR_LIST_ENTRY *le; struct mft_inode *mi; + struct ATTR_FILE_NAME *fname; struct ATTR_FILE_NAME *de_name = (struct ATTR_FILE_NAME *)(de + 1); u16 de_key_size = le16_to_cpu(de->key_size); mi_get_ref(&ni->mi, &de->ref); mi_get_ref(&dir_ni->mi, &de_name->home); - /* Insert new name in MFT. */ + /* Fill duplicate from any ATTR_NAME. */ + fname = ni_fname_name(ni, NULL, NULL, NULL, NULL); + if (fname) + memcpy(&de_name->dup, &fname->dup, sizeof(fname->dup)); + de_name->dup.fa = ni->std_fa; + + /* Insert new name into MFT. */ err = ni_insert_resident(ni, de_key_size, ATTR_NAME, NULL, 0, &attr, &mi, &le); if (err) @@ -2967,7 +3021,7 @@ int ni_add_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), de_name, de_key_size); - /* Insert new name in directory. */ + /* Insert new name into directory. */ err = indx_insert_entry(&dir_ni->dir, dir_ni, de, ni->mi.sbi, NULL, 0); if (err) ni_remove_attr_le(ni, attr, mi, le); @@ -2991,7 +3045,7 @@ int ni_rename(struct ntfs_inode *dir_ni, struct ntfs_inode *new_dir_ni, * 1) Add new name and remove old name. * 2) Remove old name and add new name. * - * In most cases (not all!) adding new name in MFT and in directory can + * In most cases (not all!) adding new name into MFT and into directory can * allocate additional cluster(s). * Second way may result to bad inode if we can't add new name * and then can't restore (add) old name. @@ -3261,7 +3315,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) err = err2; if (is_empty) { - ntfs_mark_rec_free(sbi, mi->rno); + ntfs_mark_rec_free(sbi, mi->rno, false); rb_erase(node, &ni->mi_tree); mi_put(mi); } diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 49b7df616778..e7c494005122 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -3843,6 +3843,8 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) memset(&rst_info2, 0, sizeof(struct restart_info)); err = log_read_rst(log, l_size, false, &rst_info2); + if (err) + goto out; /* Determine which restart area to use. */ if (!rst_info2.restart || rst_info2.last_lsn <= rst_info.last_lsn) @@ -5057,7 +5059,7 @@ undo_action_next: goto add_allocated_vcns; vcn = le64_to_cpu(lrh->target_vcn); - vcn &= ~(log->clst_per_page - 1); + vcn &= ~(u64)(log->clst_per_page - 1); add_allocated_vcns: for (i = 0, vcn = le64_to_cpu(lrh->target_vcn), diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 1835e35199c2..4ed15f64b17f 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -703,12 +703,14 @@ out: /* * ntfs_mark_rec_free - Mark record as free. + * is_mft - true if we are changing MFT */ -void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno) +void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno, bool is_mft) { struct wnd_bitmap *wnd = &sbi->mft.bitmap; - down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT); + if (!is_mft) + down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT); if (rno >= wnd->nbits) goto out; @@ -727,7 +729,8 @@ void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno) sbi->mft.next_free = rno; out: - up_write(&wnd->rw_lock); + if (!is_mft) + up_write(&wnd->rw_lock); } /* @@ -780,7 +783,7 @@ out: */ int ntfs_refresh_zone(struct ntfs_sb_info *sbi) { - CLST zone_limit, zone_max, lcn, vcn, len; + CLST lcn, vcn, len; size_t lcn_s, zlen; struct wnd_bitmap *wnd = &sbi->used.bitmap; struct ntfs_inode *ni = sbi->mft.ni; @@ -789,16 +792,6 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi) if (wnd_zone_len(wnd)) return 0; - /* - * Compute the MFT zone at two steps. - * It would be nice if we are able to allocate 1/8 of - * total clusters for MFT but not more then 512 MB. - */ - zone_limit = (512 * 1024 * 1024) >> sbi->cluster_bits; - zone_max = wnd->nbits >> 3; - if (zone_max > zone_limit) - zone_max = zone_limit; - vcn = bytes_to_cluster(sbi, (u64)sbi->mft.bitmap.nbits << sbi->record_bits); @@ -812,13 +805,7 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi) lcn_s = lcn + 1; /* Try to allocate clusters after last MFT run. */ - zlen = wnd_find(wnd, zone_max, lcn_s, 0, &lcn_s); - if (!zlen) { - ntfs_notice(sbi->sb, "MftZone: unavailable"); - return 0; - } - - /* Truncate too large zone. */ + zlen = wnd_find(wnd, sbi->zone_max, lcn_s, 0, &lcn_s); wnd_zone_set(wnd, lcn_s, zlen); return 0; @@ -827,16 +814,21 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi) /* * ntfs_update_mftmirr - Update $MFTMirr data. */ -int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) +void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) { int err; struct super_block *sb = sbi->sb; - u32 blocksize = sb->s_blocksize; + u32 blocksize; sector_t block1, block2; u32 bytes; + if (!sb) + return; + + blocksize = sb->s_blocksize; + if (!(sbi->flags & NTFS_FLAGS_MFTMIRR)) - return 0; + return; err = 0; bytes = sbi->mft.recs_mirr << sbi->record_bits; @@ -847,16 +839,13 @@ int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) struct buffer_head *bh1, *bh2; bh1 = sb_bread(sb, block1++); - if (!bh1) { - err = -EIO; - goto out; - } + if (!bh1) + return; bh2 = sb_getblk(sb, block2++); if (!bh2) { put_bh(bh1); - err = -EIO; - goto out; + return; } if (buffer_locked(bh2)) @@ -876,13 +865,24 @@ int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) put_bh(bh2); if (err) - goto out; + return; } sbi->flags &= ~NTFS_FLAGS_MFTMIRR; +} -out: - return err; +/* + * ntfs_bad_inode + * + * Marks inode as bad and marks fs as 'dirty' + */ +void ntfs_bad_inode(struct inode *inode, const char *hint) +{ + struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; + + ntfs_inode_err(inode, "%s", hint); + make_bad_inode(inode); + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); } /* @@ -1395,7 +1395,7 @@ int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr, if (buffer_locked(bh)) __wait_on_buffer(bh); - lock_buffer(nb->bh[idx]); + lock_buffer(bh); bh_data = bh->b_data + off; end_data = Add2Ptr(bh_data, op); @@ -2424,7 +2424,7 @@ static inline void ntfs_unmap_and_discard(struct ntfs_sb_info *sbi, CLST lcn, void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) { - CLST end, i; + CLST end, i, zone_len, zlen; struct wnd_bitmap *wnd = &sbi->used.bitmap; down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); @@ -2459,6 +2459,28 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) ntfs_unmap_and_discard(sbi, lcn, len); wnd_set_free(wnd, lcn, len); + /* append to MFT zone, if possible. */ + zone_len = wnd_zone_len(wnd); + zlen = min(zone_len + len, sbi->zone_max); + + if (zlen == zone_len) { + /* MFT zone already has maximum size. */ + } else if (!zone_len) { + /* Create MFT zone only if 'zlen' is large enough. */ + if (zlen == sbi->zone_max) + wnd_zone_set(wnd, lcn, zlen); + } else { + CLST zone_lcn = wnd_zone_bit(wnd); + + if (lcn + len == zone_lcn) { + /* Append into head MFT zone. */ + wnd_zone_set(wnd, lcn, zlen); + } else if (zone_lcn + zone_len == lcn) { + /* Append into tail MFT zone. */ + wnd_zone_set(wnd, zone_lcn, zlen); + } + } + out: up_write(&wnd->rw_lock); } diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 6f81e3a49abf..440328147e7e 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1042,19 +1042,16 @@ int indx_find(struct ntfs_index *indx, struct ntfs_inode *ni, { int err; struct NTFS_DE *e; - const struct INDEX_HDR *hdr; struct indx_node *node; if (!root) root = indx_get_root(&ni->dir, ni, NULL, NULL); if (!root) { - err = -EINVAL; - goto out; + /* Should not happen. */ + return -EINVAL; } - hdr = &root->ihdr; - /* Check cache. */ e = fnd->level ? fnd->de[fnd->level - 1] : fnd->root_de; if (e && !de_is_last(e) && @@ -1068,39 +1065,35 @@ int indx_find(struct ntfs_index *indx, struct ntfs_inode *ni, fnd_clear(fnd); /* Lookup entry that is <= to the search value. */ - e = hdr_find_e(indx, hdr, key, key_len, ctx, diff); + e = hdr_find_e(indx, &root->ihdr, key, key_len, ctx, diff); if (!e) return -EINVAL; fnd->root_de = e; - err = 0; for (;;) { node = NULL; - if (*diff >= 0 || !de_has_vcn_ex(e)) { - *entry = e; - goto out; - } + if (*diff >= 0 || !de_has_vcn_ex(e)) + break; /* Read next level. */ err = indx_read(indx, ni, de_get_vbn(e), &node); if (err) - goto out; + return err; /* Lookup entry that is <= to the search value. */ e = hdr_find_e(indx, &node->index->ihdr, key, key_len, ctx, diff); if (!e) { - err = -EINVAL; put_indx_node(node); - goto out; + return -EINVAL; } fnd_push(fnd, node, e); } -out: - return err; + *entry = e; + return 0; } int indx_find_sort(struct ntfs_index *indx, struct ntfs_inode *ni, @@ -1354,7 +1347,7 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, goto out; err = ni_insert_nonresident(ni, ATTR_ALLOC, in->name, in->name_len, - &run, 0, len, 0, &alloc, NULL); + &run, 0, len, 0, &alloc, NULL, NULL); if (err) goto out1; @@ -1685,8 +1678,8 @@ indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni, { int err; const struct NTFS_DE *sp; - struct NTFS_DE *e, *de_t, *up_e = NULL; - struct indx_node *n2 = NULL; + struct NTFS_DE *e, *de_t, *up_e; + struct indx_node *n2; struct indx_node *n1 = fnd->nodes[level]; struct INDEX_HDR *hdr1 = &n1->index->ihdr; struct INDEX_HDR *hdr2; @@ -1994,7 +1987,7 @@ static int indx_free_children(struct ntfs_index *indx, struct ntfs_inode *ni, const struct NTFS_DE *e, bool trim) { int err; - struct indx_node *n; + struct indx_node *n = NULL; struct INDEX_HDR *hdr; CLST vbn = de_get_vbn(e); size_t i; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 80104afeb2cd..51363d4e8636 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -430,6 +430,7 @@ end_enum: } else if (fname && fname->home.low == cpu_to_le32(MFT_REC_EXTEND) && fname->home.seq == cpu_to_le16(MFT_REC_EXTEND)) { /* Records in $Extend are not a files or general directories. */ + inode->i_op = &ntfs_file_inode_operations; } else { err = -EINVAL; goto out; @@ -500,7 +501,7 @@ struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref, inode = ntfs_read_mft(inode, name, ref); else if (ref->seq != ntfs_i(inode)->mi.mrec->seq) { /* Inode overlaps? */ - make_bad_inode(inode); + _ntfs_bad_inode(inode); } return inode; @@ -1632,7 +1633,7 @@ out4: ni->mi.dirty = false; discard_new_inode(inode); out3: - ntfs_mark_rec_free(sbi, ino); + ntfs_mark_rec_free(sbi, ino, false); out2: __putname(new_de); @@ -1655,7 +1656,6 @@ int ntfs_link_inode(struct inode *inode, struct dentry *dentry) struct ntfs_inode *ni = ntfs_i(inode); struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; struct NTFS_DE *de; - struct ATTR_FILE_NAME *de_name; /* Allocate PATH_MAX bytes. */ de = __getname(); @@ -1670,15 +1670,6 @@ int ntfs_link_inode(struct inode *inode, struct dentry *dentry) if (err) goto out; - de_name = (struct ATTR_FILE_NAME *)(de + 1); - /* Fill duplicate info. */ - de_name->dup.cr_time = de_name->dup.m_time = de_name->dup.c_time = - de_name->dup.a_time = kernel2nt(&inode->i_ctime); - de_name->dup.alloc_size = de_name->dup.data_size = - cpu_to_le64(inode->i_size); - de_name->dup.fa = ni->std_fa; - de_name->dup.ea_size = de_name->dup.reparse = 0; - err = ni_add_name(ntfs_i(d_inode(dentry->d_parent)), ni, de); out: __putname(de); @@ -1731,9 +1722,7 @@ int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry) if (inode->i_nlink) mark_inode_dirty(inode); } else if (!ni_remove_name_undo(dir_ni, ni, de, de2, undo_remove)) { - make_bad_inode(inode); - ntfs_inode_err(inode, "failed to undo unlink"); - ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + _ntfs_bad_inode(inode); } else { if (ni_is_dirty(dir)) mark_inode_dirty(dir); diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index bc741213ad84..bc22cc321a74 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -208,7 +208,7 @@ static int ntfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, } /* - * ntfs_rmdir - inode_operations::rm_dir + * ntfs_rmdir - inode_operations::rmdir */ static int ntfs_rmdir(struct inode *dir, struct dentry *dentry) { @@ -308,9 +308,7 @@ static int ntfs_rename(struct user_namespace *mnt_userns, struct inode *dir, err = ni_rename(dir_ni, new_dir_ni, ni, de, new_de, &is_bad); if (is_bad) { /* Restore after failed rename failed too. */ - make_bad_inode(inode); - ntfs_inode_err(inode, "failed to undo rename"); - ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + _ntfs_bad_inode(inode); } else if (!err) { inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(dir); diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 8dbdca03e1af..2c791222c4e2 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -220,6 +220,7 @@ struct ntfs_sb_info { u32 flags; // See NTFS_FLAGS_XXX. + CLST zone_max; // Maximum MFT zone length in clusters CLST bad_clusters; // The count of marked bad clusters. u16 max_bytes_per_attr; // Maximum attribute size in record. @@ -408,8 +409,6 @@ enum REPARSE_SIGN { }; /* Functions from attrib.c */ -int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni, - struct runs_tree *run, const CLST *vcn); int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, CLST vcn, CLST lcn, CLST len, CLST *pre_alloc, enum ALLOCATE_OPT opt, CLST *alen, const size_t fr, @@ -440,6 +439,7 @@ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr, int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, u64 new_valid); int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes); +int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes); int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size); /* Functions from attrlist.c */ @@ -528,7 +528,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, const struct runs_tree *run, CLST svcn, CLST len, __le16 flags, struct ATTRIB **new_attr, - struct mft_inode **mi); + struct mft_inode **mi, struct ATTR_LIST_ENTRY **le); int ni_insert_resident(struct ntfs_inode *ni, u32 data_size, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct ATTRIB **new_attr, struct mft_inode **mi, @@ -589,10 +589,12 @@ int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len, enum ALLOCATE_OPT opt); int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft, struct ntfs_inode *ni, struct mft_inode **mi); -void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno); +void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno, bool is_mft); int ntfs_clear_mft_tail(struct ntfs_sb_info *sbi, size_t from, size_t to); int ntfs_refresh_zone(struct ntfs_sb_info *sbi); -int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait); +void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait); +void ntfs_bad_inode(struct inode *inode, const char *hint); +#define _ntfs_bad_inode(i) ntfs_bad_inode(i, __func__) enum NTFS_DIRTY_FLAGS { NTFS_DIRTY_CLEAR = 0, NTFS_DIRTY_DIRTY = 1, @@ -738,7 +740,6 @@ static inline struct ATTRIB *rec_find_attr_le(struct mft_inode *rec, int mi_write(struct mft_inode *mi, int wait); int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, __le16 flags, bool is_mft); -void mi_mark_free(struct mft_inode *mi); struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, const __le16 *name, u8 name_len, u32 asize, u16 name_off); @@ -780,10 +781,10 @@ bool run_lookup_entry(const struct runs_tree *run, CLST vcn, CLST *lcn, void run_truncate(struct runs_tree *run, CLST vcn); void run_truncate_head(struct runs_tree *run, CLST vcn); void run_truncate_around(struct runs_tree *run, CLST vcn); -bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *Index); bool run_add_entry(struct runs_tree *run, CLST vcn, CLST lcn, CLST len, bool is_mft); bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len); +bool run_insert_range(struct runs_tree *run, CLST vcn, CLST len); bool run_get_entry(const struct runs_tree *run, size_t index, CLST *vcn, CLST *lcn, CLST *len); bool run_is_mapped_full(const struct runs_tree *run, CLST svcn, CLST evcn); @@ -802,6 +803,7 @@ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, #define run_unpack_ex run_unpack #endif int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn); +int run_clone(const struct runs_tree *run, struct runs_tree *new_run); /* Globals from super.c */ void *ntfs_set_shared(void *ptr, u32 bytes); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 861e35791506..7d2fac5ee215 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -395,28 +395,6 @@ int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, } /* - * mi_mark_free - Mark record as unused and marks it as free in bitmap. - */ -void mi_mark_free(struct mft_inode *mi) -{ - CLST rno = mi->rno; - struct ntfs_sb_info *sbi = mi->sbi; - - if (rno >= MFT_REC_RESERVED && rno < MFT_REC_FREE) { - ntfs_clear_mft_tail(sbi, rno, rno + 1); - mi->dirty = false; - return; - } - - if (mi->mrec) { - clear_rec_inuse(mi->mrec); - mi->dirty = true; - mi_write(mi, 0); - } - ntfs_mark_rec_free(sbi, rno); -} - -/* * mi_insert_attr - Reserve space for new attribute. * * Return: Not full constructed attribute or NULL if not possible to create. @@ -445,12 +423,11 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, attr = NULL; while ((attr = mi_enum_attr(mi, attr))) { diff = compare_attr(attr, type, name, name_len, upcase); - if (diff > 0) - break; + if (diff < 0) continue; - if (!is_attr_indexed(attr)) + if (!diff && !is_attr_indexed(attr)) return NULL; break; } diff --git a/fs/ntfs3/run.c b/fs/ntfs3/run.c index a8fec651f973..aaaa0d3d35a2 100644 --- a/fs/ntfs3/run.c +++ b/fs/ntfs3/run.c @@ -31,7 +31,7 @@ struct ntfs_run { * Case of entry missing from list 'index' will be set to * point to insertion position for the entry question. */ -bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *index) +static bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *index) { size_t min_idx, max_idx, mid_idx; struct ntfs_run *r; @@ -547,6 +547,48 @@ bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len) return true; } +/* run_insert_range + * + * Helper for attr_insert_range(), + * which is helper for fallocate(insert_range). + */ +bool run_insert_range(struct runs_tree *run, CLST vcn, CLST len) +{ + size_t index; + struct ntfs_run *r, *e; + + if (WARN_ON(!run_lookup(run, vcn, &index))) + return false; /* Should never be here. */ + + e = run->runs + run->count; + r = run->runs + index; + + if (vcn > r->vcn) + r += 1; + + for (; r < e; r++) + r->vcn += len; + + r = run->runs + index; + + if (vcn > r->vcn) { + /* split fragment. */ + CLST len1 = vcn - r->vcn; + CLST len2 = r->len - len1; + CLST lcn2 = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len1); + + r->len = len1; + + if (!run_add_entry(run, vcn + len, lcn2, len2, false)) + return false; + } + + if (!run_add_entry(run, vcn, SPARSE_LCN, len, false)) + return false; + + return true; +} + /* * run_get_entry - Return index-th mapped region. */ @@ -778,26 +820,36 @@ int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf, CLST next_vcn, vcn, lcn; CLST prev_lcn = 0; CLST evcn1 = svcn + len; + const struct ntfs_run *r, *r_end; int packed_size = 0; size_t i; - bool ok; s64 dlcn; int offset_size, size_size, tmp; - next_vcn = vcn = svcn; - *packed_vcns = 0; if (!len) goto out; - ok = run_lookup_entry(run, vcn, &lcn, &len, &i); + /* Check all required entries [svcn, encv1) available. */ + if (!run_lookup(run, svcn, &i)) + return -ENOENT; + + r_end = run->runs + run->count; + r = run->runs + i; - if (!ok) - goto error; + for (next_vcn = r->vcn + r->len; next_vcn < evcn1; + next_vcn = r->vcn + r->len) { + if (++r >= r_end || r->vcn != next_vcn) + return -ENOENT; + } - if (next_vcn != vcn) - goto error; + /* Repeat cycle above and pack runs. Assume no errors. */ + r = run->runs + i; + len = svcn - r->vcn; + vcn = svcn; + lcn = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len); + len = r->len - len; for (;;) { next_vcn = vcn + len; @@ -846,12 +898,10 @@ int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf, if (packed_size + 1 >= run_buf_size || next_vcn >= evcn1) goto out; - ok = run_get_entry(run, ++i, &vcn, &lcn, &len); - if (!ok) - goto error; - - if (next_vcn != vcn) - goto error; + r += 1; + vcn = r->vcn; + lcn = r->lcn; + len = r->len; } out: @@ -860,9 +910,6 @@ out: run_buf[0] = 0; return packed_size + 1; - -error: - return -EOPNOTSUPP; } /* @@ -1109,3 +1156,28 @@ int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn) *highest_vcn = vcn64 - 1; return 0; } + +/* + * run_clone + * + * Make a copy of run + */ +int run_clone(const struct runs_tree *run, struct runs_tree *new_run) +{ + size_t bytes = run->count * sizeof(struct ntfs_run); + + if (bytes > new_run->allocated) { + struct ntfs_run *new_ptr = kvmalloc(bytes, GFP_KERNEL); + + if (!new_ptr) + return -ENOMEM; + + kvfree(new_run->runs); + new_run->runs = new_ptr; + new_run->allocated = bytes; + } + + memcpy(new_run->runs, run->runs, bytes); + new_run->count = run->count; + return 0; +} diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 0c6de6287737..47012c9bf505 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -30,6 +30,7 @@ #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/log2.h> +#include <linux/minmax.h> #include <linux/module.h> #include <linux/nls.h> #include <linux/seq_file.h> @@ -390,7 +391,7 @@ static int ntfs_fs_reconfigure(struct fs_context *fc) return -EINVAL; } - memcpy(sbi->options, new_opts, sizeof(*new_opts)); + swap(sbi->options, fc->fs_private); return 0; } @@ -870,6 +871,13 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, sb->s_maxbytes = 0xFFFFFFFFull << sbi->cluster_bits; #endif + /* + * Compute the MFT zone at two steps. + * It would be nice if we are able to allocate 1/8 of + * total clusters for MFT but not more then 512 MB. + */ + sbi->zone_max = min_t(CLST, 0x20000000 >> sbi->cluster_bits, clusters >> 3); + err = 0; out: @@ -900,6 +908,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.high = 0; sbi->sb = sb; + sbi->options = fc->fs_private; + fc->fs_private = NULL; sb->s_flags |= SB_NODIRATIME; sb->s_magic = 0x7366746e; // "ntfs" sb->s_op = &ntfs_sops; @@ -1262,8 +1272,6 @@ load_root: goto put_inode_out; } - fc->fs_private = NULL; - return 0; put_inode_out: @@ -1378,7 +1386,7 @@ static const struct fs_context_operations ntfs_context_ops = { /* * ntfs_init_fs_context - Initialize spi and opts * - * This will called when mount/remount. We will first initiliaze + * This will called when mount/remount. We will first initialize * options so that if remount we can use just that. */ static int ntfs_init_fs_context(struct fs_context *fc) @@ -1416,7 +1424,6 @@ static int ntfs_init_fs_context(struct fs_context *fc) mutex_init(&sbi->compress.mtx_lzx); #endif - sbi->options = opts; fc->s_fs_info = sbi; ok: fc->fs_private = opts; diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 5e0e0280e70d..6ae1f56b7358 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -118,7 +118,7 @@ static int ntfs_read_ea(struct ntfs_inode *ni, struct EA_FULL **ea, run_init(&run); - err = attr_load_runs(attr_ea, ni, &run, NULL); + err = attr_load_runs_range(ni, ATTR_EA, NULL, 0, &run, 0, size); if (!err) err = ntfs_read_run_nb(sbi, &run, 0, ea_p, size, NULL); run_close(&run); @@ -444,6 +444,11 @@ update_ea: /* Delete xattr, ATTR_EA */ ni_remove_attr_le(ni, attr, mi, le); } else if (attr->non_res) { + err = attr_load_runs_range(ni, ATTR_EA, NULL, 0, &ea_run, 0, + size); + if (err) + goto out; + err = ntfs_sb_write_run(sbi, &ea_run, 0, ea_all, size, 0); if (err) goto out; @@ -478,8 +483,7 @@ out: } #ifdef CONFIG_NTFS3_FS_POSIX_ACL -static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns, - struct inode *inode, int type, +static struct posix_acl *ntfs_get_acl_ex(struct inode *inode, int type, int locked) { struct ntfs_inode *ni = ntfs_i(inode); @@ -514,7 +518,7 @@ static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns, /* Translate extended attribute to acl. */ if (err >= 0) { - acl = posix_acl_from_xattr(mnt_userns, buf, err); + acl = posix_acl_from_xattr(&init_user_ns, buf, err); } else if (err == -ENODATA) { acl = NULL; } else { @@ -537,8 +541,7 @@ struct posix_acl *ntfs_get_acl(struct inode *inode, int type, bool rcu) if (rcu) return ERR_PTR(-ECHILD); - /* TODO: init_user_ns? */ - return ntfs_get_acl_ex(&init_user_ns, inode, type, 0); + return ntfs_get_acl_ex(inode, type, 0); } static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, @@ -547,28 +550,23 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, { const char *name; size_t size, name_len; - void *value = NULL; - int err = 0; + void *value; + int err; int flags; + umode_t mode; if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; + mode = inode->i_mode; switch (type) { case ACL_TYPE_ACCESS: /* Do not change i_mode if we are in init_acl */ if (acl && !init_acl) { - umode_t mode; - err = posix_acl_update_mode(mnt_userns, inode, &mode, &acl); if (err) - goto out; - - if (inode->i_mode != mode) { - inode->i_mode = mode; - mark_inode_dirty(inode); - } + return err; } name = XATTR_NAME_POSIX_ACL_ACCESS; name_len = sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1; @@ -595,7 +593,7 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, value = kmalloc(size, GFP_NOFS); if (!value) return -ENOMEM; - err = posix_acl_to_xattr(mnt_userns, acl, value, size); + err = posix_acl_to_xattr(&init_user_ns, acl, value, size); if (err < 0) goto out; flags = 0; @@ -604,8 +602,13 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, err = ntfs_set_ea(inode, name, name_len, value, size, flags, 0); if (err == -ENODATA && !size) err = 0; /* Removing non existed xattr. */ - if (!err) + if (!err) { set_cached_acl(inode, type, acl); + if (inode->i_mode != mode) { + inode->i_mode = mode; + mark_inode_dirty(inode); + } + } out: kfree(value); @@ -641,7 +644,7 @@ static int ntfs_xattr_get_acl(struct user_namespace *mnt_userns, if (!acl) return -ENODATA; - err = posix_acl_to_xattr(mnt_userns, acl, buffer, size); + err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return err; @@ -665,12 +668,12 @@ static int ntfs_xattr_set_acl(struct user_namespace *mnt_userns, if (!value) { acl = NULL; } else { - acl = posix_acl_from_xattr(mnt_userns, value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { - err = posix_acl_valid(mnt_userns, acl); + err = posix_acl_valid(&init_user_ns, acl); if (err) goto release_and_out; } @@ -706,13 +709,13 @@ int ntfs_init_acl(struct user_namespace *mnt_userns, struct inode *inode, inode->i_default_acl = NULL; } - if (!acl) - inode->i_acl = NULL; - else { + if (acl) { if (!err) err = ntfs_set_acl_ex(mnt_userns, inode, acl, ACL_TYPE_ACCESS, true); posix_acl_release(acl); + } else { + inode->i_acl = NULL; } return err; diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index e360543ad7e7..8b2020f92b5f 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -296,17 +296,25 @@ static void dlmfs_evict_inode(struct inode *inode) { int status; struct dlmfs_inode_private *ip; + struct user_lock_res *lockres; + int teardown; clear_inode(inode); mlog(0, "inode %lu\n", inode->i_ino); ip = DLMFS_I(inode); + lockres = &ip->ip_lockres; if (S_ISREG(inode->i_mode)) { - status = user_dlm_destroy_lock(&ip->ip_lockres); - if (status < 0) - mlog_errno(status); + spin_lock(&lockres->l_lock); + teardown = !!(lockres->l_flags & USER_LOCK_IN_TEARDOWN); + spin_unlock(&lockres->l_lock); + if (!teardown) { + status = user_dlm_destroy_lock(lockres); + if (status < 0) + mlog_errno(status); + } iput(ip->ip_parent); goto clear_fields; } diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 801e60bab955..c28bc983a7b1 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3403,10 +3403,12 @@ void ocfs2_dlm_shutdown(struct ocfs2_super *osb, ocfs2_lock_res_free(&osb->osb_nfs_sync_lockres); ocfs2_lock_res_free(&osb->osb_orphan_scan.os_lockres); - ocfs2_cluster_disconnect(osb->cconn, hangup_pending); - osb->cconn = NULL; + if (osb->cconn) { + ocfs2_cluster_disconnect(osb->cconn, hangup_pending); + osb->cconn = NULL; - ocfs2_dlm_shutdown_debug(osb); + ocfs2_dlm_shutdown_debug(osb); + } } static int ocfs2_drop_lock(struct ocfs2_super *osb, diff --git a/fs/ocfs2/heartbeat.c b/fs/ocfs2/heartbeat.c index 9099d8fc7599..22da768e65b7 100644 --- a/fs/ocfs2/heartbeat.c +++ b/fs/ocfs2/heartbeat.c @@ -2,12 +2,13 @@ /* * heartbeat.c * - * Register ourselves with the heartbaet service, keep our node maps + * Register ourselves with the heartbeat service, keep our node maps * up to date, and fire off recovery when needed. * * Copyright (C) 2002, 2004 Oracle. All rights reserved. */ +#include <linux/bitmap.h> #include <linux/fs.h> #include <linux/types.h> #include <linux/highmem.h> @@ -24,18 +25,12 @@ #include "buffer_head_io.h" -static inline void __ocfs2_node_map_set_bit(struct ocfs2_node_map *map, - int bit); -static inline void __ocfs2_node_map_clear_bit(struct ocfs2_node_map *map, - int bit); - /* special case -1 for now * TODO: should *really* make sure the calling func never passes -1!! */ static void ocfs2_node_map_init(struct ocfs2_node_map *map) { map->num_nodes = OCFS2_NODE_MAP_MAX_NODES; - memset(map->map, 0, BITS_TO_LONGS(OCFS2_NODE_MAP_MAX_NODES) * - sizeof(unsigned long)); + bitmap_zero(map->map, OCFS2_NODE_MAP_MAX_NODES); } void ocfs2_init_node_maps(struct ocfs2_super *osb) @@ -65,12 +60,6 @@ void ocfs2_do_node_down(int node_num, void *data) ocfs2_recovery_thread(osb, node_num); } -static inline void __ocfs2_node_map_set_bit(struct ocfs2_node_map *map, - int bit) -{ - set_bit(bit, map->map); -} - void ocfs2_node_map_set_bit(struct ocfs2_super *osb, struct ocfs2_node_map *map, int bit) @@ -79,16 +68,10 @@ void ocfs2_node_map_set_bit(struct ocfs2_super *osb, return; BUG_ON(bit >= map->num_nodes); spin_lock(&osb->node_map_lock); - __ocfs2_node_map_set_bit(map, bit); + set_bit(bit, map->map); spin_unlock(&osb->node_map_lock); } -static inline void __ocfs2_node_map_clear_bit(struct ocfs2_node_map *map, - int bit) -{ - clear_bit(bit, map->map); -} - void ocfs2_node_map_clear_bit(struct ocfs2_super *osb, struct ocfs2_node_map *map, int bit) @@ -97,7 +80,7 @@ void ocfs2_node_map_clear_bit(struct ocfs2_super *osb, return; BUG_ON(bit >= map->num_nodes); spin_lock(&osb->node_map_lock); - __ocfs2_node_map_clear_bit(map, bit); + clear_bit(bit, map->map); spin_unlock(&osb->node_map_lock); } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index c75fd54b9185..961d1cf54388 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -197,6 +197,7 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode) * callers. */ if (S_ISDIR(mode)) set_nlink(inode, 2); + mode = mode_strip_sgid(&init_user_ns, dir, mode); inode_init_owner(&init_user_ns, inode, dir, mode); status = dquot_initialize(inode); if (status) diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 0b6f551a342a..dc9f76ab7e13 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -412,7 +412,7 @@ out_unlock: goto out_err; } -/* Write information to global quota file. Expects exlusive lock on quota +/* Write information to global quota file. Expects exclusive lock on quota * file inode and quota info */ static int __ocfs2_global_write_info(struct super_block *sb, int type) { diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 013a727bd7c8..e2cc9eec287c 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1914,8 +1914,7 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) !ocfs2_is_hard_readonly(osb)) hangup_needed = 1; - if (osb->cconn) - ocfs2_dlm_shutdown(osb, hangup_needed); + ocfs2_dlm_shutdown(osb, hangup_needed); ocfs2_blockcheck_stats_debugfs_remove(&osb->osb_ecc_stats); debugfs_remove_recursive(osb->osb_debug_root); diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 2eada97bbd23..e065a5b9a442 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -259,7 +259,7 @@ static int ovl_encode_fh(struct inode *inode, u32 *fid, int *max_len, return FILEID_INVALID; dentry = d_find_any_alias(inode); - if (WARN_ON(!dentry)) + if (!dentry) return FILEID_INVALID; bytes = ovl_dentry_to_fid(ofs, dentry, fid, buflen); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 7922b619f6c8..0fbcb590af84 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -454,14 +454,18 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) return res; } +#ifdef CONFIG_FS_POSIX_ACL /* * Apply the idmapping of the layer to POSIX ACLs. The caller must pass a clone * of the POSIX ACLs retrieved from the lower layer to this function to not * alter the POSIX ACLs for the underlying filesystem. */ -static void ovl_idmap_posix_acl(struct user_namespace *mnt_userns, +static void ovl_idmap_posix_acl(struct inode *realinode, + struct user_namespace *mnt_userns, struct posix_acl *acl) { + struct user_namespace *fs_userns = i_user_ns(realinode); + for (unsigned int i = 0; i < acl->a_count; i++) { vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -469,11 +473,11 @@ static void ovl_idmap_posix_acl(struct user_namespace *mnt_userns, struct posix_acl_entry *e = &acl->a_entries[i]; switch (e->e_tag) { case ACL_USER: - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, e->e_uid); + vfsuid = make_vfsuid(mnt_userns, fs_userns, e->e_uid); e->e_uid = vfsuid_into_kuid(vfsuid); break; case ACL_GROUP: - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, e->e_gid); + vfsgid = make_vfsgid(mnt_userns, fs_userns, e->e_gid); e->e_gid = vfsgid_into_kgid(vfsgid); break; } @@ -497,7 +501,7 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) struct posix_acl *acl, *clone; struct path realpath; - if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode)) + if (!IS_POSIXACL(realinode)) return NULL; /* Careful in RCU walk mode */ @@ -535,7 +539,7 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) if (!clone) clone = ERR_PTR(-ENOMEM); else - ovl_idmap_posix_acl(mnt_user_ns(realpath.mnt), clone); + ovl_idmap_posix_acl(realinode, mnt_user_ns(realpath.mnt), clone); /* * Since we're not in RCU path walk we always need to release the * original ACLs. @@ -543,6 +547,7 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) posix_acl_release(acl); return clone; } +#endif int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags) { diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 65c4346a5b43..69dc577974f8 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -42,7 +42,7 @@ static int ovl_check_redirect(struct path *path, struct ovl_lookup_data *d, * One of the ancestor path elements in an absolute path * lookup in ovl_lookup_layer() could have been opaque and * that will stop further lookup in lower layers (d->stop=true) - * But we have found an absolute redirect in decendant path + * But we have found an absolute redirect in descendant path * element and that should force continue lookup in lower * layers (reset d->stop). */ @@ -648,7 +648,7 @@ static int ovl_get_index_name_fh(struct ovl_fh *fh, struct qstr *name) * If the index dentry for a copy up origin inode is positive, but points * to an inode different than the upper inode, then either the upper inode * has been copied up and not indexed or it was indexed, but since then - * index dir was cleared. Either way, that index cannot be used to indentify + * index dir was cleared. Either way, that index cannot be used to identify * the overlay inode. */ int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin, diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 6ec815b84d48..87759165d32b 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -590,7 +590,13 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); + +#ifdef CONFIG_FS_POSIX_ACL struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu); +#else +#define ovl_get_acl NULL +#endif + int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags); bool ovl_is_private_xattr(struct super_block *sb, const char *name); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index e0a2e0468ee7..ec746d447f1b 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -301,7 +301,7 @@ static int ovl_sync_fs(struct super_block *sb, int wait) /** * ovl_statfs - * @sb: The overlayfs super block + * @dentry: The dentry to query * @buf: The struct kstatfs to fill in with stats * * Get the filesystem statistics. As writes always target the upper layer @@ -349,6 +349,8 @@ static inline int ovl_xino_def(void) /** * ovl_show_options + * @m: the seq_file handle + * @dentry: The dentry to query * * Prints the mount options for a given superblock. * Returns zero; does not fail. @@ -1412,11 +1414,12 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, */ err = ovl_setxattr(ofs, ofs->workdir, OVL_XATTR_OPAQUE, "0", 1); if (err) { + pr_warn("failed to set xattr on upper\n"); ofs->noxattr = true; if (ofs->config.index || ofs->config.metacopy) { ofs->config.index = false; ofs->config.metacopy = false; - pr_warn("upper fs does not support xattr, falling back to index=off,metacopy=off.\n"); + pr_warn("...falling back to index=off,metacopy=off.\n"); } /* * xattr support is required for persistent st_ino. @@ -1424,8 +1427,10 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, */ if (ofs->config.xino == OVL_XINO_AUTO) { ofs->config.xino = OVL_XINO_OFF; - pr_warn("upper fs does not support xattr, falling back to xino=off.\n"); + pr_warn("...falling back to xino=off.\n"); } + if (err == -EPERM && !ofs->config.userxattr) + pr_info("try mounting with 'userxattr' option\n"); err = 0; } else { ovl_removexattr(ofs, ofs->workdir, OVL_XATTR_OPAQUE); @@ -2032,7 +2037,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_stack_depth = 0; sb->s_maxbytes = MAX_LFS_FILESIZE; atomic_long_set(&ofs->last_ino, 1); - /* Assume underlaying fs uses 32bit inodes unless proven otherwise */ + /* Assume underlying fs uses 32bit inodes unless proven otherwise */ if (ofs->config.xino != OVL_XINO_OFF) { ofs->xino_mode = BITS_PER_LONG - 32; if (!ofs->xino_mode) { diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 1d17d7b13dcd..5af33800743e 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -361,6 +361,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; + struct user_namespace *fs_userns = i_user_ns(inode); int found = 0; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -376,7 +377,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, goto check_perm; break; case ACL_USER: - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, + vfsuid = make_vfsuid(mnt_userns, fs_userns, pa->e_uid); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto mask; @@ -390,7 +391,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, } break; case ACL_GROUP: - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, + vfsgid = make_vfsgid(mnt_userns, fs_userns, pa->e_gid); if (vfsgid_in_group_p(vfsgid)) { found = 1; @@ -736,6 +737,7 @@ void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns, { struct posix_acl_xattr_header *header = value; struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end; + struct user_namespace *fs_userns = i_user_ns(inode); int count; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -753,13 +755,13 @@ void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns, switch (le16_to_cpu(entry->e_tag)) { case ACL_USER: uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, uid); + vfsuid = make_vfsuid(mnt_userns, fs_userns, uid); entry->e_id = cpu_to_le32(from_kuid(&init_user_ns, vfsuid_into_kuid(vfsuid))); break; case ACL_GROUP: gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, gid); + vfsgid = make_vfsgid(mnt_userns, fs_userns, gid); entry->e_id = cpu_to_le32(from_kgid(&init_user_ns, vfsgid_into_kgid(vfsgid))); break; @@ -775,6 +777,7 @@ void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns, { struct posix_acl_xattr_header *header = value; struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end; + struct user_namespace *fs_userns = i_user_ns(inode); int count; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -793,13 +796,13 @@ void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns, case ACL_USER: uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); vfsuid = VFSUIDT_INIT(uid); - uid = from_vfsuid(mnt_userns, &init_user_ns, vfsuid); + uid = from_vfsuid(mnt_userns, fs_userns, vfsuid); entry->e_id = cpu_to_le32(from_kuid(&init_user_ns, uid)); break; case ACL_GROUP: gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); vfsgid = VFSGIDT_INIT(gid); - gid = from_vfsgid(mnt_userns, &init_user_ns, vfsgid); + gid = from_vfsgid(mnt_userns, fs_userns, vfsgid); entry->e_id = cpu_to_le32(from_kgid(&init_user_ns, gid)); break; default: diff --git a/fs/proc/array.c b/fs/proc/array.c index eb815759842c..99fcbfda8e25 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -69,7 +69,6 @@ #include <linux/sched/cputime.h> #include <linux/proc_fs.h> #include <linux/ioport.h> -#include <linux/uaccess.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/hugetlb.h> @@ -100,6 +99,10 @@ void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape) { char tcomm[64]; + /* + * Test before PF_KTHREAD because all workqueue worker threads are + * kernel threads. + */ if (p->flags & PF_WQ_WORKER) wq_worker_comm(tcomm, sizeof(tcomm), p); else if (p->flags & PF_KTHREAD) diff --git a/fs/proc/base.c b/fs/proc/base.c index 8dfa36a99c74..93f7e3d971e4 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1885,7 +1885,7 @@ void proc_pid_evict_inode(struct proc_inode *ei) put_pid(pid); } -struct inode *proc_pid_make_inode(struct super_block * sb, +struct inode *proc_pid_make_inode(struct super_block *sb, struct task_struct *task, umode_t mode) { struct inode * inode; @@ -1914,11 +1914,6 @@ struct inode *proc_pid_make_inode(struct super_block * sb, /* Let the pid remember us for quick removal */ ei->pid = pid; - if (S_ISDIR(mode)) { - spin_lock(&pid->lock); - hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes); - spin_unlock(&pid->lock); - } task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); @@ -1931,6 +1926,39 @@ out_unlock: return NULL; } +/* + * Generating an inode and adding it into @pid->inodes, so that task will + * invalidate inode's dentry before being released. + * + * This helper is used for creating dir-type entries under '/proc' and + * '/proc/<tgid>/task'. Other entries(eg. fd, stat) under '/proc/<tgid>' + * can be released by invalidating '/proc/<tgid>' dentry. + * In theory, dentries under '/proc/<tgid>/task' can also be released by + * invalidating '/proc/<tgid>' dentry, we reserve it to handle single + * thread exiting situation: Any one of threads should invalidate its + * '/proc/<tgid>/task/<pid>' dentry before released. + */ +static struct inode *proc_pid_make_base_inode(struct super_block *sb, + struct task_struct *task, umode_t mode) +{ + struct inode *inode; + struct proc_inode *ei; + struct pid *pid; + + inode = proc_pid_make_inode(sb, task, mode); + if (!inode) + return NULL; + + /* Let proc_flush_pid find this directory inode */ + ei = PROC_I(inode); + pid = ei->pid; + spin_lock(&pid->lock); + hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes); + spin_unlock(&pid->lock); + + return inode; +} + int pid_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -3369,7 +3397,8 @@ static struct dentry *proc_pid_instantiate(struct dentry * dentry, { struct inode *inode; - inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); + inode = proc_pid_make_base_inode(dentry->d_sb, task, + S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); @@ -3671,7 +3700,8 @@ static struct dentry *proc_task_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { struct inode *inode; - inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); + inode = proc_pid_make_base_inode(dentry->d_sb, task, + S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 73aeb4e6d32e..f495fdb39151 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -26,8 +26,6 @@ #include <linux/mount.h> #include <linux/bug.h> -#include <linux/uaccess.h> - #include "internal.h" static void proc_evict_inode(struct inode *inode) @@ -214,7 +212,15 @@ static void unuse_pde(struct proc_dir_entry *pde) complete(pde->pde_unload_completion); } -/* pde is locked on entry, unlocked on exit */ +/* + * At most 2 contexts can enter this function: the one doing the last + * close on the descriptor and whoever is deleting PDE itself. + * + * First to enter calls ->proc_release hook and signals its completion + * to the second one which waits and then does nothing. + * + * PDE is locked on entry, unlocked on exit. + */ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) __releases(&pde->pde_unload_lock) { @@ -224,9 +230,6 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) * * rmmod (remove_proc_entry() et al) can't delete an entry and proceed: * "struct file" needs to be available at the right moment. - * - * Therefore, first process to enter this function does ->release() and - * signals its completion to the other process which does nothing. */ if (pdeo->closing) { /* somebody else is doing that, just wait */ @@ -240,10 +243,12 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) pdeo->closing = true; spin_unlock(&pde->pde_unload_lock); + file = pdeo->file; pde->proc_ops->proc_release(file_inode(file), file); + spin_lock(&pde->pde_unload_lock); - /* After ->release. */ + /* Strictly after ->proc_release, see above. */ list_del(&pdeo->lh); c = pdeo->c; spin_unlock(&pde->pde_unload_lock); @@ -489,6 +494,9 @@ static int proc_reg_open(struct inode *inode, struct file *file) typeof_member(struct proc_ops, proc_release) release; struct pde_opener *pdeo; + if (!pde->proc_ops->proc_lseek) + file->f_mode &= ~FMODE_LSEEK; + if (pde_is_permanent(pde)) { open = pde->proc_ops->proc_open; if (open) diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index b38ad552887f..592e6dc7c110 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -15,7 +15,6 @@ #include <linux/fs.h> #include <linux/syslog.h> -#include <linux/uaccess.h> #include <asm/io.h> extern wait_queue_head_t log_wait; diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 13452b32e2bd..4d3493579458 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -21,7 +21,6 @@ #include <linux/seq_file.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> -#include <linux/uaccess.h> #include <asm/tlb.h> #include <asm/div64.h> #include "internal.h" diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 913e5acefbb6..856839b8ae8b 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -8,9 +8,6 @@ * * proc net directory handling functions */ - -#include <linux/uaccess.h> - #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> @@ -353,6 +350,12 @@ static __net_init int proc_net_ns_init(struct net *net) kgid_t gid; int err; + /* + * This PDE acts only as an anchor for /proc/${pid}/net hierarchy. + * Corresponding inode (PDE(inode) == net->proc_net) is never + * instantiated therefore blanket zeroing is fine. + * net->proc_net_stat inode is instantiated normally. + */ err = -ENOMEM; netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!netd) diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c index c69ff191e5d8..5c6a5ceab2f1 100644 --- a/fs/proc/proc_tty.c +++ b/fs/proc/proc_tty.c @@ -4,8 +4,6 @@ * * Copyright 1997, Theodore Ts'o */ - -#include <linux/uaccess.h> #include <linux/module.h> #include <linux/init.h> #include <linux/errno.h> diff --git a/fs/proc/root.c b/fs/proc/root.c index c7e3b1350ef8..3c2ee3eb1138 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -6,9 +6,6 @@ * * proc root directory handling functions */ - -#include <linux/uaccess.h> - #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> @@ -305,6 +302,11 @@ void __init proc_root_init(void) proc_mkdir("bus", NULL); proc_sys_init(); + /* + * Last things last. It is not like userspace processes eager + * to open /proc files exist at this point but register last + * anyway. + */ register_filesystem(&proc_fs_type); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 2d04e3470d4c..4e0023643f8b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -406,6 +406,7 @@ struct mem_size_stats { u64 pss_anon; u64 pss_file; u64 pss_shmem; + u64 pss_dirty; u64 pss_locked; u64 swap_pss; }; @@ -427,6 +428,7 @@ static void smaps_page_accumulate(struct mem_size_stats *mss, mss->pss_locked += pss; if (dirty || PageDirty(page)) { + mss->pss_dirty += pss; if (private) mss->private_dirty += size; else @@ -525,10 +527,12 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; - bool migration = false; + bool migration = false, young = false, dirty = false; if (pte_present(*pte)) { page = vm_normal_page(vma, addr, *pte); + young = pte_young(*pte); + dirty = pte_dirty(*pte); } else if (is_swap_pte(*pte)) { swp_entry_t swpent = pte_to_swp_entry(*pte); @@ -558,8 +562,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), - locked, migration); + smaps_account(mss, page, false, young, dirty, locked, migration); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -808,6 +811,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss, { SEQ_PUT_DEC("Rss: ", mss->resident); SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nPss_Dirty: ", mss->pss_dirty >> PSS_SHIFT); if (rollup_mode) { /* * These are meaningful only for smaps_rollup, otherwise two of @@ -860,7 +864,7 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss, false); seq_printf(m, "THPeligible: %d\n", - transparent_hugepage_active(vma)); + hugepage_vma_check(vma, vma->vm_flags, true, false)); if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); @@ -1792,7 +1796,7 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, return NULL; page = vm_normal_page(vma, addr, pte); - if (!page) + if (!page || is_zone_device_page(page)) return NULL; if (PageReserved(page)) diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 4eaeb645e759..f2aa86c421f2 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -25,7 +25,6 @@ #include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> -#include <linux/uaccess.h> #include <linux/uio.h> #include <linux/cc_platform.h> #include <asm/io.h> diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 49650e54d2f8..846f9455ae22 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -86,7 +86,7 @@ static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) static inline void mangle(struct seq_file *m, const char *s) { - seq_escape(m, s, " \t\n\\"); + seq_escape(m, s, " \t\n\\#"); } static void show_type(struct seq_file *m, struct super_block *sb) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 28966da7834e..0427b44bfee5 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -3002,7 +3002,7 @@ static int __init dquot_init(void) pr_info("VFS: Dquot-cache hash table entries: %ld (order %ld," " %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order)); - if (register_shrinker(&dqcache_shrinker)) + if (register_shrinker(&dqcache_shrinker, "dquota-cache")) panic("Cannot register dquot shrinker"); return 0; diff --git a/fs/read_write.c b/fs/read_write.c index ea59dd0095c2..1a261dcf1778 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -378,14 +378,13 @@ EXPORT_SYMBOL(rw_verify_area); static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { - struct iovec iov = { .iov_base = buf, .iov_len = len }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); - iov_iter_init(&iter, READ, &iov, 1, len); + iov_iter_ubuf(&iter, READ, buf, len); ret = call_read_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); @@ -481,14 +480,13 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { - struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); - iov_iter_init(&iter, WRITE, &iov, 1, len); + iov_iter_ubuf(&iter, WRITE, (void __user *)buf, len); ret = call_write_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); diff --git a/fs/remap_range.c b/fs/remap_range.c index 046a513dbc3a..654912d06862 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -14,6 +14,7 @@ #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> +#include <linux/dax.h> #include "internal.h" #include <linux/uaccess.h> @@ -263,9 +264,11 @@ out_error: * If there's an error, then the usual negative error code is returned. * Otherwise returns 0 with *len set to the request length. */ -int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t *len, unsigned int remap_flags) +int +__generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags, + const struct iomap_ops *dax_read_ops) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); @@ -325,8 +328,18 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, if (remap_flags & REMAP_FILE_DEDUP) { bool is_same = false; - ret = vfs_dedupe_file_range_compare(file_in, pos_in, - file_out, pos_out, *len, &is_same); + if (*len == 0) + return 0; + + if (!IS_DAX(inode_in)) + ret = vfs_dedupe_file_range_compare(file_in, pos_in, + file_out, pos_out, *len, &is_same); + else if (dax_read_ops) + ret = dax_dedupe_file_range_compare(inode_in, pos_in, + inode_out, pos_out, *len, &is_same, + dax_read_ops); + else + return -EINVAL; if (ret) return ret; if (!is_same) @@ -344,6 +357,14 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, return ret; } + +int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags) +{ + return __generic_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags, NULL); +} EXPORT_SYMBOL(generic_remap_file_range_prep); loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, diff --git a/fs/splice.c b/fs/splice.c index 93a2c9bf6249..0878b852b355 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -301,11 +301,9 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, { struct iov_iter to; struct kiocb kiocb; - unsigned int i_head; int ret; iov_iter_pipe(&to, READ, pipe, len); - i_head = to.head; init_sync_kiocb(&kiocb, in); kiocb.ki_pos = *ppos; ret = call_read_iter(in, &kiocb, &to); @@ -313,9 +311,8 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, *ppos = kiocb.ki_pos; file_accessed(in); } else if (ret < 0) { - to.head = i_head; - to.iov_offset = 0; - iov_iter_advance(&to, 0); /* to free what was emitted */ + /* free what was emitted */ + pipe_discard_from(pipe, to.start_head); /* * callers of ->splice_read() expect -EAGAIN on * "can't put anything in there", rather than -EFAULT. @@ -1161,39 +1158,40 @@ static int iter_to_pipe(struct iov_iter *from, }; size_t total = 0; int ret = 0; - bool failed = false; - while (iov_iter_count(from) && !failed) { + while (iov_iter_count(from)) { struct page *pages[16]; - ssize_t copied; + ssize_t left; size_t start; - int n; + int i, n; - copied = iov_iter_get_pages(from, pages, ~0UL, 16, &start); - if (copied <= 0) { - ret = copied; + left = iov_iter_get_pages2(from, pages, ~0UL, 16, &start); + if (left <= 0) { + ret = left; break; } - for (n = 0; copied; n++, start = 0) { - int size = min_t(int, copied, PAGE_SIZE - start); - if (!failed) { - buf.page = pages[n]; - buf.offset = start; - buf.len = size; - ret = add_to_pipe(pipe, &buf); - if (unlikely(ret < 0)) { - failed = true; - } else { - iov_iter_advance(from, ret); - total += ret; - } - } else { - put_page(pages[n]); + n = DIV_ROUND_UP(left + start, PAGE_SIZE); + for (i = 0; i < n; i++) { + int size = min_t(int, left, PAGE_SIZE - start); + + buf.page = pages[i]; + buf.offset = start; + buf.len = size; + ret = add_to_pipe(pipe, &buf); + if (unlikely(ret < 0)) { + iov_iter_revert(from, left); + // this one got dropped by add_to_pipe() + while (++i < n) + put_page(pages[i]); + goto out; } - copied -= size; + total += ret; + left -= size; + start = 0; } } +out: return total ? total : ret; } diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile index 7bd9b8b856d0..477c89a519ee 100644 --- a/fs/squashfs/Makefile +++ b/fs/squashfs/Makefile @@ -5,9 +5,9 @@ obj-$(CONFIG_SQUASHFS) += squashfs.o squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o -squashfs-y += namei.o super.o symlink.o decompressor.o +squashfs-y += namei.o super.o symlink.o decompressor.o page_actor.o squashfs-$(CONFIG_SQUASHFS_FILE_CACHE) += file_cache.o -squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o page_actor.o +squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o squashfs-$(CONFIG_SQUASHFS_DECOMP_SINGLE) += decompressor_single.o squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI) += decompressor_multi.o squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) += decompressor_multi_percpu.o diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 8879d052f96c..833aca92301f 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -34,12 +34,15 @@ static int copy_bio_to_actor(struct bio *bio, struct squashfs_page_actor *actor, int offset, int req_length) { - void *actor_addr = squashfs_first_page(actor); + void *actor_addr; struct bvec_iter_all iter_all = {}; struct bio_vec *bvec = bvec_init_iter_all(&iter_all); int copied_bytes = 0; int actor_offset = 0; + squashfs_actor_nobuff(actor); + actor_addr = squashfs_first_page(actor); + if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) return 0; @@ -49,8 +52,9 @@ static int copy_bio_to_actor(struct bio *bio, bytes_to_copy = min_t(int, bytes_to_copy, req_length - copied_bytes); - memcpy(actor_addr + actor_offset, bvec_virt(bvec) + offset, - bytes_to_copy); + if (!IS_ERR(actor_addr)) + memcpy(actor_addr + actor_offset, bvec_virt(bvec) + + offset, bytes_to_copy); actor_offset += bytes_to_copy; copied_bytes += bytes_to_copy; diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h index 1b9ccfd0aa51..19ab60834389 100644 --- a/fs/squashfs/decompressor.h +++ b/fs/squashfs/decompressor.h @@ -20,6 +20,7 @@ struct squashfs_decompressor { struct bio *, int, int, struct squashfs_page_actor *); int id; char *name; + int alloc_buffer; int supported; }; diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 7f0904b20329..e56510964b22 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -39,6 +39,7 @@ #include "squashfs_fs_sb.h" #include "squashfs_fs_i.h" #include "squashfs.h" +#include "page_actor.h" /* * Locate cache slot in range [offset, index] for specified inode. If @@ -496,7 +497,137 @@ out: return res; } +static int squashfs_readahead_fragment(struct page **page, + unsigned int pages, unsigned int expected) +{ + struct inode *inode = page[0]->mapping->host; + struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb, + squashfs_i(inode)->fragment_block, + squashfs_i(inode)->fragment_size); + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + unsigned int n, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; + + if (buffer->error) + goto out; + + expected += squashfs_i(inode)->fragment_offset; + + for (n = 0; n < pages; n++) { + unsigned int base = (page[n]->index & mask) << PAGE_SHIFT; + unsigned int offset = base + squashfs_i(inode)->fragment_offset; + + if (expected > offset) { + unsigned int avail = min_t(unsigned int, expected - + offset, PAGE_SIZE); + + squashfs_fill_page(page[n], buffer, offset, avail); + } + + unlock_page(page[n]); + put_page(page[n]); + } + +out: + squashfs_cache_put(buffer); + return buffer->error; +} + +static void squashfs_readahead(struct readahead_control *ractl) +{ + struct inode *inode = ractl->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + size_t mask = (1UL << msblk->block_log) - 1; + unsigned short shift = msblk->block_log - PAGE_SHIFT; + loff_t start = readahead_pos(ractl) & ~mask; + size_t len = readahead_length(ractl) + readahead_pos(ractl) - start; + struct squashfs_page_actor *actor; + unsigned int nr_pages = 0; + struct page **pages; + int i, file_end = i_size_read(inode) >> msblk->block_log; + unsigned int max_pages = 1UL << shift; + + readahead_expand(ractl, start, (len | mask) + 1); + + pages = kmalloc_array(max_pages, sizeof(void *), GFP_KERNEL); + if (!pages) + return; + + for (;;) { + pgoff_t index; + int res, bsize; + u64 block = 0; + unsigned int expected; + + nr_pages = __readahead_batch(ractl, pages, max_pages); + if (!nr_pages) + break; + + if (readahead_pos(ractl) >= i_size_read(inode)) + goto skip_pages; + + index = pages[0]->index >> shift; + if ((pages[nr_pages - 1]->index >> shift) != index) + goto skip_pages; + + expected = index == file_end ? + (i_size_read(inode) & (msblk->block_size - 1)) : + msblk->block_size; + + if (index == file_end && squashfs_i(inode)->fragment_block != + SQUASHFS_INVALID_BLK) { + res = squashfs_readahead_fragment(pages, nr_pages, + expected); + if (res) + goto skip_pages; + continue; + } + + bsize = read_blocklist(inode, index, &block); + if (bsize == 0) + goto skip_pages; + + actor = squashfs_page_actor_init_special(msblk, pages, nr_pages, + expected); + if (!actor) + goto skip_pages; + + res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor); + + squashfs_page_actor_free(actor); + + if (res == expected) { + int bytes; + + /* Last page (if present) may have trailing bytes not filled */ + bytes = res % PAGE_SIZE; + if (pages[nr_pages - 1]->index == file_end && bytes) + memzero_page(pages[nr_pages - 1], bytes, + PAGE_SIZE - bytes); + + for (i = 0; i < nr_pages; i++) { + flush_dcache_page(pages[i]); + SetPageUptodate(pages[i]); + } + } + + for (i = 0; i < nr_pages; i++) { + unlock_page(pages[i]); + put_page(pages[i]); + } + } + + kfree(pages); + return; + +skip_pages: + for (i = 0; i < nr_pages; i++) { + unlock_page(pages[i]); + put_page(pages[i]); + } + kfree(pages); +} const struct address_space_operations squashfs_aops = { - .read_folio = squashfs_read_folio + .read_folio = squashfs_read_folio, + .readahead = squashfs_readahead }; diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index a4894cc59447..f1ccad519e28 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -18,9 +18,6 @@ #include "squashfs.h" #include "page_actor.h" -static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, - int pages, struct page **page, int bytes); - /* Read separately compressed datablock directly into page cache */ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, int expected) @@ -33,7 +30,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; int start_index = target_page->index & ~mask; int end_index = start_index | mask; - int i, n, pages, missing_pages, bytes, res = -ENOMEM; + int i, n, pages, bytes, res = -ENOMEM; struct page **page; struct squashfs_page_actor *actor; void *pageaddr; @@ -47,50 +44,38 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, if (page == NULL) return res; - /* - * Create a "page actor" which will kmap and kunmap the - * page cache pages appropriately within the decompressor - */ - actor = squashfs_page_actor_init_special(page, pages, 0); - if (actor == NULL) - goto out; - /* Try to grab all the pages covered by the Squashfs block */ - for (missing_pages = 0, i = 0, n = start_index; i < pages; i++, n++) { + for (i = 0, n = start_index; n <= end_index; n++) { page[i] = (n == target_page->index) ? target_page : grab_cache_page_nowait(target_page->mapping, n); - if (page[i] == NULL) { - missing_pages++; + if (page[i] == NULL) continue; - } if (PageUptodate(page[i])) { unlock_page(page[i]); put_page(page[i]); - page[i] = NULL; - missing_pages++; + continue; } + + i++; } - if (missing_pages) { - /* - * Couldn't get one or more pages, this page has either - * been VM reclaimed, but others are still in the page cache - * and uptodate, or we're racing with another thread in - * squashfs_readpage also trying to grab them. Fall back to - * using an intermediate buffer. - */ - res = squashfs_read_cache(target_page, block, bsize, pages, - page, expected); - if (res < 0) - goto mark_errored; + pages = i; + /* + * Create a "page actor" which will kmap and kunmap the + * page cache pages appropriately within the decompressor + */ + actor = squashfs_page_actor_init_special(msblk, page, pages, expected); + if (actor == NULL) goto out; - } /* Decompress directly into the page cache buffers */ res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor); + + squashfs_page_actor_free(actor); + if (res < 0) goto mark_errored; @@ -99,12 +84,12 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, goto mark_errored; } - /* Last page may have trailing bytes not filled */ + /* Last page (if present) may have trailing bytes not filled */ bytes = res % PAGE_SIZE; - if (bytes) { - pageaddr = kmap_atomic(page[pages - 1]); + if (page[pages - 1]->index == end_index && bytes) { + pageaddr = kmap_local_page(page[pages - 1]); memset(pageaddr + bytes, 0, PAGE_SIZE - bytes); - kunmap_atomic(pageaddr); + kunmap_local(pageaddr); } /* Mark pages as uptodate, unlock and release */ @@ -116,7 +101,6 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, put_page(page[i]); } - kfree(actor); kfree(page); return 0; @@ -135,40 +119,6 @@ mark_errored: } out: - kfree(actor); kfree(page); return res; } - - -static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, - int pages, struct page **page, int bytes) -{ - struct inode *i = target_page->mapping->host; - struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, - block, bsize); - int res = buffer->error, n, offset = 0; - - if (res) { - ERROR("Unable to read page, block %llx, size %x\n", block, - bsize); - goto out; - } - - for (n = 0; n < pages && bytes > 0; n++, - bytes -= PAGE_SIZE, offset += PAGE_SIZE) { - int avail = min_t(int, bytes, PAGE_SIZE); - - if (page[n] == NULL) - continue; - - squashfs_fill_page(page[n], buffer, offset, avail); - unlock_page(page[n]); - if (page[n] != target_page) - put_page(page[n]); - } - -out: - squashfs_cache_put(buffer); - return res; -} diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c index b685b6238316..49797729f143 100644 --- a/fs/squashfs/lz4_wrapper.c +++ b/fs/squashfs/lz4_wrapper.c @@ -119,10 +119,12 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm, buff = stream->output; while (data) { if (bytes <= PAGE_SIZE) { - memcpy(data, buff, bytes); + if (!IS_ERR(data)) + memcpy(data, buff, bytes); break; } - memcpy(data, buff, PAGE_SIZE); + if (!IS_ERR(data)) + memcpy(data, buff, PAGE_SIZE); buff += PAGE_SIZE; bytes -= PAGE_SIZE; data = squashfs_next_page(output); @@ -139,5 +141,6 @@ const struct squashfs_decompressor squashfs_lz4_comp_ops = { .decompress = lz4_uncompress, .id = LZ4_COMPRESSION, .name = "lz4", + .alloc_buffer = 0, .supported = 1 }; diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c index cb510a631968..d216aeefa865 100644 --- a/fs/squashfs/lzo_wrapper.c +++ b/fs/squashfs/lzo_wrapper.c @@ -93,10 +93,12 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm, buff = stream->output; while (data) { if (bytes <= PAGE_SIZE) { - memcpy(data, buff, bytes); + if (!IS_ERR(data)) + memcpy(data, buff, bytes); break; } else { - memcpy(data, buff, PAGE_SIZE); + if (!IS_ERR(data)) + memcpy(data, buff, PAGE_SIZE); buff += PAGE_SIZE; bytes -= PAGE_SIZE; data = squashfs_next_page(output); @@ -116,5 +118,6 @@ const struct squashfs_decompressor squashfs_lzo_comp_ops = { .decompress = lzo_uncompress, .id = LZO_COMPRESSION, .name = "lzo", + .alloc_buffer = 0, .supported = 1 }; diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c index 520d323a99ce..54b93bf4a25c 100644 --- a/fs/squashfs/page_actor.c +++ b/fs/squashfs/page_actor.c @@ -7,6 +7,8 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/pagemap.h> +#include "squashfs_fs_sb.h" +#include "decompressor.h" #include "page_actor.h" /* @@ -50,6 +52,7 @@ struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, actor->buffer = buffer; actor->pages = pages; actor->next_page = 0; + actor->tmp_buffer = NULL; actor->squashfs_first_page = cache_first_page; actor->squashfs_next_page = cache_next_page; actor->squashfs_finish_page = cache_finish_page; @@ -57,40 +60,72 @@ struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, } /* Implementation of page_actor for decompressing directly into page cache. */ +static void *handle_next_page(struct squashfs_page_actor *actor) +{ + int max_pages = (actor->length + PAGE_SIZE - 1) >> PAGE_SHIFT; + + if (actor->returned_pages == max_pages) + return NULL; + + if ((actor->next_page == actor->pages) || + (actor->next_index != actor->page[actor->next_page]->index)) { + actor->next_index++; + actor->returned_pages++; + return actor->alloc_buffer ? actor->tmp_buffer : ERR_PTR(-ENOMEM); + } + + actor->next_index++; + actor->returned_pages++; + return actor->pageaddr = kmap_local_page(actor->page[actor->next_page++]); +} + static void *direct_first_page(struct squashfs_page_actor *actor) { - actor->next_page = 1; - return actor->pageaddr = kmap_atomic(actor->page[0]); + return handle_next_page(actor); } static void *direct_next_page(struct squashfs_page_actor *actor) { - if (actor->pageaddr) - kunmap_atomic(actor->pageaddr); + if (actor->pageaddr) { + kunmap_local(actor->pageaddr); + actor->pageaddr = NULL; + } - return actor->pageaddr = actor->next_page == actor->pages ? NULL : - kmap_atomic(actor->page[actor->next_page++]); + return handle_next_page(actor); } static void direct_finish_page(struct squashfs_page_actor *actor) { if (actor->pageaddr) - kunmap_atomic(actor->pageaddr); + kunmap_local(actor->pageaddr); } -struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page, - int pages, int length) +struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_info *msblk, + struct page **page, int pages, int length) { struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); if (actor == NULL) return NULL; + if (msblk->decompressor->alloc_buffer) { + actor->tmp_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); + + if (actor->tmp_buffer == NULL) { + kfree(actor); + return NULL; + } + } else + actor->tmp_buffer = NULL; + actor->length = length ? : pages * PAGE_SIZE; actor->page = page; actor->pages = pages; actor->next_page = 0; + actor->returned_pages = 0; + actor->next_index = page[0]->index & ~((1 << (msblk->block_log - PAGE_SHIFT)) - 1); actor->pageaddr = NULL; + actor->alloc_buffer = msblk->decompressor->alloc_buffer; actor->squashfs_first_page = direct_first_page; actor->squashfs_next_page = direct_next_page; actor->squashfs_finish_page = direct_finish_page; diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h index 2e3073ace009..95ffbb543d91 100644 --- a/fs/squashfs/page_actor.h +++ b/fs/squashfs/page_actor.h @@ -6,63 +6,34 @@ * Phillip Lougher <phillip@squashfs.org.uk> */ -#ifndef CONFIG_SQUASHFS_FILE_DIRECT -struct squashfs_page_actor { - void **page; - int pages; - int length; - int next_page; -}; - -static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page, - int pages, int length) -{ - struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); - - if (actor == NULL) - return NULL; - - actor->length = length ? : pages * PAGE_SIZE; - actor->page = page; - actor->pages = pages; - actor->next_page = 0; - return actor; -} - -static inline void *squashfs_first_page(struct squashfs_page_actor *actor) -{ - actor->next_page = 1; - return actor->page[0]; -} - -static inline void *squashfs_next_page(struct squashfs_page_actor *actor) -{ - return actor->next_page == actor->pages ? NULL : - actor->page[actor->next_page++]; -} - -static inline void squashfs_finish_page(struct squashfs_page_actor *actor) -{ - /* empty */ -} -#else struct squashfs_page_actor { union { void **buffer; struct page **page; }; void *pageaddr; + void *tmp_buffer; void *(*squashfs_first_page)(struct squashfs_page_actor *); void *(*squashfs_next_page)(struct squashfs_page_actor *); void (*squashfs_finish_page)(struct squashfs_page_actor *); int pages; int length; int next_page; + int alloc_buffer; + int returned_pages; + pgoff_t next_index; }; -extern struct squashfs_page_actor *squashfs_page_actor_init(void **, int, int); -extern struct squashfs_page_actor *squashfs_page_actor_init_special(struct page - **, int, int); +extern struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, + int pages, int length); +extern struct squashfs_page_actor *squashfs_page_actor_init_special( + struct squashfs_sb_info *msblk, + struct page **page, int pages, int length); +static inline void squashfs_page_actor_free(struct squashfs_page_actor *actor) +{ + kfree(actor->tmp_buffer); + kfree(actor); +} static inline void *squashfs_first_page(struct squashfs_page_actor *actor) { return actor->squashfs_first_page(actor); @@ -75,5 +46,8 @@ static inline void squashfs_finish_page(struct squashfs_page_actor *actor) { actor->squashfs_finish_page(actor); } -#endif +static inline void squashfs_actor_nobuff(struct squashfs_page_actor *actor) +{ + actor->alloc_buffer = 0; +} #endif diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 6d594ba2ed28..32565dafa7f3 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -29,7 +29,6 @@ #include <linux/module.h> #include <linux/magic.h> #include <linux/xattr.h> -#include <linux/backing-dev.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" @@ -113,24 +112,6 @@ static const struct squashfs_decompressor *supported_squashfs_filesystem( return decompressor; } -static int squashfs_bdi_init(struct super_block *sb) -{ - int err; - unsigned int major = MAJOR(sb->s_dev); - unsigned int minor = MINOR(sb->s_dev); - - bdi_put(sb->s_bdi); - sb->s_bdi = &noop_backing_dev_info; - - err = super_setup_bdi_name(sb, "squashfs_%u_%u", major, minor); - if (err) - return err; - - sb->s_bdi->ra_pages = 0; - sb->s_bdi->io_pages = 0; - - return 0; -} static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) { @@ -146,20 +127,6 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) TRACE("Entered squashfs_fill_superblock\n"); - /* - * squashfs provides 'backing_dev_info' in order to disable read-ahead. For - * squashfs, I/O is not deferred, it is done immediately in read_folio, - * which means the user would always have to wait their own I/O. So the effect - * of readahead is very weak for squashfs. squashfs_bdi_init will set - * sb->s_bdi->ra_pages and sb->s_bdi->io_pages to 0 and close readahead for - * squashfs. - */ - err = squashfs_bdi_init(sb); - if (err) { - errorf(fc, "squashfs init bdi failed"); - return err; - } - sb->s_fs_info = kzalloc(sizeof(*msblk), GFP_KERNEL); if (sb->s_fs_info == NULL) { ERROR("Failed to allocate squashfs_sb_info\n"); diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c index 68f6d09bb3a2..6c49481a2f8c 100644 --- a/fs/squashfs/xz_wrapper.c +++ b/fs/squashfs/xz_wrapper.c @@ -131,6 +131,10 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, stream->buf.out_pos = 0; stream->buf.out_size = PAGE_SIZE; stream->buf.out = squashfs_first_page(output); + if (IS_ERR(stream->buf.out)) { + error = PTR_ERR(stream->buf.out); + goto finish; + } for (;;) { enum xz_ret xz_err; @@ -156,7 +160,10 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, if (stream->buf.out_pos == stream->buf.out_size) { stream->buf.out = squashfs_next_page(output); - if (stream->buf.out != NULL) { + if (IS_ERR(stream->buf.out)) { + error = PTR_ERR(stream->buf.out); + break; + } else if (stream->buf.out != NULL) { stream->buf.out_pos = 0; total += PAGE_SIZE; } @@ -171,6 +178,7 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, } } +finish: squashfs_finish_page(output); return error ? error : total + stream->buf.out_pos; @@ -183,5 +191,6 @@ const struct squashfs_decompressor squashfs_xz_comp_ops = { .decompress = squashfs_xz_uncompress, .id = XZ_COMPRESSION, .name = "xz", + .alloc_buffer = 1, .supported = 1 }; diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c index a20e9042146b..cbb7afe7bc46 100644 --- a/fs/squashfs/zlib_wrapper.c +++ b/fs/squashfs/zlib_wrapper.c @@ -62,6 +62,11 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, stream->next_out = squashfs_first_page(output); stream->avail_in = 0; + if (IS_ERR(stream->next_out)) { + error = PTR_ERR(stream->next_out); + goto finish; + } + for (;;) { int zlib_err; @@ -85,7 +90,10 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, if (stream->avail_out == 0) { stream->next_out = squashfs_next_page(output); - if (stream->next_out != NULL) + if (IS_ERR(stream->next_out)) { + error = PTR_ERR(stream->next_out); + break; + } else if (stream->next_out != NULL) stream->avail_out = PAGE_SIZE; } @@ -107,6 +115,7 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, } } +finish: squashfs_finish_page(output); if (!error) @@ -122,6 +131,7 @@ const struct squashfs_decompressor squashfs_zlib_comp_ops = { .decompress = zlib_uncompress, .id = ZLIB_COMPRESSION, .name = "zlib", + .alloc_buffer = 1, .supported = 1 }; diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c index c40445dbf38c..0e407c4d8b3b 100644 --- a/fs/squashfs/zstd_wrapper.c +++ b/fs/squashfs/zstd_wrapper.c @@ -80,6 +80,10 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, out_buf.size = PAGE_SIZE; out_buf.dst = squashfs_first_page(output); + if (IS_ERR(out_buf.dst)) { + error = PTR_ERR(out_buf.dst); + goto finish; + } for (;;) { size_t zstd_err; @@ -104,7 +108,10 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, if (out_buf.pos == out_buf.size) { out_buf.dst = squashfs_next_page(output); - if (out_buf.dst == NULL) { + if (IS_ERR(out_buf.dst)) { + error = PTR_ERR(out_buf.dst); + break; + } else if (out_buf.dst == NULL) { /* Shouldn't run out of pages * before stream is done. */ @@ -129,6 +136,8 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, } } +finish: + squashfs_finish_page(output); return error ? error : total_out; @@ -140,5 +149,6 @@ const struct squashfs_decompressor squashfs_zstd_comp_ops = { .decompress = zstd_uncompress, .id = ZSTD_COMPRESSION, .name = "zstd", + .alloc_buffer = 1, .supported = 1 }; diff --git a/fs/super.c b/fs/super.c index 60f57c7bc0a6..734ed584a946 100644 --- a/fs/super.c +++ b/fs/super.c @@ -265,7 +265,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, s->s_shrink.count_objects = super_cache_count; s->s_shrink.batch = 1024; s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE; - if (prealloc_shrinker(&s->s_shrink)) + if (prealloc_shrinker(&s->s_shrink, "sb-%s", type->name)) goto fail; if (list_lru_init_memcg(&s->s_dentry_lru, &s->s_shrink)) goto fail; @@ -423,6 +423,35 @@ bool trylock_super(struct super_block *sb) } /** + * retire_super - prevents superblock from being reused + * @sb: superblock to retire + * + * The function marks superblock to be ignored in superblock test, which + * prevents it from being reused for any new mounts. If the superblock has + * a private bdi, it also unregisters it, but doesn't reduce the refcount + * of the superblock to prevent potential races. The refcount is reduced + * by generic_shutdown_super(). The function can not be called + * concurrently with generic_shutdown_super(). It is safe to call the + * function multiple times, subsequent calls have no effect. + * + * The marker will affect the re-use only for block-device-based + * superblocks. Other superblocks will still get marked if this function + * is used, but that will not affect their reusability. + */ +void retire_super(struct super_block *sb) +{ + WARN_ON(!sb->s_bdev); + down_write(&sb->s_umount); + if (sb->s_iflags & SB_I_PERSB_BDI) { + bdi_unregister(sb->s_bdi); + sb->s_iflags &= ~SB_I_PERSB_BDI; + } + sb->s_iflags |= SB_I_RETIRED; + up_write(&sb->s_umount); +} +EXPORT_SYMBOL(retire_super); + +/** * generic_shutdown_super - common helper for ->kill_sb() * @sb: superblock to kill * @@ -1216,7 +1245,7 @@ static int set_bdev_super_fc(struct super_block *s, struct fs_context *fc) static int test_bdev_super_fc(struct super_block *s, struct fs_context *fc) { - return s->s_bdev == fc->sget_key; + return !(s->s_iflags & SB_I_RETIRED) && s->s_bdev == fc->sget_key; } /** @@ -1288,6 +1317,8 @@ int get_tree_bdev(struct fs_context *fc, } else { s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); + shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", + fc->fs_type->name, s->s_id); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, fc); if (error) { @@ -1307,7 +1338,7 @@ EXPORT_SYMBOL(get_tree_bdev); static int test_bdev_super(struct super_block *s, void *data) { - return (void *)s->s_bdev == data; + return !(s->s_iflags & SB_I_RETIRED) && (void *)s->s_bdev == data; } struct dentry *mount_bdev(struct file_system_type *fs_type, @@ -1363,6 +1394,8 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, } else { s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); + shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", + fs_type->name, s->s_id); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (error) { diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 81d26abf486f..da85b3979195 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -141,6 +141,8 @@ struct tracefs_mount_opts { kuid_t uid; kgid_t gid; umode_t mode; + /* Opt_* bitfield. */ + unsigned int opts; }; enum { @@ -241,6 +243,7 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) kgid_t gid; char *p; + opts->opts = 0; opts->mode = TRACEFS_DEFAULT_MODE; while ((p = strsep(&data, ",")) != NULL) { @@ -275,24 +278,36 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) * but traditionally tracefs has ignored all mount options */ } + + opts->opts |= BIT(token); } return 0; } -static int tracefs_apply_options(struct super_block *sb) +static int tracefs_apply_options(struct super_block *sb, bool remount) { struct tracefs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); struct tracefs_mount_opts *opts = &fsi->mount_opts; - inode->i_mode &= ~S_IALLUGO; - inode->i_mode |= opts->mode; + /* + * On remount, only reset mode/uid/gid if they were provided as mount + * options. + */ + + if (!remount || opts->opts & BIT(Opt_mode)) { + inode->i_mode &= ~S_IALLUGO; + inode->i_mode |= opts->mode; + } - inode->i_uid = opts->uid; + if (!remount || opts->opts & BIT(Opt_uid)) + inode->i_uid = opts->uid; - /* Set all the group ids to the mount option */ - set_gid(sb->s_root, opts->gid); + if (!remount || opts->opts & BIT(Opt_gid)) { + /* Set all the group ids to the mount option */ + set_gid(sb->s_root, opts->gid); + } return 0; } @@ -307,7 +322,7 @@ static int tracefs_remount(struct super_block *sb, int *flags, char *data) if (err) goto fail; - tracefs_apply_options(sb); + tracefs_apply_options(sb, true); fail: return err; @@ -359,7 +374,7 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &tracefs_super_operations; - tracefs_apply_options(sb); + tracefs_apply_options(sb, false); return 0; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 0978d01b0ea4..d0c9a09988bc 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2430,7 +2430,7 @@ static int __init ubifs_init(void) if (!ubifs_inode_slab) return -ENOMEM; - err = register_shrinker(&ubifs_shrinker_info); + err = register_shrinker(&ubifs_shrinker_info, "ubifs-slab"); if (err) goto out_slab; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index de86f5b2859f..175de70e3adf 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1601,6 +1601,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } + /* Reset ptes for the whole vma range if wr-protected */ + if (userfaultfd_wp(vma)) + uffd_wp_range(mm, vma, start, vma_end - start, false); + new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, @@ -1925,10 +1929,8 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; - features = uffdio_api.features; - ret = -EINVAL; - if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) - goto err_out; + /* Ignore unsupported features (userspace built against newer kernel) */ + features = uffdio_api.features & UFFD_API_FEATURES; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index b056cfc6398e..03135a1c31b6 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -106,6 +106,7 @@ xfs-y += xfs_log.o \ xfs_icreate_item.o \ xfs_inode_item.o \ xfs_inode_item_recover.o \ + xfs_iunlink_item.o \ xfs_refcount_item.o \ xfs_rmap_item.o \ xfs_log_recover.o \ @@ -129,6 +130,11 @@ xfs-$(CONFIG_SYSCTL) += xfs_sysctl.o xfs-$(CONFIG_COMPAT) += xfs_ioctl32.o xfs-$(CONFIG_EXPORTFS_BLOCK_OPS) += xfs_pnfs.o +# notify failure +ifeq ($(CONFIG_MEMORY_FAILURE),y) +xfs-$(CONFIG_FS_DAX) += xfs_notify_failure.o +endif + # online scrub/repair ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y) diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 3e920cf1b454..bb0c700afe3c 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -120,18 +120,18 @@ xfs_initialize_perag_data( for (index = 0; index < agcount; index++) { /* - * read the agf, then the agi. This gets us - * all the information we need and populates the - * per-ag structures for us. + * Read the AGF and AGI buffers to populate the per-ag + * structures for us. */ - error = xfs_alloc_pagf_init(mp, NULL, index, 0); - if (error) + pag = xfs_perag_get(mp, index); + error = xfs_alloc_read_agf(pag, NULL, 0, NULL); + if (!error) + error = xfs_ialloc_read_agi(pag, NULL, NULL); + if (error) { + xfs_perag_put(pag); return error; + } - error = xfs_ialloc_pagi_init(mp, NULL, index); - if (error) - return error; - pag = xfs_perag_get(mp, index); ifree += pag->pagi_freecount; ialloc += pag->pagi_count; bfree += pag->pagf_freeblks; @@ -194,17 +194,76 @@ xfs_free_perag( XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0); cancel_delayed_work_sync(&pag->pag_blockgc_work); - xfs_iunlink_destroy(pag); xfs_buf_hash_destroy(pag); call_rcu(&pag->rcu_head, __xfs_free_perag); } } +/* Find the size of the AG, in blocks. */ +static xfs_agblock_t +__xfs_ag_block_count( + struct xfs_mount *mp, + xfs_agnumber_t agno, + xfs_agnumber_t agcount, + xfs_rfsblock_t dblocks) +{ + ASSERT(agno < agcount); + + if (agno < agcount - 1) + return mp->m_sb.sb_agblocks; + return dblocks - (agno * mp->m_sb.sb_agblocks); +} + +xfs_agblock_t +xfs_ag_block_count( + struct xfs_mount *mp, + xfs_agnumber_t agno) +{ + return __xfs_ag_block_count(mp, agno, mp->m_sb.sb_agcount, + mp->m_sb.sb_dblocks); +} + +/* Calculate the first and last possible inode number in an AG. */ +static void +__xfs_agino_range( + struct xfs_mount *mp, + xfs_agblock_t eoag, + xfs_agino_t *first, + xfs_agino_t *last) +{ + xfs_agblock_t bno; + + /* + * Calculate the first inode, which will be in the first + * cluster-aligned block after the AGFL. + */ + bno = round_up(XFS_AGFL_BLOCK(mp) + 1, M_IGEO(mp)->cluster_align); + *first = XFS_AGB_TO_AGINO(mp, bno); + + /* + * Calculate the last inode, which will be at the end of the + * last (aligned) cluster that can be allocated in the AG. + */ + bno = round_down(eoag, M_IGEO(mp)->cluster_align); + *last = XFS_AGB_TO_AGINO(mp, bno) - 1; +} + +void +xfs_agino_range( + struct xfs_mount *mp, + xfs_agnumber_t agno, + xfs_agino_t *first, + xfs_agino_t *last) +{ + return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last); +} + int xfs_initialize_perag( struct xfs_mount *mp, xfs_agnumber_t agcount, + xfs_rfsblock_t dblocks, xfs_agnumber_t *maxagi) { struct xfs_perag *pag; @@ -263,13 +322,18 @@ xfs_initialize_perag( if (error) goto out_remove_pag; - error = xfs_iunlink_init(pag); - if (error) - goto out_hash_destroy; - /* first new pag is fully initialized */ if (first_initialised == NULLAGNUMBER) first_initialised = index; + + /* + * Pre-calculated geometry + */ + pag->block_count = __xfs_ag_block_count(mp, index, agcount, + dblocks); + pag->min_block = XFS_AGFL_BLOCK(mp); + __xfs_agino_range(mp, pag->block_count, &pag->agino_min, + &pag->agino_max); } index = xfs_set_inode_alloc(mp, agcount); @@ -280,8 +344,6 @@ xfs_initialize_perag( mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp); return 0; -out_hash_destroy: - xfs_buf_hash_destroy(pag); out_remove_pag: radix_tree_delete(&mp->m_perag_tree, index); out_free_pag: @@ -293,7 +355,6 @@ out_unwind_new_pags: if (!pag) break; xfs_buf_hash_destroy(pag); - xfs_iunlink_destroy(pag); kmem_free(pag); } return error; @@ -321,12 +382,6 @@ xfs_get_aghdr_buf( return 0; } -static inline bool is_log_ag(struct xfs_mount *mp, struct aghdr_init_data *id) -{ - return mp->m_sb.sb_logstart > 0 && - id->agno == XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart); -} - /* * Generic btree root block init function */ @@ -352,7 +407,7 @@ xfs_freesp_init_recs( arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1); arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks); - if (is_log_ag(mp, id)) { + if (xfs_ag_contains_log(mp, id->agno)) { struct xfs_alloc_rec *nrec; xfs_agblock_t start = XFS_FSB_TO_AGBNO(mp, mp->m_sb.sb_logstart); @@ -479,7 +534,7 @@ xfs_rmaproot_init( } /* account for the log space */ - if (is_log_ag(mp, id)) { + if (xfs_ag_contains_log(mp, id->agno)) { rrec = XFS_RMAP_REC_ADDR(block, be16_to_cpu(block->bb_numrecs) + 1); rrec->rm_startblock = cpu_to_be32( @@ -550,7 +605,7 @@ xfs_agfblock_init( agf->agf_refcount_blocks = cpu_to_be32(1); } - if (is_log_ag(mp, id)) { + if (xfs_ag_contains_log(mp, id->agno)) { int64_t logblocks = mp->m_sb.sb_logblocks; be32_add_cpu(&agf->agf_freeblks, -logblocks); @@ -761,11 +816,11 @@ xfs_ag_init_headers( int xfs_ag_shrink_space( - struct xfs_mount *mp, + struct xfs_perag *pag, struct xfs_trans **tpp, - xfs_agnumber_t agno, xfs_extlen_t delta) { + struct xfs_mount *mp = pag->pag_mount; struct xfs_alloc_arg args = { .tp = *tpp, .mp = mp, @@ -782,14 +837,14 @@ xfs_ag_shrink_space( xfs_agblock_t aglen; int error, err2; - ASSERT(agno == mp->m_sb.sb_agcount - 1); - error = xfs_ialloc_read_agi(mp, *tpp, agno, &agibp); + ASSERT(pag->pag_agno == mp->m_sb.sb_agcount - 1); + error = xfs_ialloc_read_agi(pag, *tpp, &agibp); if (error) return error; agi = agibp->b_addr; - error = xfs_alloc_read_agf(mp, *tpp, agno, 0, &agfbp); + error = xfs_alloc_read_agf(pag, *tpp, 0, &agfbp); if (error) return error; @@ -801,13 +856,14 @@ xfs_ag_shrink_space( if (delta >= aglen) return -EINVAL; - args.fsbno = XFS_AGB_TO_FSB(mp, agno, aglen - delta); + args.fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, aglen - delta); /* * Make sure that the last inode cluster cannot overlap with the new * end of the AG, even if it's sparse. */ - error = xfs_ialloc_check_shrink(*tpp, agno, agibp, aglen - delta); + error = xfs_ialloc_check_shrink(*tpp, pag->pag_agno, agibp, + aglen - delta); if (error) return error; @@ -815,7 +871,7 @@ xfs_ag_shrink_space( * Disable perag reservations so it doesn't cause the allocation request * to fail. We'll reestablish reservation before we return. */ - error = xfs_ag_resv_free(agibp->b_pag); + error = xfs_ag_resv_free(pag); if (error) return error; @@ -844,7 +900,7 @@ xfs_ag_shrink_space( be32_add_cpu(&agi->agi_length, -delta); be32_add_cpu(&agf->agf_length, -delta); - err2 = xfs_ag_resv_init(agibp->b_pag, *tpp); + err2 = xfs_ag_resv_init(pag, *tpp); if (err2) { be32_add_cpu(&agi->agi_length, delta); be32_add_cpu(&agf->agf_length, delta); @@ -868,8 +924,9 @@ xfs_ag_shrink_space( xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH); xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH); return 0; + resv_init_out: - err2 = xfs_ag_resv_init(agibp->b_pag, *tpp); + err2 = xfs_ag_resv_init(pag, *tpp); if (!err2) return error; resv_err: @@ -883,9 +940,8 @@ resv_err: */ int xfs_ag_extend_space( - struct xfs_mount *mp, + struct xfs_perag *pag, struct xfs_trans *tp, - struct aghdr_init_data *id, xfs_extlen_t len) { struct xfs_buf *bp; @@ -893,23 +949,20 @@ xfs_ag_extend_space( struct xfs_agf *agf; int error; - /* - * Change the agi length. - */ - error = xfs_ialloc_read_agi(mp, tp, id->agno, &bp); + ASSERT(pag->pag_agno == pag->pag_mount->m_sb.sb_agcount - 1); + + error = xfs_ialloc_read_agi(pag, tp, &bp); if (error) return error; agi = bp->b_addr; be32_add_cpu(&agi->agi_length, len); - ASSERT(id->agno == mp->m_sb.sb_agcount - 1 || - be32_to_cpu(agi->agi_length) == mp->m_sb.sb_agblocks); xfs_ialloc_log_agi(tp, bp, XFS_AGI_LENGTH); /* * Change agf length. */ - error = xfs_alloc_read_agf(mp, tp, id->agno, 0, &bp); + error = xfs_alloc_read_agf(pag, tp, 0, &bp); if (error) return error; @@ -924,49 +977,49 @@ xfs_ag_extend_space( * XFS_RMAP_OINFO_SKIP_UPDATE is used here to tell the rmap btree that * this doesn't actually exist in the rmap btree. */ - error = xfs_rmap_free(tp, bp, bp->b_pag, - be32_to_cpu(agf->agf_length) - len, + error = xfs_rmap_free(tp, bp, pag, be32_to_cpu(agf->agf_length) - len, len, &XFS_RMAP_OINFO_SKIP_UPDATE); if (error) return error; - return xfs_free_extent(tp, XFS_AGB_TO_FSB(mp, id->agno, + error = xfs_free_extent(tp, XFS_AGB_TO_FSB(pag->pag_mount, pag->pag_agno, be32_to_cpu(agf->agf_length) - len), len, &XFS_RMAP_OINFO_SKIP_UPDATE, XFS_AG_RESV_NONE); + if (error) + return error; + + /* Update perag geometry */ + pag->block_count = be32_to_cpu(agf->agf_length); + __xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min, + &pag->agino_max); + return 0; } /* Retrieve AG geometry. */ int xfs_ag_get_geometry( - struct xfs_mount *mp, - xfs_agnumber_t agno, + struct xfs_perag *pag, struct xfs_ag_geometry *ageo) { struct xfs_buf *agi_bp; struct xfs_buf *agf_bp; struct xfs_agi *agi; struct xfs_agf *agf; - struct xfs_perag *pag; unsigned int freeblks; int error; - if (agno >= mp->m_sb.sb_agcount) - return -EINVAL; - /* Lock the AG headers. */ - error = xfs_ialloc_read_agi(mp, NULL, agno, &agi_bp); + error = xfs_ialloc_read_agi(pag, NULL, &agi_bp); if (error) return error; - error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agf_bp); + error = xfs_alloc_read_agf(pag, NULL, 0, &agf_bp); if (error) goto out_agi; - pag = agi_bp->b_pag; - /* Fill out form. */ memset(ageo, 0, sizeof(*ageo)); - ageo->ag_number = agno; + ageo->ag_number = pag->pag_agno; agi = agi_bp->b_addr; ageo->ag_icount = be32_to_cpu(agi->agi_count); diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h index e411d51c2589..517a138faa66 100644 --- a/fs/xfs/libxfs/xfs_ag.h +++ b/fs/xfs/libxfs/xfs_ag.h @@ -67,6 +67,12 @@ struct xfs_perag { /* for rcu-safe freeing */ struct rcu_head rcu_head; + /* Precalculated geometry info */ + xfs_agblock_t block_count; + xfs_agblock_t min_block; + xfs_agino_t agino_min; + xfs_agino_t agino_max; + #ifdef __KERNEL__ /* -- kernel only structures below this line -- */ @@ -97,17 +103,11 @@ struct xfs_perag { /* background prealloc block trimming */ struct delayed_work pag_blockgc_work; - /* - * Unlinked inode information. This incore information reflects - * data stored in the AGI, so callers must hold the AGI buffer lock - * or have some other means to control concurrency. - */ - struct rhashtable pagi_unlinked_hash; #endif /* __KERNEL__ */ }; int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount, - xfs_agnumber_t *maxagi); + xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi); int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno); void xfs_free_perag(struct xfs_mount *mp); @@ -117,6 +117,56 @@ struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *mp, xfs_agnumber_t agno, void xfs_perag_put(struct xfs_perag *pag); /* + * Per-ag geometry infomation and validation + */ +xfs_agblock_t xfs_ag_block_count(struct xfs_mount *mp, xfs_agnumber_t agno); +void xfs_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno, + xfs_agino_t *first, xfs_agino_t *last); + +static inline bool +xfs_verify_agbno(struct xfs_perag *pag, xfs_agblock_t agbno) +{ + if (agbno >= pag->block_count) + return false; + if (agbno <= pag->min_block) + return false; + return true; +} + +/* + * Verify that an AG inode number pointer neither points outside the AG + * nor points at static metadata. + */ +static inline bool +xfs_verify_agino(struct xfs_perag *pag, xfs_agino_t agino) +{ + if (agino < pag->agino_min) + return false; + if (agino > pag->agino_max) + return false; + return true; +} + +/* + * Verify that an AG inode number pointer neither points outside the AG + * nor points at static metadata, or is NULLAGINO. + */ +static inline bool +xfs_verify_agino_or_null(struct xfs_perag *pag, xfs_agino_t agino) +{ + if (agino == NULLAGINO) + return true; + return xfs_verify_agino(pag, agino); +} + +static inline bool +xfs_ag_contains_log(struct xfs_mount *mp, xfs_agnumber_t agno) +{ + return mp->m_sb.sb_logstart > 0 && + agno == XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart); +} + +/* * Perag iteration APIs */ static inline struct xfs_perag * @@ -168,11 +218,10 @@ struct aghdr_init_data { }; int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id); -int xfs_ag_shrink_space(struct xfs_mount *mp, struct xfs_trans **tpp, - xfs_agnumber_t agno, xfs_extlen_t delta); -int xfs_ag_extend_space(struct xfs_mount *mp, struct xfs_trans *tp, - struct aghdr_init_data *id, xfs_extlen_t len); -int xfs_ag_get_geometry(struct xfs_mount *mp, xfs_agnumber_t agno, - struct xfs_ag_geometry *ageo); +int xfs_ag_shrink_space(struct xfs_perag *pag, struct xfs_trans **tpp, + xfs_extlen_t delta); +int xfs_ag_extend_space(struct xfs_perag *pag, struct xfs_trans *tp, + xfs_extlen_t len); +int xfs_ag_get_geometry(struct xfs_perag *pag, struct xfs_ag_geometry *ageo); #endif /* __LIBXFS_AG_H */ diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index fe94058d4e9e..5af123d13a63 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -322,7 +322,7 @@ out: * address. */ if (has_resv) { - error2 = xfs_alloc_pagf_init(mp, tp, pag->pag_agno, 0); + error2 = xfs_alloc_read_agf(pag, tp, 0, NULL); if (error2) return error2; diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index d3f2886fdc08..e2bdf089c0a3 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -84,7 +84,7 @@ xfs_prealloc_blocks( /* * The number of blocks per AG that we withhold from xfs_mod_fdblocks to * guarantee that we can refill the AGFL prior to allocating space in a nearly - * full AG. Although the the space described by the free space btrees, the + * full AG. Although the space described by the free space btrees, the * blocks used by the freesp btrees themselves, and the blocks owned by the * AGFL are counted in the ondisk fdblocks, it's a mistake to let the ondisk * free space in the AG drop so low that the free space btrees cannot refill an @@ -248,7 +248,7 @@ xfs_alloc_get_rec( int *stat) /* output: success/failure */ { struct xfs_mount *mp = cur->bc_mp; - xfs_agnumber_t agno = cur->bc_ag.pag->pag_agno; + struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; int error; @@ -263,11 +263,11 @@ xfs_alloc_get_rec( goto out_bad_rec; /* check for valid extent range, including overflow */ - if (!xfs_verify_agbno(mp, agno, *bno)) + if (!xfs_verify_agbno(pag, *bno)) goto out_bad_rec; if (*bno > *bno + *len) goto out_bad_rec; - if (!xfs_verify_agbno(mp, agno, *bno + *len - 1)) + if (!xfs_verify_agbno(pag, *bno + *len - 1)) goto out_bad_rec; return 0; @@ -275,7 +275,8 @@ xfs_alloc_get_rec( out_bad_rec: xfs_warn(mp, "%s Freespace BTree record corruption in AG %d detected!", - cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size", agno); + cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size", + pag->pag_agno); xfs_warn(mp, "start block 0x%x block count 0x%x", *bno, *len); return -EFSCORRUPTED; @@ -703,20 +704,19 @@ const struct xfs_buf_ops xfs_agfl_buf_ops = { /* * Read in the allocation group free block array. */ -int /* error */ +int xfs_alloc_read_agfl( - xfs_mount_t *mp, /* mount point structure */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_agnumber_t agno, /* allocation group number */ - struct xfs_buf **bpp) /* buffer for the ag free block array */ + struct xfs_perag *pag, + struct xfs_trans *tp, + struct xfs_buf **bpp) { - struct xfs_buf *bp; /* return value */ - int error; + struct xfs_mount *mp = pag->pag_mount; + struct xfs_buf *bp; + int error; - ASSERT(agno != NULLAGNUMBER); error = xfs_trans_read_buf( mp, tp, mp->m_ddev_targp, - XFS_AG_DADDR(mp, agno, XFS_AGFL_DADDR(mp)), + XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGFL_DADDR(mp)), XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops); if (error) return error; @@ -1075,7 +1075,8 @@ xfs_alloc_ag_vextent_small( be32_to_cpu(agf->agf_flcount) <= args->minleft) goto out; - error = xfs_alloc_get_freelist(args->tp, args->agbp, &fbno, 0); + error = xfs_alloc_get_freelist(args->pag, args->tp, args->agbp, + &fbno, 0); if (error) goto error; if (fbno == NULLAGBLOCK) @@ -2609,7 +2610,7 @@ xfs_alloc_fix_freelist( ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); if (!pag->pagf_init) { - error = xfs_alloc_read_agf(mp, tp, args->agno, flags, &agbp); + error = xfs_alloc_read_agf(pag, tp, flags, &agbp); if (error) { /* Couldn't lock the AGF so skip this AG. */ if (error == -EAGAIN) @@ -2639,7 +2640,7 @@ xfs_alloc_fix_freelist( * Can fail if we're not blocking on locks, and it's held. */ if (!agbp) { - error = xfs_alloc_read_agf(mp, tp, args->agno, flags, &agbp); + error = xfs_alloc_read_agf(pag, tp, flags, &agbp); if (error) { /* Couldn't lock the AGF so skip this AG. */ if (error == -EAGAIN) @@ -2697,7 +2698,7 @@ xfs_alloc_fix_freelist( else targs.oinfo = XFS_RMAP_OINFO_AG; while (!(flags & XFS_ALLOC_FLAG_NOSHRINK) && pag->pagf_flcount > need) { - error = xfs_alloc_get_freelist(tp, agbp, &bno, 0); + error = xfs_alloc_get_freelist(pag, tp, agbp, &bno, 0); if (error) goto out_agbp_relse; @@ -2712,7 +2713,7 @@ xfs_alloc_fix_freelist( targs.alignment = targs.minlen = targs.prod = 1; targs.type = XFS_ALLOCTYPE_THIS_AG; targs.pag = pag; - error = xfs_alloc_read_agfl(mp, tp, targs.agno, &agflbp); + error = xfs_alloc_read_agfl(pag, tp, &agflbp); if (error) goto out_agbp_relse; @@ -2741,7 +2742,7 @@ xfs_alloc_fix_freelist( * Put each allocated block on the list. */ for (bno = targs.agbno; bno < targs.agbno + targs.len; bno++) { - error = xfs_alloc_put_freelist(tp, agbp, + error = xfs_alloc_put_freelist(pag, tp, agbp, agflbp, bno, 0); if (error) goto out_agflbp_relse; @@ -2767,6 +2768,7 @@ out_no_agbp: */ int xfs_alloc_get_freelist( + struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, xfs_agblock_t *bnop, @@ -2779,7 +2781,6 @@ xfs_alloc_get_freelist( int error; uint32_t logflags; struct xfs_mount *mp = tp->t_mountp; - struct xfs_perag *pag; /* * Freelist is empty, give up. @@ -2791,8 +2792,7 @@ xfs_alloc_get_freelist( /* * Read the array of free blocks. */ - error = xfs_alloc_read_agfl(mp, tp, be32_to_cpu(agf->agf_seqno), - &agflbp); + error = xfs_alloc_read_agfl(pag, tp, &agflbp); if (error) return error; @@ -2807,7 +2807,6 @@ xfs_alloc_get_freelist( if (be32_to_cpu(agf->agf_flfirst) == xfs_agfl_size(mp)) agf->agf_flfirst = 0; - pag = agbp->b_pag; ASSERT(!pag->pagf_agflreset); be32_add_cpu(&agf->agf_flcount, -1); pag->pagf_flcount--; @@ -2868,29 +2867,11 @@ xfs_alloc_log_agf( } /* - * Interface for inode allocation to force the pag data to be initialized. - */ -int /* error */ -xfs_alloc_pagf_init( - xfs_mount_t *mp, /* file system mount structure */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_agnumber_t agno, /* allocation group number */ - int flags) /* XFS_ALLOC_FLAGS_... */ -{ - struct xfs_buf *bp; - int error; - - error = xfs_alloc_read_agf(mp, tp, agno, flags, &bp); - if (!error) - xfs_trans_brelse(tp, bp); - return error; -} - -/* * Put the block on the freelist for the allocation group. */ int xfs_alloc_put_freelist( + struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, struct xfs_buf *agflbp, @@ -2899,21 +2880,22 @@ xfs_alloc_put_freelist( { struct xfs_mount *mp = tp->t_mountp; struct xfs_agf *agf = agbp->b_addr; - struct xfs_perag *pag; __be32 *blockp; int error; uint32_t logflags; __be32 *agfl_bno; int startoff; - if (!agflbp && (error = xfs_alloc_read_agfl(mp, tp, - be32_to_cpu(agf->agf_seqno), &agflbp))) - return error; + if (!agflbp) { + error = xfs_alloc_read_agfl(pag, tp, &agflbp); + if (error) + return error; + } + be32_add_cpu(&agf->agf_fllast, 1); if (be32_to_cpu(agf->agf_fllast) == xfs_agfl_size(mp)) agf->agf_fllast = 0; - pag = agbp->b_pag; ASSERT(!pag->pagf_agflreset); be32_add_cpu(&agf->agf_flcount, 1); pag->pagf_flcount++; @@ -3070,61 +3052,57 @@ const struct xfs_buf_ops xfs_agf_buf_ops = { /* * Read in the allocation group header (free/alloc section). */ -int /* error */ +int xfs_read_agf( - struct xfs_mount *mp, /* mount point structure */ - struct xfs_trans *tp, /* transaction pointer */ - xfs_agnumber_t agno, /* allocation group number */ - int flags, /* XFS_BUF_ */ - struct xfs_buf **bpp) /* buffer for the ag freelist header */ + struct xfs_perag *pag, + struct xfs_trans *tp, + int flags, + struct xfs_buf **agfbpp) { - int error; + struct xfs_mount *mp = pag->pag_mount; + int error; - trace_xfs_read_agf(mp, agno); + trace_xfs_read_agf(pag->pag_mount, pag->pag_agno); - ASSERT(agno != NULLAGNUMBER); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, - XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)), - XFS_FSS_TO_BB(mp, 1), flags, bpp, &xfs_agf_buf_ops); + XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGF_DADDR(mp)), + XFS_FSS_TO_BB(mp, 1), flags, agfbpp, &xfs_agf_buf_ops); if (error) return error; - ASSERT(!(*bpp)->b_error); - xfs_buf_set_ref(*bpp, XFS_AGF_REF); + xfs_buf_set_ref(*agfbpp, XFS_AGF_REF); return 0; } /* - * Read in the allocation group header (free/alloc section). + * Read in the allocation group header (free/alloc section) and initialise the + * perag structure if necessary. If the caller provides @agfbpp, then return the + * locked buffer to the caller, otherwise free it. */ -int /* error */ +int xfs_alloc_read_agf( - struct xfs_mount *mp, /* mount point structure */ - struct xfs_trans *tp, /* transaction pointer */ - xfs_agnumber_t agno, /* allocation group number */ - int flags, /* XFS_ALLOC_FLAG_... */ - struct xfs_buf **bpp) /* buffer for the ag freelist header */ + struct xfs_perag *pag, + struct xfs_trans *tp, + int flags, + struct xfs_buf **agfbpp) { - struct xfs_agf *agf; /* ag freelist header */ - struct xfs_perag *pag; /* per allocation group data */ + struct xfs_buf *agfbp; + struct xfs_agf *agf; int error; int allocbt_blks; - trace_xfs_alloc_read_agf(mp, agno); + trace_xfs_alloc_read_agf(pag->pag_mount, pag->pag_agno); /* We don't support trylock when freeing. */ ASSERT((flags & (XFS_ALLOC_FLAG_FREEING | XFS_ALLOC_FLAG_TRYLOCK)) != (XFS_ALLOC_FLAG_FREEING | XFS_ALLOC_FLAG_TRYLOCK)); - ASSERT(agno != NULLAGNUMBER); - error = xfs_read_agf(mp, tp, agno, + error = xfs_read_agf(pag, tp, (flags & XFS_ALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0, - bpp); + &agfbp); if (error) return error; - ASSERT(!(*bpp)->b_error); - agf = (*bpp)->b_addr; - pag = (*bpp)->b_pag; + agf = agfbp->b_addr; if (!pag->pagf_init) { pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks); pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks); @@ -3138,7 +3116,7 @@ xfs_alloc_read_agf( be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]); pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level); pag->pagf_init = 1; - pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf); + pag->pagf_agflreset = xfs_agfl_needs_reset(pag->pag_mount, agf); /* * Update the in-core allocbt counter. Filter out the rmapbt @@ -3148,13 +3126,14 @@ xfs_alloc_read_agf( * counter only tracks non-root blocks. */ allocbt_blks = pag->pagf_btreeblks; - if (xfs_has_rmapbt(mp)) + if (xfs_has_rmapbt(pag->pag_mount)) allocbt_blks -= be32_to_cpu(agf->agf_rmap_blocks) - 1; if (allocbt_blks > 0) - atomic64_add(allocbt_blks, &mp->m_allocbt_blks); + atomic64_add(allocbt_blks, + &pag->pag_mount->m_allocbt_blks); } #ifdef DEBUG - else if (!xfs_is_shutdown(mp)) { + else if (!xfs_is_shutdown(pag->pag_mount)) { ASSERT(pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks)); ASSERT(pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks)); ASSERT(pag->pagf_flcount == be32_to_cpu(agf->agf_flcount)); @@ -3165,6 +3144,10 @@ xfs_alloc_read_agf( be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi])); } #endif + if (agfbpp) + *agfbpp = agfbp; + else + xfs_trans_brelse(tp, agfbp); return 0; } diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 84ca09b2223f..2c3f762dfb58 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -95,6 +95,11 @@ xfs_extlen_t xfs_alloc_longest_free_extent(struct xfs_perag *pag, xfs_extlen_t need, xfs_extlen_t reserved); unsigned int xfs_alloc_min_freelist(struct xfs_mount *mp, struct xfs_perag *pag); +int xfs_alloc_get_freelist(struct xfs_perag *pag, struct xfs_trans *tp, + struct xfs_buf *agfbp, xfs_agblock_t *bnop, int btreeblk); +int xfs_alloc_put_freelist(struct xfs_perag *pag, struct xfs_trans *tp, + struct xfs_buf *agfbp, struct xfs_buf *agflbp, + xfs_agblock_t bno, int btreeblk); /* * Compute and fill in value of m_alloc_maxlevels. @@ -104,17 +109,6 @@ xfs_alloc_compute_maxlevels( struct xfs_mount *mp); /* file system mount structure */ /* - * Get a block from the freelist. - * Returns with the buffer for the block gotten. - */ -int /* error */ -xfs_alloc_get_freelist( - struct xfs_trans *tp, /* transaction pointer */ - struct xfs_buf *agbp, /* buffer containing the agf structure */ - xfs_agblock_t *bnop, /* block address retrieved from freelist */ - int btreeblk); /* destination is a AGF btree */ - -/* * Log the given fields from the agf structure. */ void @@ -124,38 +118,6 @@ xfs_alloc_log_agf( uint32_t fields);/* mask of fields to be logged (XFS_AGF_...) */ /* - * Interface for inode allocation to force the pag data to be initialized. - */ -int /* error */ -xfs_alloc_pagf_init( - struct xfs_mount *mp, /* file system mount structure */ - struct xfs_trans *tp, /* transaction pointer */ - xfs_agnumber_t agno, /* allocation group number */ - int flags); /* XFS_ALLOC_FLAGS_... */ - -/* - * Put the block on the freelist for the allocation group. - */ -int /* error */ -xfs_alloc_put_freelist( - struct xfs_trans *tp, /* transaction pointer */ - struct xfs_buf *agbp, /* buffer for a.g. freelist header */ - struct xfs_buf *agflbp,/* buffer for a.g. free block array */ - xfs_agblock_t bno, /* block being freed */ - int btreeblk); /* owner was a AGF btree */ - -/* - * Read in the allocation group header (free/alloc section). - */ -int /* error */ -xfs_alloc_read_agf( - struct xfs_mount *mp, /* mount point structure */ - struct xfs_trans *tp, /* transaction pointer */ - xfs_agnumber_t agno, /* allocation group number */ - int flags, /* XFS_ALLOC_FLAG_... */ - struct xfs_buf **bpp); /* buffer for the ag freelist header */ - -/* * Allocate an extent (variable-size). */ int /* error */ @@ -206,10 +168,12 @@ xfs_alloc_get_rec( xfs_extlen_t *len, /* output: length of extent */ int *stat); /* output: success/failure */ -int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_agnumber_t agno, int flags, struct xfs_buf **bpp); -int xfs_alloc_read_agfl(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_agnumber_t agno, struct xfs_buf **bpp); +int xfs_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags, + struct xfs_buf **agfbpp); +int xfs_alloc_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags, + struct xfs_buf **agfbpp); +int xfs_alloc_read_agfl(struct xfs_perag *pag, struct xfs_trans *tp, + struct xfs_buf **bpp); int xfs_free_agfl_block(struct xfs_trans *, xfs_agnumber_t, xfs_agblock_t, struct xfs_buf *, struct xfs_owner_info *); int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags); diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index 8c9f73cc0bee..549a3cba0234 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -60,8 +60,8 @@ xfs_allocbt_alloc_block( xfs_agblock_t bno; /* Allocate the new block from the freelist. If we can't, give up. */ - error = xfs_alloc_get_freelist(cur->bc_tp, cur->bc_ag.agbp, - &bno, 1); + error = xfs_alloc_get_freelist(cur->bc_ag.pag, cur->bc_tp, + cur->bc_ag.agbp, &bno, 1); if (error) return error; @@ -71,7 +71,7 @@ xfs_allocbt_alloc_block( } atomic64_inc(&cur->bc_mp->m_allocbt_blks); - xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.agbp->b_pag, bno, 1, false); + xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.pag, bno, 1, false); new->s = cpu_to_be32(bno); @@ -89,7 +89,8 @@ xfs_allocbt_free_block( int error; bno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp)); - error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1); + error = xfs_alloc_put_freelist(cur->bc_ag.pag, cur->bc_tp, agbp, NULL, + bno, 1); if (error) return error; diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 224649a76cbb..e28d93d232de 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -67,12 +67,10 @@ int xfs_inode_hasattr( struct xfs_inode *ip) { - if (!XFS_IFORK_Q(ip)) + if (!xfs_inode_has_attr_fork(ip)) return 0; - if (!ip->i_afp) - return 0; - if (ip->i_afp->if_format == XFS_DINODE_FMT_EXTENTS && - ip->i_afp->if_nextents == 0) + if (ip->i_af.if_format == XFS_DINODE_FMT_EXTENTS && + ip->i_af.if_nextents == 0) return 0; return 1; } @@ -85,7 +83,7 @@ bool xfs_attr_is_leaf( struct xfs_inode *ip) { - struct xfs_ifork *ifp = ip->i_afp; + struct xfs_ifork *ifp = &ip->i_af; struct xfs_iext_cursor icur; struct xfs_bmbt_irec imap; @@ -231,7 +229,7 @@ xfs_attr_get_ilocked( if (!xfs_inode_hasattr(args->dp)) return -ENOATTR; - if (args->dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL) + if (args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) return xfs_attr_shortform_getvalue(args); if (xfs_attr_is_leaf(args->dp)) return xfs_attr_leaf_get(args); @@ -354,7 +352,7 @@ xfs_attr_try_sf_addname( /* * Build initial attribute list (if required). */ - if (dp->i_afp->if_format == XFS_DINODE_FMT_EXTENTS) + if (dp->i_af.if_format == XFS_DINODE_FMT_EXTENTS) xfs_attr_shortform_create(args); error = xfs_attr_shortform_addname(args); @@ -864,7 +862,7 @@ xfs_attr_lookup( if (!xfs_inode_hasattr(dp)) return -ENOATTR; - if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL) + if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) return xfs_attr_sf_findname(args, NULL, NULL); if (xfs_attr_is_leaf(dp)) { @@ -1001,7 +999,7 @@ xfs_attr_set( * If the inode doesn't have an attribute fork, add one. * (inode must not be locked when we call this routine) */ - if (XFS_IFORK_Q(dp) == 0) { + if (xfs_inode_has_attr_fork(dp) == 0) { int sf_size = sizeof(struct xfs_attr_sf_hdr) + xfs_attr_sf_entsize_byname(args->namelen, args->valuelen); @@ -1101,7 +1099,7 @@ static inline int xfs_attr_sf_totsize(struct xfs_inode *dp) { struct xfs_attr_shortform *sf; - sf = (struct xfs_attr_shortform *)dp->i_afp->if_u1.if_data; + sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data; return be16_to_cpu(sf->hdr.totsize); } @@ -1558,7 +1556,7 @@ xfs_attr_node_get( * If not in a transaction, we have to release all the buffers. */ out_release: - for (i = 0; state != NULL && i < state->path.active; i++) { + for (i = 0; i < state->path.active; i++) { xfs_trans_brelse(args->trans, state->path.blk[i].bp); state->path.blk[i].bp = NULL; } diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h index dfb47fa63c6d..81be9b3e4004 100644 --- a/fs/xfs/libxfs/xfs_attr.h +++ b/fs/xfs/libxfs/xfs_attr.h @@ -560,9 +560,9 @@ static inline bool xfs_attr_is_shortform( struct xfs_inode *ip) { - return ip->i_afp->if_format == XFS_DINODE_FMT_LOCAL || - (ip->i_afp->if_format == XFS_DINODE_FMT_EXTENTS && - ip->i_afp->if_nextents == 0); + return ip->i_af.if_format == XFS_DINODE_FMT_LOCAL || + (ip->i_af.if_format == XFS_DINODE_FMT_EXTENTS && + ip->i_af.if_nextents == 0); } static inline enum xfs_delattr_state @@ -573,10 +573,10 @@ xfs_attr_init_add_state(struct xfs_da_args *args) * next state, the attribute fork may be null. This can occur only occur * on a pure remove, but we grab the next state before we check if a * replace operation is being performed. If we are called from any other - * context, i_afp is guaranteed to exist. Hence if the attr fork is + * context, i_af is guaranteed to exist. Hence if the attr fork is * null, we were called from a pure remove operation and so we are done. */ - if (!args->dp->i_afp) + if (!xfs_inode_has_attr_fork(args->dp)) return XFS_DAS_DONE; args->op_flags |= XFS_DA_OP_ADDNAME; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 8f47396f8dd2..beee51ad75ce 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -590,7 +590,7 @@ xfs_attr_shortform_bytesfit( * to real extents, or the delalloc conversion will take care of the * literal area rebalancing. */ - if (bytes <= XFS_IFORK_ASIZE(dp)) + if (bytes <= xfs_inode_attr_fork_size(dp)) return dp->i_forkoff; /* @@ -682,7 +682,7 @@ xfs_attr_shortform_create( struct xfs_da_args *args) { struct xfs_inode *dp = args->dp; - struct xfs_ifork *ifp = dp->i_afp; + struct xfs_ifork *ifp = &dp->i_af; struct xfs_attr_sf_hdr *hdr; trace_xfs_attr_sf_create(args); @@ -719,7 +719,7 @@ xfs_attr_sf_findname( int end; int i; - sf = (struct xfs_attr_shortform *)args->dp->i_afp->if_u1.if_data; + sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data; sfe = &sf->list[0]; end = sf->hdr.count; for (i = 0; i < end; sfe = xfs_attr_sf_nextentry(sfe), @@ -764,7 +764,7 @@ xfs_attr_shortform_add( mp = dp->i_mount; dp->i_forkoff = forkoff; - ifp = dp->i_afp; + ifp = &dp->i_af; ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data; if (xfs_attr_sf_findname(args, &sfe, NULL) == -EEXIST) @@ -797,11 +797,9 @@ xfs_attr_fork_remove( struct xfs_inode *ip, struct xfs_trans *tp) { - ASSERT(ip->i_afp->if_nextents == 0); + ASSERT(ip->i_af.if_nextents == 0); - xfs_idestroy_fork(ip->i_afp); - kmem_cache_free(xfs_ifork_cache, ip->i_afp); - ip->i_afp = NULL; + xfs_ifork_zap_attr(ip); ip->i_forkoff = 0; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } @@ -825,7 +823,7 @@ xfs_attr_sf_removename( dp = args->dp; mp = dp->i_mount; - sf = (struct xfs_attr_shortform *)dp->i_afp->if_u1.if_data; + sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data; error = xfs_attr_sf_findname(args, &sfe, &base); @@ -889,7 +887,7 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args) trace_xfs_attr_sf_lookup(args); - ifp = args->dp->i_afp; + ifp = &args->dp->i_af; ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data; sfe = &sf->list[0]; @@ -917,8 +915,8 @@ xfs_attr_shortform_getvalue( struct xfs_attr_sf_entry *sfe; int i; - ASSERT(args->dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL); - sf = (struct xfs_attr_shortform *)args->dp->i_afp->if_u1.if_data; + ASSERT(args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL); + sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data; sfe = &sf->list[0]; for (i = 0; i < sf->hdr.count; sfe = xfs_attr_sf_nextentry(sfe), i++) { @@ -948,7 +946,7 @@ xfs_attr_shortform_to_leaf( trace_xfs_attr_sf_to_leaf(args); dp = args->dp; - ifp = dp->i_afp; + ifp = &dp->i_af; sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data; size = be16_to_cpu(sf->hdr.totsize); tmpbuffer = kmem_alloc(size, 0); @@ -1055,8 +1053,8 @@ xfs_attr_shortform_verify( int i; int64_t size; - ASSERT(ip->i_afp->if_format == XFS_DINODE_FMT_LOCAL); - ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK); + ASSERT(ip->i_af.if_format == XFS_DINODE_FMT_LOCAL); + ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK); sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data; size = ifp->if_bytes; diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index 7298c148f848..d440393b40eb 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -543,6 +543,7 @@ xfs_attr_rmtval_stale( { struct xfs_mount *mp = ip->i_mount; struct xfs_buf *bp; + int error; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); @@ -550,14 +551,18 @@ xfs_attr_rmtval_stale( XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK)) return -EFSCORRUPTED; - bp = xfs_buf_incore(mp->m_ddev_targp, + error = xfs_buf_incore(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, map->br_startblock), - XFS_FSB_TO_BB(mp, map->br_blockcount), incore_flags); - if (bp) { - xfs_buf_stale(bp); - xfs_buf_relse(bp); + XFS_FSB_TO_BB(mp, map->br_blockcount), + incore_flags, &bp); + if (error) { + if (error == -ENOENT) + return 0; + return error; } + xfs_buf_stale(bp); + xfs_buf_relse(bp); return 0; } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 6833110d1bd4..e56723dc9cd5 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -128,7 +128,7 @@ xfs_bmbt_lookup_first( */ static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); return whichfork != XFS_COW_FORK && ifp->if_format == XFS_DINODE_FMT_EXTENTS && @@ -140,7 +140,7 @@ static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork) */ static inline bool xfs_bmap_wants_extents(struct xfs_inode *ip, int whichfork) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); return whichfork != XFS_COW_FORK && ifp->if_format == XFS_DINODE_FMT_BTREE && @@ -319,7 +319,7 @@ xfs_bmap_check_leaf_extents( int whichfork) /* data or attr fork */ { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_block *block; /* current btree block */ xfs_fsblock_t bno; /* block # of "block" */ struct xfs_buf *bp; /* buffer for "block" */ @@ -538,7 +538,7 @@ xfs_bmap_btree_to_extents( int *logflagsp, /* inode logging flags */ int whichfork) /* data or attr fork */ { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_mount *mp = ip->i_mount; struct xfs_btree_block *rblock = ifp->if_broot; struct xfs_btree_block *cblock;/* child btree block */ @@ -616,7 +616,7 @@ xfs_bmap_extents_to_btree( mp = ip->i_mount; ASSERT(whichfork != XFS_COW_FORK); - ifp = XFS_IFORK_PTR(ip, whichfork); + ifp = xfs_ifork_ptr(ip, whichfork); ASSERT(ifp->if_format == XFS_DINODE_FMT_EXTENTS); /* @@ -745,7 +745,7 @@ xfs_bmap_local_to_extents_empty( struct xfs_inode *ip, int whichfork) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); ASSERT(whichfork != XFS_COW_FORK); ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); @@ -785,7 +785,7 @@ xfs_bmap_local_to_extents( * So sending the data fork of a regular inode is invalid. */ ASSERT(!(S_ISREG(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK)); - ifp = XFS_IFORK_PTR(ip, whichfork); + ifp = xfs_ifork_ptr(ip, whichfork); ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL); if (!ifp->if_bytes) { @@ -880,7 +880,7 @@ xfs_bmap_add_attrfork_btree( mp = ip->i_mount; - if (XFS_BMAP_BMDR_SPACE(block) <= XFS_IFORK_DSIZE(ip)) + if (XFS_BMAP_BMDR_SPACE(block) <= xfs_inode_data_fork_size(ip)) *flags |= XFS_ILOG_DBROOT; else { cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK); @@ -920,7 +920,7 @@ xfs_bmap_add_attrfork_extents( int error; /* error return value */ if (ip->i_df.if_nextents * sizeof(struct xfs_bmbt_rec) <= - XFS_IFORK_DSIZE(ip)) + xfs_inode_data_fork_size(ip)) return 0; cur = NULL; error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, flags, @@ -951,7 +951,7 @@ xfs_bmap_add_attrfork_local( { struct xfs_da_args dargs; /* args for dir/attr code */ - if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip)) + if (ip->i_df.if_bytes <= xfs_inode_data_fork_size(ip)) return 0; if (S_ISDIR(VFS_I(ip)->i_mode)) { @@ -1023,7 +1023,7 @@ xfs_bmap_add_attrfork( int logflags; /* logging flags */ int error; /* error return value */ - ASSERT(XFS_IFORK_Q(ip) == 0); + ASSERT(xfs_inode_has_attr_fork(ip) == 0); mp = ip->i_mount; ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); @@ -1034,16 +1034,15 @@ xfs_bmap_add_attrfork( rsvd, &tp); if (error) return error; - if (XFS_IFORK_Q(ip)) + if (xfs_inode_has_attr_fork(ip)) goto trans_cancel; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); error = xfs_bmap_set_attrforkoff(ip, size, &version); if (error) goto trans_cancel; - ASSERT(ip->i_afp == NULL); - ip->i_afp = xfs_ifork_alloc(XFS_DINODE_FMT_EXTENTS, 0); + xfs_ifork_init_attr(ip, XFS_DINODE_FMT_EXTENTS, 0); logflags = 0; switch (ip->i_df.if_format) { case XFS_DINODE_FMT_LOCAL: @@ -1116,7 +1115,7 @@ xfs_iread_bmbt_block( xfs_extnum_t num_recs; xfs_extnum_t j; int whichfork = cur->bc_ino.whichfork; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); block = xfs_btree_get_block(cur, level, &bp); @@ -1164,7 +1163,7 @@ xfs_iread_extents( int whichfork) { struct xfs_iread_state ir; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_mount *mp = ip->i_mount; struct xfs_btree_cur *cur; int error; @@ -1208,7 +1207,7 @@ xfs_bmap_first_unused( xfs_fileoff_t *first_unused, /* unused block */ int whichfork) /* data or attr fork */ { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec got; struct xfs_iext_cursor icur; xfs_fileoff_t lastaddr = 0; @@ -1255,7 +1254,7 @@ xfs_bmap_last_before( xfs_fileoff_t *last_block, /* last block */ int whichfork) /* data or attr fork */ { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec got; struct xfs_iext_cursor icur; int error; @@ -1289,7 +1288,7 @@ xfs_bmap_last_extent( struct xfs_bmbt_irec *rec, int *is_empty) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_iext_cursor icur; int error; @@ -1355,7 +1354,7 @@ xfs_bmap_last_offset( xfs_fileoff_t *last_block, int whichfork) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec rec; int is_empty; int error; @@ -1389,7 +1388,7 @@ xfs_bmap_add_extent_delay_real( int whichfork) { struct xfs_mount *mp = bma->ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork); struct xfs_bmbt_irec *new = &bma->got; int error; /* error return value */ int i; /* temp state */ @@ -1955,7 +1954,7 @@ xfs_bmap_add_extent_unwritten_real( *logflagsp = 0; cur = *curp; - ifp = XFS_IFORK_PTR(ip, whichfork); + ifp = xfs_ifork_ptr(ip, whichfork); ASSERT(!isnullstartblock(new->br_startblock)); @@ -2480,7 +2479,7 @@ xfs_bmap_add_extent_hole_delay( uint32_t state = xfs_bmap_fork_to_state(whichfork); xfs_filblks_t temp; /* temp for indirect calculations */ - ifp = XFS_IFORK_PTR(ip, whichfork); + ifp = xfs_ifork_ptr(ip, whichfork); ASSERT(isnullstartblock(new->br_startblock)); /* @@ -2616,7 +2615,7 @@ xfs_bmap_add_extent_hole_real( int *logflagsp, uint32_t flags) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_mount *mp = ip->i_mount; struct xfs_btree_cur *cur = *curp; int error; /* error return value */ @@ -3185,7 +3184,8 @@ xfs_bmap_longest_free_extent( pag = xfs_perag_get(mp, ag); if (!pag->pagf_init) { - error = xfs_alloc_pagf_init(mp, tp, ag, XFS_ALLOC_FLAG_TRYLOCK); + error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_TRYLOCK, + NULL); if (error) { /* Couldn't lock the AGF, so skip this AG. */ if (error == -EAGAIN) { @@ -3866,7 +3866,7 @@ xfs_bmapi_read( { struct xfs_mount *mp = ip->i_mount; int whichfork = xfs_bmapi_whichfork(flags); - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec got; xfs_fileoff_t obno; xfs_fileoff_t end; @@ -3959,7 +3959,7 @@ xfs_bmapi_reserve_delalloc( int eof) { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); xfs_extlen_t alen; xfs_extlen_t indlen; int error; @@ -4086,7 +4086,7 @@ xfs_bmapi_allocate( { struct xfs_mount *mp = bma->ip->i_mount; int whichfork = xfs_bmapi_whichfork(bma->flags); - struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork); int tmp_logflags = 0; int error; @@ -4185,7 +4185,7 @@ xfs_bmapi_convert_unwritten( uint32_t flags) { int whichfork = xfs_bmapi_whichfork(flags); - struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork); int tmp_logflags = 0; int error; @@ -4262,7 +4262,7 @@ xfs_bmapi_minleft( struct xfs_inode *ip, int fork) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, fork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, fork); if (tp && tp->t_firstblock != NULLFSBLOCK) return 0; @@ -4283,7 +4283,7 @@ xfs_bmapi_finish( int whichfork, int error) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork); if ((bma->logflags & xfs_ilog_fext(whichfork)) && ifp->if_format != XFS_DINODE_FMT_EXTENTS) @@ -4322,7 +4322,7 @@ xfs_bmapi_write( }; struct xfs_mount *mp = ip->i_mount; int whichfork = xfs_bmapi_whichfork(flags); - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); xfs_fileoff_t end; /* end of mapped file region */ bool eof = false; /* after the end of extents */ int error; /* error return */ @@ -4503,7 +4503,7 @@ xfs_bmapi_convert_delalloc( struct iomap *iomap, unsigned int *seq) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_mount *mp = ip->i_mount; xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); struct xfs_bmalloca bma = { NULL }; @@ -4640,7 +4640,7 @@ xfs_bmapi_remap( int whichfork = xfs_bmapi_whichfork(flags); int logflags = 0, error; - ifp = XFS_IFORK_PTR(ip, whichfork); + ifp = xfs_ifork_ptr(ip, whichfork); ASSERT(len > 0); ASSERT(len <= (xfs_filblks_t)XFS_MAX_BMBT_EXTLEN); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); @@ -4797,7 +4797,7 @@ xfs_bmap_del_extent_delay( struct xfs_bmbt_irec *del) { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec new; int64_t da_old, da_new, da_diff = 0; xfs_fileoff_t del_endoff, got_endoff; @@ -4924,7 +4924,7 @@ xfs_bmap_del_extent_cow( struct xfs_bmbt_irec *del) { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); struct xfs_bmbt_irec new; xfs_fileoff_t del_endoff, got_endoff; uint32_t state = BMAP_COWFORK; @@ -5022,7 +5022,7 @@ xfs_bmap_del_extent_real( mp = ip->i_mount; XFS_STATS_INC(mp, xs_del_exlist); - ifp = XFS_IFORK_PTR(ip, whichfork); + ifp = xfs_ifork_ptr(ip, whichfork); ASSERT(del->br_blockcount > 0); xfs_iext_get_extent(ifp, icur, &got); ASSERT(got.br_startoff <= del->br_startoff); @@ -5288,7 +5288,7 @@ __xfs_bunmapi( whichfork = xfs_bmapi_whichfork(flags); ASSERT(whichfork != XFS_COW_FORK); - ifp = XFS_IFORK_PTR(ip, whichfork); + ifp = xfs_ifork_ptr(ip, whichfork); if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp))) return -EFSCORRUPTED; if (xfs_is_shutdown(mp)) @@ -5629,7 +5629,7 @@ xfs_bmse_merge( struct xfs_btree_cur *cur, int *logflags) /* output */ { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec new; xfs_filblks_t blockcount; int error, i; @@ -5750,7 +5750,7 @@ xfs_bmap_collapse_extents( { int whichfork = XFS_DATA_FORK; struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur = NULL; struct xfs_bmbt_irec got, prev; struct xfs_iext_cursor icur; @@ -5865,7 +5865,7 @@ xfs_bmap_insert_extents( { int whichfork = XFS_DATA_FORK; struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur = NULL; struct xfs_bmbt_irec got, next; struct xfs_iext_cursor icur; @@ -5965,7 +5965,7 @@ xfs_bmap_split_extent( xfs_fileoff_t split_fsb) { int whichfork = XFS_DATA_FORK; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur = NULL; struct xfs_bmbt_irec got; struct xfs_bmbt_irec new; /* split extent */ diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 2b77d45c215f..cfa052d40105 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -304,7 +304,7 @@ xfs_bmbt_get_minrecs( if (level == cur->bc_nlevels - 1) { struct xfs_ifork *ifp; - ifp = XFS_IFORK_PTR(cur->bc_ino.ip, + ifp = xfs_ifork_ptr(cur->bc_ino.ip, cur->bc_ino.whichfork); return xfs_bmbt_maxrecs(cur->bc_mp, @@ -322,7 +322,7 @@ xfs_bmbt_get_maxrecs( if (level == cur->bc_nlevels - 1) { struct xfs_ifork *ifp; - ifp = XFS_IFORK_PTR(cur->bc_ino.ip, + ifp = xfs_ifork_ptr(cur->bc_ino.ip, cur->bc_ino.whichfork); return xfs_bmbt_maxrecs(cur->bc_mp, @@ -550,7 +550,7 @@ xfs_bmbt_init_cursor( struct xfs_inode *ip, /* inode owning the btree */ int whichfork) /* data or attr fork */ { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur; ASSERT(whichfork != XFS_COW_FORK); @@ -564,7 +564,7 @@ xfs_bmbt_init_cursor( if (xfs_has_crc(mp)) cur->bc_flags |= XFS_BTREE_CRC_BLOCKS; - cur->bc_ino.forksize = XFS_IFORK_SIZE(ip, whichfork); + cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork); cur->bc_ino.ip = ip; cur->bc_ino.allocated = 0; cur->bc_ino.flags = 0; @@ -664,7 +664,7 @@ xfs_bmbt_change_owner( ASSERT(tp || buffer_list); ASSERT(!(tp && buffer_list)); - ASSERT(XFS_IFORK_PTR(ip, whichfork)->if_format == XFS_DINODE_FMT_BTREE); + ASSERT(xfs_ifork_ptr(ip, whichfork)->if_format == XFS_DINODE_FMT_BTREE); cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork); cur->bc_ino.flags |= XFS_BTCUR_BMBT_INVALID_OWNER; diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 2eecc49fc1b2..4c16c8c31fcb 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -91,10 +91,9 @@ xfs_btree_check_lblock_siblings( static inline xfs_failaddr_t xfs_btree_check_sblock_siblings( - struct xfs_mount *mp, + struct xfs_perag *pag, struct xfs_btree_cur *cur, int level, - xfs_agnumber_t agno, xfs_agblock_t agbno, __be32 dsibling) { @@ -110,7 +109,7 @@ xfs_btree_check_sblock_siblings( if (!xfs_btree_check_sptr(cur, sibling, level + 1)) return __this_address; } else { - if (!xfs_verify_agbno(mp, agno, sibling)) + if (!xfs_verify_agbno(pag, sibling)) return __this_address; } return NULL; @@ -195,11 +194,11 @@ __xfs_btree_check_sblock( struct xfs_buf *bp) { struct xfs_mount *mp = cur->bc_mp; + struct xfs_perag *pag = cur->bc_ag.pag; xfs_btnum_t btnum = cur->bc_btnum; int crc = xfs_has_crc(mp); xfs_failaddr_t fa; xfs_agblock_t agbno = NULLAGBLOCK; - xfs_agnumber_t agno = NULLAGNUMBER; if (crc) { if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) @@ -217,16 +216,14 @@ __xfs_btree_check_sblock( cur->bc_ops->get_maxrecs(cur, level)) return __this_address; - if (bp) { + if (bp) agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp)); - agno = xfs_daddr_to_agno(mp, xfs_buf_daddr(bp)); - } - fa = xfs_btree_check_sblock_siblings(mp, cur, level, agno, agbno, + fa = xfs_btree_check_sblock_siblings(pag, cur, level, agbno, block->bb_u.s.bb_leftsib); if (!fa) - fa = xfs_btree_check_sblock_siblings(mp, cur, level, agno, - agbno, block->bb_u.s.bb_rightsib); + fa = xfs_btree_check_sblock_siblings(pag, cur, level, agbno, + block->bb_u.s.bb_rightsib); return fa; } @@ -288,7 +285,7 @@ xfs_btree_check_sptr( { if (level <= 0) return false; - return xfs_verify_agbno(cur->bc_mp, cur->bc_ag.pag->pag_agno, agbno); + return xfs_verify_agbno(cur->bc_ag.pag, agbno); } /* @@ -725,7 +722,7 @@ xfs_btree_ifork_ptr( if (cur->bc_flags & XFS_BTREE_STAGING) return cur->bc_ino.ifake->if_fork; - return XFS_IFORK_PTR(cur->bc_ino.ip, cur->bc_ino.whichfork); + return xfs_ifork_ptr(cur->bc_ino.ip, cur->bc_ino.whichfork); } /* @@ -3559,7 +3556,7 @@ xfs_btree_kill_iroot( { int whichfork = cur->bc_ino.whichfork; struct xfs_inode *ip = cur->bc_ino.ip; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_block *block; struct xfs_btree_block *cblock; union xfs_btree_key *kp; @@ -4595,7 +4592,6 @@ xfs_btree_sblock_verify( { struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); - xfs_agnumber_t agno; xfs_agblock_t agbno; xfs_failaddr_t fa; @@ -4604,12 +4600,11 @@ xfs_btree_sblock_verify( return __this_address; /* sibling pointer verification */ - agno = xfs_daddr_to_agno(mp, xfs_buf_daddr(bp)); agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp)); - fa = xfs_btree_check_sblock_siblings(mp, NULL, -1, agno, agbno, + fa = xfs_btree_check_sblock_siblings(bp->b_pag, NULL, -1, agbno, block->bb_u.s.bb_leftsib); if (!fa) - fa = xfs_btree_check_sblock_siblings(mp, NULL, -1, agno, agbno, + fa = xfs_btree_check_sblock_siblings(bp->b_pag, NULL, -1, agbno, block->bb_u.s.bb_rightsib); return fa; } diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 3cd51fa3837b..76eedc2756b3 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -193,7 +193,7 @@ xfs_dir_isempty( ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); if (dp->i_disk_size == 0) /* might happen during shutdown. */ return 1; - if (dp->i_disk_size > XFS_IFORK_DSIZE(dp)) + if (dp->i_disk_size > xfs_inode_data_fork_size(dp)) return 0; sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; return !sfp->count; diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c index df0869bba275..00f960a703b2 100644 --- a/fs/xfs/libxfs/xfs_dir2_block.c +++ b/fs/xfs/libxfs/xfs_dir2_block.c @@ -842,7 +842,7 @@ xfs_dir2_block_removename( * See if the size as a shortform is good enough. */ size = xfs_dir2_block_sfsize(dp, hdr, &sfh); - if (size > XFS_IFORK_DSIZE(dp)) + if (size > xfs_inode_data_fork_size(dp)) return 0; /* @@ -1055,7 +1055,7 @@ xfs_dir2_leaf_to_block( * Now see if the resulting block can be shrunken to shortform. */ size = xfs_dir2_block_sfsize(dp, hdr, &sfh); - if (size > XFS_IFORK_DSIZE(dp)) + if (size > xfs_inode_data_fork_size(dp)) return 0; return xfs_dir2_block_to_sf(args, dbp, size, &sfh); @@ -1071,7 +1071,7 @@ xfs_dir2_sf_to_block( struct xfs_trans *tp = args->trans; struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK); + struct xfs_ifork *ifp = xfs_ifork_ptr(dp, XFS_DATA_FORK); struct xfs_da_geometry *geo = args->geo; xfs_dir2_db_t blkno; /* dir-relative block # (0) */ xfs_dir2_data_hdr_t *hdr; /* block header */ diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 5a97a87eaa20..003812fd7d35 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -237,7 +237,7 @@ xfs_dir2_block_sfsize( (i8count ? /* inumber */ count * XFS_INO64_SIZE : count * XFS_INO32_SIZE); - if (size > XFS_IFORK_DSIZE(dp)) + if (size > xfs_inode_data_fork_size(dp)) return size; /* size value is a failure */ } /* @@ -406,7 +406,7 @@ xfs_dir2_sf_addname( * Won't fit as shortform any more (due to size), * or the pick routine says it won't (due to offset values). */ - if (new_isize > XFS_IFORK_DSIZE(dp) || + if (new_isize > xfs_inode_data_fork_size(dp) || (pick = xfs_dir2_sf_addname_pick(args, objchange, &sfep, &offset)) == 0) { /* @@ -710,7 +710,7 @@ xfs_dir2_sf_verify( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); struct xfs_dir2_sf_hdr *sfp; struct xfs_dir2_sf_entry *sfep; struct xfs_dir2_sf_entry *next_sfep; @@ -1031,7 +1031,7 @@ xfs_dir2_sf_replace_needblock( newsize = dp->i_df.if_bytes + (sfp->count + 1) * XFS_INO64_DIFF; return inum > XFS_DIR2_MAX_SHORT_INUM && - sfp->i8count == 0 && newsize > XFS_IFORK_DSIZE(dp); + sfp->i8count == 0 && newsize > xfs_inode_data_fork_size(dp); } /* diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index afdfc8108c5f..b55bdfa9c8a8 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -704,7 +704,7 @@ struct xfs_agfl { * When the bigtime feature is enabled, ondisk inode timestamps become an * unsigned 64-bit nanoseconds counter. This means that the bigtime inode * timestamp epoch is the start of the classic timestamp range, which is - * Dec 31 20:45:52 UTC 1901. Because the epochs are not the same, callers + * Dec 13 20:45:52 UTC 1901. Because the epochs are not the same, callers * /must/ use the bigtime conversion functions when encoding and decoding raw * timestamps. */ diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index bf2f4bc89193..6cdfd64bc56b 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -105,7 +105,6 @@ xfs_inobt_get_rec( int *stat) { struct xfs_mount *mp = cur->bc_mp; - xfs_agnumber_t agno = cur->bc_ag.pag->pag_agno; union xfs_btree_rec *rec; int error; uint64_t realfree; @@ -116,7 +115,7 @@ xfs_inobt_get_rec( xfs_inobt_btrec_to_irec(mp, rec, irec); - if (!xfs_verify_agino(mp, agno, irec->ir_startino)) + if (!xfs_verify_agino(cur->bc_ag.pag, irec->ir_startino)) goto out_bad_rec; if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT || irec->ir_count > XFS_INODES_PER_CHUNK) @@ -137,7 +136,8 @@ xfs_inobt_get_rec( out_bad_rec: xfs_warn(mp, "%s Inode BTree record corruption in AG %d detected!", - cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free", agno); + cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free", + cur->bc_ag.pag->pag_agno); xfs_warn(mp, "start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x", irec->ir_startino, irec->ir_count, irec->ir_freecount, @@ -1610,7 +1610,7 @@ xfs_dialloc_good_ag( return false; if (!pag->pagi_init) { - error = xfs_ialloc_pagi_init(mp, tp, pag->pag_agno); + error = xfs_ialloc_read_agi(pag, tp, NULL); if (error) return false; } @@ -1621,7 +1621,7 @@ xfs_dialloc_good_ag( return false; if (!pag->pagf_init) { - error = xfs_alloc_pagf_init(mp, tp, pag->pag_agno, flags); + error = xfs_alloc_read_agf(pag, tp, flags, NULL); if (error) return false; } @@ -1679,7 +1679,7 @@ xfs_dialloc_try_ag( * Then read in the AGI buffer and recheck with the AGI buffer * lock held. */ - error = xfs_ialloc_read_agi(pag->pag_mount, *tpp, pag->pag_agno, &agbp); + error = xfs_ialloc_read_agi(pag, *tpp, &agbp); if (error) return error; @@ -2169,7 +2169,7 @@ xfs_difree( /* * Get the allocation group header. */ - error = xfs_ialloc_read_agi(mp, tp, pag->pag_agno, &agbp); + error = xfs_ialloc_read_agi(pag, tp, &agbp); if (error) { xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.", __func__, error); @@ -2215,7 +2215,7 @@ xfs_imap_lookup( int error; int i; - error = xfs_ialloc_read_agi(mp, tp, pag->pag_agno, &agbp); + error = xfs_ialloc_read_agi(pag, tp, &agbp); if (error) { xfs_alert(mp, "%s: xfs_ialloc_read_agi() returned error %d, agno %d", @@ -2571,47 +2571,48 @@ const struct xfs_buf_ops xfs_agi_buf_ops = { */ int xfs_read_agi( - struct xfs_mount *mp, /* file system mount structure */ - struct xfs_trans *tp, /* transaction pointer */ - xfs_agnumber_t agno, /* allocation group number */ - struct xfs_buf **bpp) /* allocation group hdr buf */ + struct xfs_perag *pag, + struct xfs_trans *tp, + struct xfs_buf **agibpp) { + struct xfs_mount *mp = pag->pag_mount; int error; - trace_xfs_read_agi(mp, agno); + trace_xfs_read_agi(pag->pag_mount, pag->pag_agno); - ASSERT(agno != NULLAGNUMBER); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, - XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)), - XFS_FSS_TO_BB(mp, 1), 0, bpp, &xfs_agi_buf_ops); + XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)), + XFS_FSS_TO_BB(mp, 1), 0, agibpp, &xfs_agi_buf_ops); if (error) return error; if (tp) - xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_AGI_BUF); + xfs_trans_buf_set_type(tp, *agibpp, XFS_BLFT_AGI_BUF); - xfs_buf_set_ref(*bpp, XFS_AGI_REF); + xfs_buf_set_ref(*agibpp, XFS_AGI_REF); return 0; } +/* + * Read in the agi and initialise the per-ag data. If the caller supplies a + * @agibpp, return the locked AGI buffer to them, otherwise release it. + */ int xfs_ialloc_read_agi( - struct xfs_mount *mp, /* file system mount structure */ - struct xfs_trans *tp, /* transaction pointer */ - xfs_agnumber_t agno, /* allocation group number */ - struct xfs_buf **bpp) /* allocation group hdr buf */ + struct xfs_perag *pag, + struct xfs_trans *tp, + struct xfs_buf **agibpp) { - struct xfs_agi *agi; /* allocation group header */ - struct xfs_perag *pag; /* per allocation group data */ + struct xfs_buf *agibp; + struct xfs_agi *agi; int error; - trace_xfs_ialloc_read_agi(mp, agno); + trace_xfs_ialloc_read_agi(pag->pag_mount, pag->pag_agno); - error = xfs_read_agi(mp, tp, agno, bpp); + error = xfs_read_agi(pag, tp, &agibp); if (error) return error; - agi = (*bpp)->b_addr; - pag = (*bpp)->b_pag; + agi = agibp->b_addr; if (!pag->pagi_init) { pag->pagi_freecount = be32_to_cpu(agi->agi_freecount); pag->pagi_count = be32_to_cpu(agi->agi_count); @@ -2623,27 +2624,11 @@ xfs_ialloc_read_agi( * we are in the middle of a forced shutdown. */ ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) || - xfs_is_shutdown(mp)); - return 0; -} - -/* - * Read in the agi to initialise the per-ag data in the mount structure - */ -int -xfs_ialloc_pagi_init( - xfs_mount_t *mp, /* file system mount structure */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_agnumber_t agno) /* allocation group number */ -{ - struct xfs_buf *bp = NULL; - int error; - - error = xfs_ialloc_read_agi(mp, tp, agno, &bp); - if (error) - return error; - if (bp) - xfs_trans_brelse(tp, bp); + xfs_is_shutdown(pag->pag_mount)); + if (agibpp) + *agibpp = agibp; + else + xfs_trans_brelse(tp, agibp); return 0; } @@ -2912,8 +2897,7 @@ xfs_ialloc_calc_rootino( * allocation group, or very odd geometries created by old mkfs * versions on very small filesystems. */ - if (mp->m_sb.sb_logstart && - XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == 0) + if (xfs_ag_contains_log(mp, 0)) first_bno += mp->m_sb.sb_logblocks; /* diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index a7705b6a1fd3..9bbbca6ac4ed 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -62,25 +62,10 @@ xfs_ialloc_log_agi( struct xfs_buf *bp, /* allocation group header buffer */ uint32_t fields); /* bitmask of fields to log */ -/* - * Read in the allocation group header (inode allocation section) - */ -int /* error */ -xfs_ialloc_read_agi( - struct xfs_mount *mp, /* file system mount structure */ - struct xfs_trans *tp, /* transaction pointer */ - xfs_agnumber_t agno, /* allocation group number */ - struct xfs_buf **bpp); /* allocation group hdr buf */ - -/* - * Read in the allocation group header to initialise the per-ag data - * in the mount structure - */ -int -xfs_ialloc_pagi_init( - struct xfs_mount *mp, /* file system mount structure */ - struct xfs_trans *tp, /* transaction pointer */ - xfs_agnumber_t agno); /* allocation group number */ +int xfs_read_agi(struct xfs_perag *pag, struct xfs_trans *tp, + struct xfs_buf **agibpp); +int xfs_ialloc_read_agi(struct xfs_perag *pag, struct xfs_trans *tp, + struct xfs_buf **agibpp); /* * Lookup a record by ino in the btree given by cur. @@ -102,8 +87,6 @@ int xfs_ialloc_inode_init(struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_agblock_t length, unsigned int gen); -int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_agnumber_t agno, struct xfs_buf **bpp); union xfs_btree_rec; void xfs_inobt_btrec_to_irec(struct xfs_mount *mp, diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index b2ad2fdc40f5..8c83e265770c 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -683,10 +683,10 @@ xfs_inobt_rec_check_count( static xfs_extlen_t xfs_inobt_max_size( - struct xfs_mount *mp, - xfs_agnumber_t agno) + struct xfs_perag *pag) { - xfs_agblock_t agblocks = xfs_ag_block_count(mp, agno); + struct xfs_mount *mp = pag->pag_mount; + xfs_agblock_t agblocks = pag->block_count; /* Bail out if we're uninitialized, which can happen in mkfs. */ if (M_IGEO(mp)->inobt_mxr[0] == 0) @@ -697,8 +697,7 @@ xfs_inobt_max_size( * never be available for the kinds of things that would require btree * expansion. We therefore can pretend the space isn't there. */ - if (mp->m_sb.sb_logstart && - XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == agno) + if (xfs_ag_contains_log(mp, pag->pag_agno)) agblocks -= mp->m_sb.sb_logblocks; return xfs_btree_calc_size(M_IGEO(mp)->inobt_mnr, @@ -722,7 +721,7 @@ xfs_inobt_cur( ASSERT(*agi_bpp == NULL); ASSERT(*curpp == NULL); - error = xfs_ialloc_read_agi(mp, tp, pag->pag_agno, agi_bpp); + error = xfs_ialloc_read_agi(pag, tp, agi_bpp); if (error) return error; @@ -757,16 +756,15 @@ xfs_inobt_count_blocks( /* Read finobt block count from AGI header. */ static int xfs_finobt_read_blocks( - struct xfs_mount *mp, - struct xfs_trans *tp, struct xfs_perag *pag, + struct xfs_trans *tp, xfs_extlen_t *tree_blocks) { struct xfs_buf *agbp; struct xfs_agi *agi; int error; - error = xfs_ialloc_read_agi(mp, tp, pag->pag_agno, &agbp); + error = xfs_ialloc_read_agi(pag, tp, &agbp); if (error) return error; @@ -794,14 +792,14 @@ xfs_finobt_calc_reserves( return 0; if (xfs_has_inobtcounts(mp)) - error = xfs_finobt_read_blocks(mp, tp, pag, &tree_len); + error = xfs_finobt_read_blocks(pag, tp, &tree_len); else error = xfs_inobt_count_blocks(mp, tp, pag, XFS_BTNUM_FINO, &tree_len); if (error) return error; - *ask += xfs_inobt_max_size(mp, pag->pag_agno); + *ask += xfs_inobt_max_size(pag); *used += tree_len; return 0; } diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 3b1b63f9d886..758aacd8166b 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -10,6 +10,7 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" +#include "xfs_ag.h" #include "xfs_inode.h" #include "xfs_errortag.h" #include "xfs_error.h" @@ -41,14 +42,12 @@ xfs_inode_buf_verify( bool readahead) { struct xfs_mount *mp = bp->b_mount; - xfs_agnumber_t agno; int i; int ni; /* * Validate the magic number and version of every inode in the buffer */ - agno = xfs_daddr_to_agno(mp, xfs_buf_daddr(bp)); ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock; for (i = 0; i < ni; i++) { struct xfs_dinode *dip; @@ -59,7 +58,7 @@ xfs_inode_buf_verify( unlinked_ino = be32_to_cpu(dip->di_next_unlinked); di_ok = xfs_verify_magic16(bp, dip->di_magic) && xfs_dinode_good_version(mp, dip->di_version) && - xfs_verify_agino_or_null(mp, agno, unlinked_ino); + xfs_verify_agino_or_null(bp->b_pag, unlinked_ino); if (unlikely(XFS_TEST_ERROR(!di_ok, mp, XFS_ERRTAG_ITOBP_INOTOBP))) { if (readahead) { @@ -178,7 +177,6 @@ xfs_inode_from_disk( xfs_failaddr_t fa; ASSERT(ip->i_cowfp == NULL); - ASSERT(ip->i_afp == NULL); fa = xfs_dinode_verify(ip->i_mount, ip->i_ino, from); if (fa) { @@ -230,7 +228,8 @@ xfs_inode_from_disk( ip->i_nblocks = be64_to_cpu(from->di_nblocks); ip->i_extsize = be32_to_cpu(from->di_extsize); ip->i_forkoff = from->di_forkoff; - ip->i_diflags = be16_to_cpu(from->di_flags); + ip->i_diflags = be16_to_cpu(from->di_flags); + ip->i_next_unlinked = be32_to_cpu(from->di_next_unlinked); if (from->di_dmevmask || from->di_dmstate) xfs_iflags_set(ip, XFS_IPRESERVE_DM_FIELDS); @@ -286,7 +285,7 @@ xfs_inode_to_disk_iext_counters( { if (xfs_inode_has_large_extent_counts(ip)) { to->di_big_nextents = cpu_to_be64(xfs_ifork_nextents(&ip->i_df)); - to->di_big_anextents = cpu_to_be32(xfs_ifork_nextents(ip->i_afp)); + to->di_big_anextents = cpu_to_be32(xfs_ifork_nextents(&ip->i_af)); /* * We might be upgrading the inode to use larger extent counters * than was previously used. Hence zero the unused field. @@ -294,7 +293,7 @@ xfs_inode_to_disk_iext_counters( to->di_nrext64_pad = cpu_to_be16(0); } else { to->di_nextents = cpu_to_be32(xfs_ifork_nextents(&ip->i_df)); - to->di_anextents = cpu_to_be16(xfs_ifork_nextents(ip->i_afp)); + to->di_anextents = cpu_to_be16(xfs_ifork_nextents(&ip->i_af)); } } @@ -326,7 +325,7 @@ xfs_inode_to_disk( to->di_nblocks = cpu_to_be64(ip->i_nblocks); to->di_extsize = cpu_to_be32(ip->i_extsize); to->di_forkoff = ip->i_forkoff; - to->di_aformat = xfs_ifork_format(ip->i_afp); + to->di_aformat = xfs_ifork_format(&ip->i_af); to->di_flags = cpu_to_be16(ip->i_diflags); if (xfs_has_v3inodes(ip->i_mount)) { diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 1a4cdf550f6d..9327a4f39206 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -35,7 +35,7 @@ xfs_init_local_fork( const void *data, int64_t size) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); int mem_size = size; bool zero_terminate; @@ -102,7 +102,7 @@ xfs_iformat_extents( int whichfork) { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); int state = xfs_bmap_fork_to_state(whichfork); xfs_extnum_t nex = xfs_dfork_nextents(dip, whichfork); int size = nex * sizeof(xfs_bmbt_rec_t); @@ -173,7 +173,7 @@ xfs_iformat_btree( int size; int level; - ifp = XFS_IFORK_PTR(ip, whichfork); + ifp = xfs_ifork_ptr(ip, whichfork); dfp = (xfs_bmdr_block_t *)XFS_DFORK_PTR(dip, whichfork); size = XFS_BMAP_BROOT_SPACE(mp, dfp); nrecs = be16_to_cpu(dfp->bb_numrecs); @@ -276,17 +276,23 @@ xfs_dfork_attr_shortform_size( return be16_to_cpu(atp->hdr.totsize); } -struct xfs_ifork * -xfs_ifork_alloc( +void +xfs_ifork_init_attr( + struct xfs_inode *ip, enum xfs_dinode_fmt format, xfs_extnum_t nextents) { - struct xfs_ifork *ifp; + ip->i_af.if_format = format; + ip->i_af.if_nextents = nextents; +} - ifp = kmem_cache_zalloc(xfs_ifork_cache, GFP_NOFS | __GFP_NOFAIL); - ifp->if_format = format; - ifp->if_nextents = nextents; - return ifp; +void +xfs_ifork_zap_attr( + struct xfs_inode *ip) +{ + xfs_idestroy_fork(&ip->i_af); + memset(&ip->i_af, 0, sizeof(struct xfs_ifork)); + ip->i_af.if_format = XFS_DINODE_FMT_EXTENTS; } int @@ -301,9 +307,9 @@ xfs_iformat_attr_fork( * Initialize the extent count early, as the per-format routines may * depend on it. */ - ip->i_afp = xfs_ifork_alloc(dip->di_aformat, naextents); + xfs_ifork_init_attr(ip, dip->di_aformat, naextents); - switch (ip->i_afp->if_format) { + switch (ip->i_af.if_format) { case XFS_DINODE_FMT_LOCAL: error = xfs_iformat_local(ip, dip, XFS_ATTR_FORK, xfs_dfork_attr_shortform_size(dip)); @@ -323,10 +329,8 @@ xfs_iformat_attr_fork( break; } - if (error) { - kmem_cache_free(xfs_ifork_cache, ip->i_afp); - ip->i_afp = NULL; - } + if (error) + xfs_ifork_zap_attr(ip); return error; } @@ -370,7 +374,7 @@ xfs_iroot_realloc( return; } - ifp = XFS_IFORK_PTR(ip, whichfork); + ifp = xfs_ifork_ptr(ip, whichfork); if (rec_diff > 0) { /* * If there wasn't any memory allocated before, just @@ -400,7 +404,7 @@ xfs_iroot_realloc( (int)new_size); ifp->if_broot_bytes = (int)new_size; ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <= - XFS_IFORK_SIZE(ip, whichfork)); + xfs_inode_fork_size(ip, whichfork)); memmove(np, op, cur_max * (uint)sizeof(xfs_fsblock_t)); return; } @@ -454,7 +458,7 @@ xfs_iroot_realloc( ifp->if_broot_bytes = (int)new_size; if (ifp->if_broot) ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <= - XFS_IFORK_SIZE(ip, whichfork)); + xfs_inode_fork_size(ip, whichfork)); return; } @@ -480,11 +484,11 @@ xfs_idata_realloc( int64_t byte_diff, int whichfork) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); int64_t new_size = ifp->if_bytes + byte_diff; ASSERT(new_size >= 0); - ASSERT(new_size <= XFS_IFORK_SIZE(ip, whichfork)); + ASSERT(new_size <= xfs_inode_fork_size(ip, whichfork)); if (byte_diff == 0) return; @@ -539,7 +543,7 @@ xfs_iextents_copy( int whichfork) { int state = xfs_bmap_fork_to_state(whichfork); - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_iext_cursor icur; struct xfs_bmbt_irec rec; int64_t copied = 0; @@ -591,7 +595,7 @@ xfs_iflush_fork( if (!iip) return; - ifp = XFS_IFORK_PTR(ip, whichfork); + ifp = xfs_ifork_ptr(ip, whichfork); /* * This can happen if we gave up in iformat in an error path, * for the attribute fork. @@ -607,7 +611,7 @@ xfs_iflush_fork( if ((iip->ili_fields & dataflag[whichfork]) && (ifp->if_bytes > 0)) { ASSERT(ifp->if_u1.if_data != NULL); - ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork)); + ASSERT(ifp->if_bytes <= xfs_inode_fork_size(ip, whichfork)); memcpy(cp, ifp->if_u1.if_data, ifp->if_bytes); } break; @@ -626,7 +630,7 @@ xfs_iflush_fork( (ifp->if_broot_bytes > 0)) { ASSERT(ifp->if_broot != NULL); ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <= - XFS_IFORK_SIZE(ip, whichfork)); + xfs_inode_fork_size(ip, whichfork)); xfs_bmbt_to_bmdr(mp, ifp->if_broot, ifp->if_broot_bytes, (xfs_bmdr_block_t *)cp, XFS_DFORK_SIZE(dip, mp, whichfork)); @@ -656,7 +660,7 @@ xfs_iext_state_to_fork( if (state & BMAP_COWFORK) return ip->i_cowfp; else if (state & BMAP_ATTRFORK) - return ip->i_afp; + return &ip->i_af; return &ip->i_df; } @@ -707,18 +711,17 @@ int xfs_ifork_verify_local_attr( struct xfs_inode *ip) { - struct xfs_ifork *ifp = ip->i_afp; + struct xfs_ifork *ifp = &ip->i_af; xfs_failaddr_t fa; - if (!ifp) + if (!xfs_inode_has_attr_fork(ip)) fa = __this_address; else fa = xfs_attr_shortform_verify(ip); if (fa) { xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork", - ifp ? ifp->if_u1.if_data : NULL, - ifp ? ifp->if_bytes : 0, fa); + ifp->if_u1.if_data, ifp->if_bytes, fa); return -EFSCORRUPTED; } @@ -731,7 +734,7 @@ xfs_iext_count_may_overflow( int whichfork, int nr_to_add) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); uint64_t max_exts; uint64_t nr_exts; diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 4f68c1f20beb..d3943d6ad0b9 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -77,28 +77,8 @@ struct xfs_ifork { /* * Fork handling. */ - -#define XFS_IFORK_Q(ip) ((ip)->i_forkoff != 0) -#define XFS_IFORK_BOFF(ip) ((int)((ip)->i_forkoff << 3)) - -#define XFS_IFORK_PTR(ip,w) \ - ((w) == XFS_DATA_FORK ? \ - &(ip)->i_df : \ - ((w) == XFS_ATTR_FORK ? \ - (ip)->i_afp : \ - (ip)->i_cowfp)) -#define XFS_IFORK_DSIZE(ip) \ - (XFS_IFORK_Q(ip) ? XFS_IFORK_BOFF(ip) : XFS_LITINO((ip)->i_mount)) -#define XFS_IFORK_ASIZE(ip) \ - (XFS_IFORK_Q(ip) ? XFS_LITINO((ip)->i_mount) - XFS_IFORK_BOFF(ip) : 0) -#define XFS_IFORK_SIZE(ip,w) \ - ((w) == XFS_DATA_FORK ? \ - XFS_IFORK_DSIZE(ip) : \ - ((w) == XFS_ATTR_FORK ? \ - XFS_IFORK_ASIZE(ip) : \ - 0)) #define XFS_IFORK_MAXEXT(ip, w) \ - (XFS_IFORK_SIZE(ip, w) / sizeof(xfs_bmbt_rec_t)) + (xfs_inode_fork_size(ip, w) / sizeof(xfs_bmbt_rec_t)) static inline bool xfs_ifork_has_extents(struct xfs_ifork *ifp) { @@ -179,8 +159,9 @@ xfs_dfork_nextents( return 0; } -struct xfs_ifork *xfs_ifork_alloc(enum xfs_dinode_fmt format, - xfs_extnum_t nextents); +void xfs_ifork_zap_attr(struct xfs_inode *ip); +void xfs_ifork_init_attr(struct xfs_inode *ip, enum xfs_dinode_fmt format, + xfs_extnum_t nextents); struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state); int xfs_iformat_data_fork(struct xfs_inode *, struct xfs_dinode *); diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 97e9e6020596..64b910caafaa 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -111,7 +111,7 @@ xfs_refcount_get_rec( int *stat) { struct xfs_mount *mp = cur->bc_mp; - xfs_agnumber_t agno = cur->bc_ag.pag->pag_agno; + struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; int error; xfs_agblock_t realstart; @@ -121,8 +121,6 @@ xfs_refcount_get_rec( return error; xfs_refcount_btrec_to_irec(rec, irec); - - agno = cur->bc_ag.pag->pag_agno; if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN) goto out_bad_rec; @@ -137,22 +135,23 @@ xfs_refcount_get_rec( } /* check for valid extent range, including overflow */ - if (!xfs_verify_agbno(mp, agno, realstart)) + if (!xfs_verify_agbno(pag, realstart)) goto out_bad_rec; if (realstart > realstart + irec->rc_blockcount) goto out_bad_rec; - if (!xfs_verify_agbno(mp, agno, realstart + irec->rc_blockcount - 1)) + if (!xfs_verify_agbno(pag, realstart + irec->rc_blockcount - 1)) goto out_bad_rec; if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT) goto out_bad_rec; - trace_xfs_refcount_get(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec); + trace_xfs_refcount_get(cur->bc_mp, pag->pag_agno, irec); return 0; out_bad_rec: xfs_warn(mp, - "Refcount BTree record corruption in AG %d detected!", agno); + "Refcount BTree record corruption in AG %d detected!", + pag->pag_agno); xfs_warn(mp, "Start block 0x%x, block count 0x%x, references 0x%x", irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount); @@ -1177,8 +1176,8 @@ xfs_refcount_finish_one( *pcur = NULL; } if (rcur == NULL) { - error = xfs_alloc_read_agf(tp->t_mountp, tp, pag->pag_agno, - XFS_ALLOC_FLAG_FREEING, &agbp); + error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_FREEING, + &agbp); if (error) goto out_drop; @@ -1710,7 +1709,7 @@ xfs_refcount_recover_cow_leftovers( if (error) return error; - error = xfs_alloc_read_agf(mp, tp, pag->pag_agno, 0, &agbp); + error = xfs_alloc_read_agf(pag, tp, 0, &agbp); if (error) goto out_trans; cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index d14c1720b0fb..316c1ec0c3c2 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -493,7 +493,7 @@ xfs_refcountbt_calc_reserves( if (!xfs_has_reflink(mp)) return 0; - error = xfs_alloc_read_agf(mp, tp, pag->pag_agno, 0, &agbp); + error = xfs_alloc_read_agf(pag, tp, 0, &agbp); if (error) return error; @@ -507,8 +507,7 @@ xfs_refcountbt_calc_reserves( * never be available for the kinds of things that would require btree * expansion. We therefore can pretend the space isn't there. */ - if (mp->m_sb.sb_logstart && - XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == pag->pag_agno) + if (xfs_ag_contains_log(mp, pag->pag_agno)) agblocks -= mp->m_sb.sb_logblocks; *ask += xfs_refcountbt_max_size(mp, agblocks); diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 2845019d31da..094dfc897ebc 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -215,7 +215,7 @@ xfs_rmap_get_rec( int *stat) { struct xfs_mount *mp = cur->bc_mp; - xfs_agnumber_t agno = cur->bc_ag.pag->pag_agno; + struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; int error; @@ -235,12 +235,12 @@ xfs_rmap_get_rec( goto out_bad_rec; } else { /* check for valid extent range, including overflow */ - if (!xfs_verify_agbno(mp, agno, irec->rm_startblock)) + if (!xfs_verify_agbno(pag, irec->rm_startblock)) goto out_bad_rec; if (irec->rm_startblock > irec->rm_startblock + irec->rm_blockcount) goto out_bad_rec; - if (!xfs_verify_agbno(mp, agno, + if (!xfs_verify_agbno(pag, irec->rm_startblock + irec->rm_blockcount - 1)) goto out_bad_rec; } @@ -254,7 +254,7 @@ xfs_rmap_get_rec( out_bad_rec: xfs_warn(mp, "Reverse Mapping BTree record corruption in AG %d detected!", - agno); + pag->pag_agno); xfs_warn(mp, "Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x", irec->rm_owner, irec->rm_flags, irec->rm_startblock, diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index 69e104d0277f..7f83f62e51e0 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -90,7 +90,7 @@ xfs_rmapbt_alloc_block( xfs_agblock_t bno; /* Allocate the new block from the freelist. If we can't, give up. */ - error = xfs_alloc_get_freelist(cur->bc_tp, cur->bc_ag.agbp, + error = xfs_alloc_get_freelist(pag, cur->bc_tp, cur->bc_ag.agbp, &bno, 1); if (error) return error; @@ -129,7 +129,7 @@ xfs_rmapbt_free_block( bno, 1); be32_add_cpu(&agf->agf_rmap_blocks, -1); xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS); - error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1); + error = xfs_alloc_put_freelist(pag, cur->bc_tp, agbp, NULL, bno, 1); if (error) return error; @@ -652,7 +652,7 @@ xfs_rmapbt_calc_reserves( if (!xfs_has_rmapbt(mp)) return 0; - error = xfs_alloc_read_agf(mp, tp, pag->pag_agno, 0, &agbp); + error = xfs_alloc_read_agf(pag, tp, 0, &agbp); if (error) return error; @@ -666,8 +666,7 @@ xfs_rmapbt_calc_reserves( * never be available for the kinds of things that would require btree * expansion. We therefore can pretend the space isn't there. */ - if (mp->m_sb.sb_logstart && - XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == pag->pag_agno) + if (xfs_ag_contains_log(mp, pag->pag_agno)) agblocks -= mp->m_sb.sb_logblocks; /* Reserve 1% of the AG or enough for 1 block per record. */ diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index 8b9bd178a487..bdc777b9ec4a 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -204,7 +204,7 @@ xfs_failaddr_t xfs_symlink_shortform_verify( struct xfs_inode *ip) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); char *sfp = (char *)ifp->if_u1.if_data; int size = ifp->if_bytes; char *endp = sfp + size; diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index e9913c2c5a24..2c4ad6e4bb14 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -515,7 +515,7 @@ xfs_calc_remove_reservation( { return XFS_DQUOT_LOGRES(mp) + xfs_calc_iunlink_add_reservation(mp) + - max((xfs_calc_inode_res(mp, 1) + + max((xfs_calc_inode_res(mp, 2) + xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1))), (xfs_calc_buf_res(4, mp->m_sb.sb_sectsize) + diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c index e810d23f2d97..5c2765934732 100644 --- a/fs/xfs/libxfs/xfs_types.c +++ b/fs/xfs/libxfs/xfs_types.c @@ -13,25 +13,13 @@ #include "xfs_mount.h" #include "xfs_ag.h" -/* Find the size of the AG, in blocks. */ -inline xfs_agblock_t -xfs_ag_block_count( - struct xfs_mount *mp, - xfs_agnumber_t agno) -{ - ASSERT(agno < mp->m_sb.sb_agcount); - - if (agno < mp->m_sb.sb_agcount - 1) - return mp->m_sb.sb_agblocks; - return mp->m_sb.sb_dblocks - (agno * mp->m_sb.sb_agblocks); -} /* * Verify that an AG block number pointer neither points outside the AG * nor points at static metadata. */ -inline bool -xfs_verify_agbno( +static inline bool +xfs_verify_agno_agbno( struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno) @@ -59,7 +47,7 @@ xfs_verify_fsbno( if (agno >= mp->m_sb.sb_agcount) return false; - return xfs_verify_agbno(mp, agno, XFS_FSB_TO_AGBNO(mp, fsbno)); + return xfs_verify_agno_agbno(mp, agno, XFS_FSB_TO_AGBNO(mp, fsbno)); } /* @@ -85,40 +73,12 @@ xfs_verify_fsbext( XFS_FSB_TO_AGNO(mp, fsbno + len - 1); } -/* Calculate the first and last possible inode number in an AG. */ -inline void -xfs_agino_range( - struct xfs_mount *mp, - xfs_agnumber_t agno, - xfs_agino_t *first, - xfs_agino_t *last) -{ - xfs_agblock_t bno; - xfs_agblock_t eoag; - - eoag = xfs_ag_block_count(mp, agno); - - /* - * Calculate the first inode, which will be in the first - * cluster-aligned block after the AGFL. - */ - bno = round_up(XFS_AGFL_BLOCK(mp) + 1, M_IGEO(mp)->cluster_align); - *first = XFS_AGB_TO_AGINO(mp, bno); - - /* - * Calculate the last inode, which will be at the end of the - * last (aligned) cluster that can be allocated in the AG. - */ - bno = round_down(eoag, M_IGEO(mp)->cluster_align); - *last = XFS_AGB_TO_AGINO(mp, bno) - 1; -} - /* * Verify that an AG inode number pointer neither points outside the AG * nor points at static metadata. */ -inline bool -xfs_verify_agino( +static inline bool +xfs_verify_agno_agino( struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agino_t agino) @@ -131,19 +91,6 @@ xfs_verify_agino( } /* - * Verify that an AG inode number pointer neither points outside the AG - * nor points at static metadata, or is NULLAGINO. - */ -bool -xfs_verify_agino_or_null( - struct xfs_mount *mp, - xfs_agnumber_t agno, - xfs_agino_t agino) -{ - return agino == NULLAGINO || xfs_verify_agino(mp, agno, agino); -} - -/* * Verify that an FS inode number pointer neither points outside the * filesystem nor points at static AG metadata. */ @@ -159,7 +106,7 @@ xfs_verify_ino( return false; if (XFS_AGINO_TO_INO(mp, agno, agino) != ino) return false; - return xfs_verify_agino(mp, agno, agino); + return xfs_verify_agno_agino(mp, agno, agino); } /* Is this an internal inode number? */ @@ -229,12 +176,8 @@ xfs_icount_range( /* root, rtbitmap, rtsum all live in the first chunk */ *min = XFS_INODES_PER_CHUNK; - for_each_perag(mp, agno, pag) { - xfs_agino_t first, last; - - xfs_agino_range(mp, agno, &first, &last); - nr_inos += last - first + 1; - } + for_each_perag(mp, agno, pag) + nr_inos += pag->agino_max - pag->agino_min + 1; *max = nr_inos; } diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index 373f64a492a4..a6b7d98cf68f 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -179,19 +179,10 @@ enum xfs_ag_resv_type { */ struct xfs_mount; -xfs_agblock_t xfs_ag_block_count(struct xfs_mount *mp, xfs_agnumber_t agno); -bool xfs_verify_agbno(struct xfs_mount *mp, xfs_agnumber_t agno, - xfs_agblock_t agbno); bool xfs_verify_fsbno(struct xfs_mount *mp, xfs_fsblock_t fsbno); bool xfs_verify_fsbext(struct xfs_mount *mp, xfs_fsblock_t fsbno, xfs_fsblock_t len); -void xfs_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno, - xfs_agino_t *first, xfs_agino_t *last); -bool xfs_verify_agino(struct xfs_mount *mp, xfs_agnumber_t agno, - xfs_agino_t agino); -bool xfs_verify_agino_or_null(struct xfs_mount *mp, xfs_agnumber_t agno, - xfs_agino_t agino); bool xfs_verify_ino(struct xfs_mount *mp, xfs_ino_t ino); bool xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino); bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino); diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index 90aebfe9dc5f..b7b838bd4ba4 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -541,16 +541,16 @@ xchk_agf( /* Check the AG length */ eoag = be32_to_cpu(agf->agf_length); - if (eoag != xfs_ag_block_count(mp, agno)) + if (eoag != pag->block_count) xchk_block_set_corrupt(sc, sc->sa.agf_bp); /* Check the AGF btree roots and levels */ agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_BNO]); - if (!xfs_verify_agbno(mp, agno, agbno)) + if (!xfs_verify_agbno(pag, agbno)) xchk_block_set_corrupt(sc, sc->sa.agf_bp); agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_CNT]); - if (!xfs_verify_agbno(mp, agno, agbno)) + if (!xfs_verify_agbno(pag, agbno)) xchk_block_set_corrupt(sc, sc->sa.agf_bp); level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]); @@ -563,7 +563,7 @@ xchk_agf( if (xfs_has_rmapbt(mp)) { agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_RMAP]); - if (!xfs_verify_agbno(mp, agno, agbno)) + if (!xfs_verify_agbno(pag, agbno)) xchk_block_set_corrupt(sc, sc->sa.agf_bp); level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]); @@ -573,7 +573,7 @@ xchk_agf( if (xfs_has_reflink(mp)) { agbno = be32_to_cpu(agf->agf_refcount_root); - if (!xfs_verify_agbno(mp, agno, agbno)) + if (!xfs_verify_agbno(pag, agbno)) xchk_block_set_corrupt(sc, sc->sa.agf_bp); level = be32_to_cpu(agf->agf_refcount_level); @@ -639,9 +639,8 @@ xchk_agfl_block( { struct xchk_agfl_info *sai = priv; struct xfs_scrub *sc = sai->sc; - xfs_agnumber_t agno = sc->sa.pag->pag_agno; - if (xfs_verify_agbno(mp, agno, agbno) && + if (xfs_verify_agbno(sc->sa.pag, agbno) && sai->nr_entries < sai->sz_entries) sai->entries[sai->nr_entries++] = agbno; else @@ -871,12 +870,12 @@ xchk_agi( /* Check the AG length */ eoag = be32_to_cpu(agi->agi_length); - if (eoag != xfs_ag_block_count(mp, agno)) + if (eoag != pag->block_count) xchk_block_set_corrupt(sc, sc->sa.agi_bp); /* Check btree roots and levels */ agbno = be32_to_cpu(agi->agi_root); - if (!xfs_verify_agbno(mp, agno, agbno)) + if (!xfs_verify_agbno(pag, agbno)) xchk_block_set_corrupt(sc, sc->sa.agi_bp); level = be32_to_cpu(agi->agi_level); @@ -885,7 +884,7 @@ xchk_agi( if (xfs_has_finobt(mp)) { agbno = be32_to_cpu(agi->agi_free_root); - if (!xfs_verify_agbno(mp, agno, agbno)) + if (!xfs_verify_agbno(pag, agbno)) xchk_block_set_corrupt(sc, sc->sa.agi_bp); level = be32_to_cpu(agi->agi_free_level); @@ -902,17 +901,17 @@ xchk_agi( /* Check inode pointers */ agino = be32_to_cpu(agi->agi_newino); - if (!xfs_verify_agino_or_null(mp, agno, agino)) + if (!xfs_verify_agino_or_null(pag, agino)) xchk_block_set_corrupt(sc, sc->sa.agi_bp); agino = be32_to_cpu(agi->agi_dirino); - if (!xfs_verify_agino_or_null(mp, agno, agino)) + if (!xfs_verify_agino_or_null(pag, agino)) xchk_block_set_corrupt(sc, sc->sa.agi_bp); /* Check unlinked inode buckets */ for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) { agino = be32_to_cpu(agi->agi_unlinked[i]); - if (!xfs_verify_agino_or_null(mp, agno, agino)) + if (!xfs_verify_agino_or_null(pag, agino)) xchk_block_set_corrupt(sc, sc->sa.agi_bp); } diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 6da7f2ca77de..1b0b4e243f77 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -106,7 +106,7 @@ xrep_agf_check_agfl_block( { struct xfs_scrub *sc = priv; - if (!xfs_verify_agbno(mp, sc->sa.pag->pag_agno, agbno)) + if (!xfs_verify_agbno(sc->sa.pag, agbno)) return -EFSCORRUPTED; return 0; } @@ -130,10 +130,7 @@ xrep_check_btree_root( struct xfs_scrub *sc, struct xrep_find_ag_btree *fab) { - struct xfs_mount *mp = sc->mp; - xfs_agnumber_t agno = sc->sm->sm_agno; - - return xfs_verify_agbno(mp, agno, fab->root) && + return xfs_verify_agbno(sc->sa.pag, fab->root) && fab->height <= fab->maxlevels; } @@ -201,8 +198,7 @@ xrep_agf_init_header( agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC); agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION); agf->agf_seqno = cpu_to_be32(sc->sa.pag->pag_agno); - agf->agf_length = cpu_to_be32(xfs_ag_block_count(mp, - sc->sa.pag->pag_agno)); + agf->agf_length = cpu_to_be32(sc->sa.pag->block_count); agf->agf_flfirst = old_agf->agf_flfirst; agf->agf_fllast = old_agf->agf_fllast; agf->agf_flcount = old_agf->agf_flcount; @@ -405,7 +401,7 @@ xrep_agf( * btrees rooted in the AGF. If the AGFL contents are obviously bad * then we'll bail out. */ - error = xfs_alloc_read_agfl(mp, sc->tp, sc->sa.pag->pag_agno, &agfl_bp); + error = xfs_alloc_read_agfl(sc->sa.pag, sc->tp, &agfl_bp); if (error) return error; @@ -666,8 +662,7 @@ xrep_agfl( * nothing wrong with the AGF, but all the AG header repair functions * have this chicken-and-egg problem. */ - error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.pag->pag_agno, 0, - &agf_bp); + error = xfs_alloc_read_agf(sc->sa.pag, sc->tp, 0, &agf_bp); if (error) return error; @@ -742,8 +737,7 @@ xrep_agi_find_btrees( int error; /* Read the AGF. */ - error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.pag->pag_agno, 0, - &agf_bp); + error = xfs_alloc_read_agf(sc->sa.pag, sc->tp, 0, &agf_bp); if (error) return error; @@ -782,8 +776,7 @@ xrep_agi_init_header( agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC); agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION); agi->agi_seqno = cpu_to_be32(sc->sa.pag->pag_agno); - agi->agi_length = cpu_to_be32(xfs_ag_block_count(mp, - sc->sa.pag->pag_agno)); + agi->agi_length = cpu_to_be32(sc->sa.pag->block_count); agi->agi_newino = cpu_to_be32(NULLAGINO); agi->agi_dirino = cpu_to_be32(NULLAGINO); if (xfs_has_crc(mp)) diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index 87518e1292f8..ab427b4d7fe0 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -93,8 +93,7 @@ xchk_allocbt_rec( struct xchk_btree *bs, const union xfs_btree_rec *rec) { - struct xfs_mount *mp = bs->cur->bc_mp; - xfs_agnumber_t agno = bs->cur->bc_ag.pag->pag_agno; + struct xfs_perag *pag = bs->cur->bc_ag.pag; xfs_agblock_t bno; xfs_extlen_t len; @@ -102,8 +101,8 @@ xchk_allocbt_rec( len = be32_to_cpu(rec->alloc.ar_blockcount); if (bno + len <= bno || - !xfs_verify_agbno(mp, agno, bno) || - !xfs_verify_agbno(mp, agno, bno + len - 1)) + !xfs_verify_agbno(pag, bno) || + !xfs_verify_agbno(pag, bno + len - 1)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); xchk_allocbt_xref(bs->sc, bno, len); diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 285995ba3947..f0b9cb6506fd 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -377,7 +377,7 @@ xchk_bmapbt_rec( struct xfs_inode *ip = bs->cur->bc_ino.ip; struct xfs_buf *bp = NULL; struct xfs_btree_block *block; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, info->whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, info->whichfork); uint64_t owner; int i; @@ -426,7 +426,7 @@ xchk_bmap_btree( struct xchk_bmap_info *info) { struct xfs_owner_info oinfo; - struct xfs_ifork *ifp = XFS_IFORK_PTR(sc->ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(sc->ip, whichfork); struct xfs_mount *mp = sc->mp; struct xfs_inode *ip = sc->ip; struct xfs_btree_cur *cur; @@ -478,7 +478,7 @@ xchk_bmap_check_rmap( return 0; /* Now look up the bmbt record. */ - ifp = XFS_IFORK_PTR(sc->ip, sbcri->whichfork); + ifp = xfs_ifork_ptr(sc->ip, sbcri->whichfork); if (!ifp) { xchk_fblock_set_corrupt(sc, sbcri->whichfork, rec->rm_offset); @@ -540,7 +540,7 @@ xchk_bmap_check_ag_rmaps( struct xfs_buf *agf; int error; - error = xfs_alloc_read_agf(sc->mp, sc->tp, pag->pag_agno, 0, &agf); + error = xfs_alloc_read_agf(pag, sc->tp, 0, &agf); if (error) return error; @@ -563,7 +563,7 @@ xchk_bmap_check_rmaps( struct xfs_scrub *sc, int whichfork) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(sc->ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(sc->ip, whichfork); struct xfs_perag *pag; xfs_agnumber_t agno; bool zero_size; @@ -578,7 +578,7 @@ xchk_bmap_check_rmaps( if (XFS_IS_REALTIME_INODE(sc->ip) && whichfork == XFS_DATA_FORK) return 0; - ASSERT(XFS_IFORK_PTR(sc->ip, whichfork) != NULL); + ASSERT(xfs_ifork_ptr(sc->ip, whichfork) != NULL); /* * Only do this for complex maps that are in btree format, or for @@ -624,7 +624,7 @@ xchk_bmap( struct xchk_bmap_info info = { NULL }; struct xfs_mount *mp = sc->mp; struct xfs_inode *ip = sc->ip; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); xfs_fileoff_t endoff; struct xfs_iext_cursor icur; int error = 0; @@ -689,7 +689,7 @@ xchk_bmap( /* Scrub extent records. */ info.lastoff = 0; - ifp = XFS_IFORK_PTR(ip, whichfork); + ifp = xfs_ifork_ptr(ip, whichfork); for_each_xfs_iext(ifp, &icur, &irec) { if (xchk_should_terminate(sc, &error) || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index 39dd46f038fe..2f4519590dc1 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -462,7 +462,7 @@ xchk_btree_check_iroot_minrecs( */ if (bs->cur->bc_btnum == XFS_BTNUM_BMAP && bs->cur->bc_ino.whichfork == XFS_DATA_FORK && - XFS_IFORK_Q(bs->sc->ip)) + xfs_inode_has_attr_fork(bs->sc->ip)) return false; return true; diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 97b54ac3075f..9bbbf20f401b 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -416,15 +416,15 @@ xchk_ag_read_headers( if (!sa->pag) return -ENOENT; - error = xfs_ialloc_read_agi(mp, sc->tp, agno, &sa->agi_bp); + error = xfs_ialloc_read_agi(sa->pag, sc->tp, &sa->agi_bp); if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI)) return error; - error = xfs_alloc_read_agf(mp, sc->tp, agno, 0, &sa->agf_bp); + error = xfs_alloc_read_agf(sa->pag, sc->tp, 0, &sa->agf_bp); if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGF)) return error; - error = xfs_alloc_read_agfl(mp, sc->tp, agno, &sa->agfl_bp); + error = xfs_alloc_read_agfl(sa->pag, sc->tp, &sa->agfl_bp); if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGFL)) return error; diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c index b962cfbbd92b..84fe3d33d699 100644 --- a/fs/xfs/scrub/dabtree.c +++ b/fs/xfs/scrub/dabtree.c @@ -482,7 +482,7 @@ xchk_da_btree( int error; /* Skip short format data structures; no btree to scan. */ - if (!xfs_ifork_has_extents(XFS_IFORK_PTR(sc->ip, whichfork))) + if (!xfs_ifork_has_extents(xfs_ifork_ptr(sc->ip, whichfork))) return 0; /* Set up initial da state. */ diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index 38897adde7b5..5abb5fdb71d9 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -667,7 +667,7 @@ xchk_directory_blocks( { struct xfs_bmbt_irec got; struct xfs_da_args args; - struct xfs_ifork *ifp = XFS_IFORK_PTR(sc->ip, XFS_DATA_FORK); + struct xfs_ifork *ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK); struct xfs_mount *mp = sc->mp; xfs_fileoff_t leaf_lblk; xfs_fileoff_t free_lblk; diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index 48a6cbdf95d0..6a6f8fe7f87c 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -78,10 +78,10 @@ xchk_fscount_warmup( continue; /* Lock both AG headers. */ - error = xfs_ialloc_read_agi(mp, sc->tp, agno, &agi_bp); + error = xfs_ialloc_read_agi(pag, sc->tp, &agi_bp); if (error) break; - error = xfs_alloc_read_agf(mp, sc->tp, agno, 0, &agf_bp); + error = xfs_alloc_read_agf(pag, sc->tp, 0, &agf_bp); if (error) break; diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c index 2e61df3bca83..aa65ec88a0c0 100644 --- a/fs/xfs/scrub/health.c +++ b/fs/xfs/scrub/health.c @@ -8,6 +8,8 @@ #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_btree.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" #include "xfs_ag.h" #include "xfs_health.h" #include "scrub/scrub.h" diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 00848ee542fb..e1026e07bf94 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -104,13 +104,13 @@ xchk_iallocbt_chunk( xfs_extlen_t len) { struct xfs_mount *mp = bs->cur->bc_mp; - xfs_agnumber_t agno = bs->cur->bc_ag.pag->pag_agno; + struct xfs_perag *pag = bs->cur->bc_ag.pag; xfs_agblock_t bno; bno = XFS_AGINO_TO_AGBNO(mp, agino); if (bno + len <= bno || - !xfs_verify_agbno(mp, agno, bno) || - !xfs_verify_agbno(mp, agno, bno + len - 1)) + !xfs_verify_agbno(pag, bno) || + !xfs_verify_agbno(pag, bno + len - 1)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); xchk_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len); @@ -421,10 +421,10 @@ xchk_iallocbt_rec( const union xfs_btree_rec *rec) { struct xfs_mount *mp = bs->cur->bc_mp; + struct xfs_perag *pag = bs->cur->bc_ag.pag; struct xchk_iallocbt *iabt = bs->private; struct xfs_inobt_rec_incore irec; uint64_t holes; - xfs_agnumber_t agno = bs->cur->bc_ag.pag->pag_agno; xfs_agino_t agino; xfs_extlen_t len; int holecount; @@ -446,8 +446,8 @@ xchk_iallocbt_rec( agino = irec.ir_startino; /* Record has to be properly aligned within the AG. */ - if (!xfs_verify_agino(mp, agno, agino) || - !xfs_verify_agino(mp, agno, agino + XFS_INODES_PER_CHUNK - 1)) { + if (!xfs_verify_agino(pag, agino) || + !xfs_verify_agino(pag, agino + XFS_INODES_PER_CHUNK - 1)) { xchk_btree_set_corrupt(bs->sc, bs->cur, 0); goto out; } diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index 3c7506c7553c..21b4c9006859 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -185,7 +185,7 @@ xchk_quota_data_fork( /* Check for data fork problems that apply only to quota files. */ max_dqid_off = ((xfs_dqid_t)-1) / qi->qi_dqperchunk; - ifp = XFS_IFORK_PTR(sc->ip, XFS_DATA_FORK); + ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK); for_each_xfs_iext(ifp, &icur, &irec) { if (xchk_should_terminate(sc, &error)) break; diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 2744eecdbaf0..c68b767dc08f 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -13,6 +13,8 @@ #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" #include "xfs_ag.h" /* @@ -332,9 +334,8 @@ xchk_refcountbt_rec( struct xchk_btree *bs, const union xfs_btree_rec *rec) { - struct xfs_mount *mp = bs->cur->bc_mp; xfs_agblock_t *cow_blocks = bs->private; - xfs_agnumber_t agno = bs->cur->bc_ag.pag->pag_agno; + struct xfs_perag *pag = bs->cur->bc_ag.pag; xfs_agblock_t bno; xfs_extlen_t len; xfs_nlink_t refcount; @@ -354,8 +355,8 @@ xchk_refcountbt_rec( /* Check the extent. */ bno &= ~XFS_REFC_COW_START; if (bno + len <= bno || - !xfs_verify_agbno(mp, agno, bno) || - !xfs_verify_agbno(mp, agno, bno + len - 1)) + !xfs_verify_agbno(pag, bno) || + !xfs_verify_agbno(pag, bno + len - 1)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); if (refcount == 0) diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 1e7b6b209ee8..c18bd039fce9 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -199,7 +199,7 @@ xrep_calc_ag_resblks( icount = pag->pagi_count; } else { /* Try to get the actual counters from disk. */ - error = xfs_ialloc_read_agi(mp, NULL, sm->sm_agno, &bp); + error = xfs_ialloc_read_agi(pag, NULL, &bp); if (!error) { icount = pag->pagi_count; xfs_buf_relse(bp); @@ -207,9 +207,9 @@ xrep_calc_ag_resblks( } /* Now grab the block counters from the AGF. */ - error = xfs_alloc_read_agf(mp, NULL, sm->sm_agno, 0, &bp); + error = xfs_alloc_read_agf(pag, NULL, 0, &bp); if (error) { - aglen = xfs_ag_block_count(mp, sm->sm_agno); + aglen = pag->block_count; freelen = aglen; usedlen = aglen; } else { @@ -220,25 +220,22 @@ xrep_calc_ag_resblks( usedlen = aglen - freelen; xfs_buf_relse(bp); } - xfs_perag_put(pag); /* If the icount is impossible, make some worst-case assumptions. */ if (icount == NULLAGINO || - !xfs_verify_agino(mp, sm->sm_agno, icount)) { - xfs_agino_t first, last; - - xfs_agino_range(mp, sm->sm_agno, &first, &last); - icount = last - first + 1; + !xfs_verify_agino(pag, icount)) { + icount = pag->agino_max - pag->agino_min + 1; } /* If the block counts are impossible, make worst-case assumptions. */ if (aglen == NULLAGBLOCK || - aglen != xfs_ag_block_count(mp, sm->sm_agno) || + aglen != pag->block_count || freelen >= aglen) { - aglen = xfs_ag_block_count(mp, sm->sm_agno); + aglen = pag->block_count; freelen = aglen; usedlen = aglen; } + xfs_perag_put(pag); trace_xrep_calc_ag_resblks(mp, sm->sm_agno, icount, aglen, freelen, usedlen); @@ -300,13 +297,13 @@ xrep_alloc_ag_block( switch (resv) { case XFS_AG_RESV_AGFL: case XFS_AG_RESV_RMAPBT: - error = xfs_alloc_get_freelist(sc->tp, sc->sa.agf_bp, &bno, 1); + error = xfs_alloc_get_freelist(sc->sa.pag, sc->tp, + sc->sa.agf_bp, &bno, 1); if (error) return error; if (bno == NULLAGBLOCK) return -ENOSPC; - xfs_extent_busy_reuse(sc->mp, sc->sa.pag, bno, - 1, false); + xfs_extent_busy_reuse(sc->mp, sc->sa.pag, bno, 1, false); *fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno, bno); if (resv == XFS_AG_RESV_RMAPBT) xfs_ag_resv_rmapbt_alloc(sc->mp, sc->sa.pag->pag_agno); @@ -457,16 +454,19 @@ xrep_invalidate_blocks( * assume it's owned by someone else. */ for_each_xbitmap_block(fsbno, bmr, n, bitmap) { + int error; + /* Skip AG headers and post-EOFS blocks */ if (!xfs_verify_fsbno(sc->mp, fsbno)) continue; - bp = xfs_buf_incore(sc->mp->m_ddev_targp, + error = xfs_buf_incore(sc->mp->m_ddev_targp, XFS_FSB_TO_DADDR(sc->mp, fsbno), - XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK); - if (bp) { - xfs_trans_bjoin(sc->tp, bp); - xfs_trans_binval(sc->tp, bp); - } + XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK, &bp); + if (error) + continue; + + xfs_trans_bjoin(sc->tp, bp); + xfs_trans_binval(sc->tp, bp); } return 0; @@ -516,8 +516,8 @@ xrep_put_freelist( return error; /* Put the block on the AGFL. */ - error = xfs_alloc_put_freelist(sc->tp, sc->sa.agf_bp, sc->sa.agfl_bp, - agbno, 0); + error = xfs_alloc_put_freelist(sc->sa.pag, sc->tp, sc->sa.agf_bp, + sc->sa.agfl_bp, agbno, 0); if (error) return error; xfs_extent_busy_insert(sc->tp, sc->sa.pag, agbno, 1, @@ -536,13 +536,12 @@ xrep_reap_block( { struct xfs_btree_cur *cur; struct xfs_buf *agf_bp = NULL; - xfs_agnumber_t agno; xfs_agblock_t agbno; bool has_other_rmap; int error; - agno = XFS_FSB_TO_AGNO(sc->mp, fsbno); agbno = XFS_FSB_TO_AGBNO(sc->mp, fsbno); + ASSERT(XFS_FSB_TO_AGNO(sc->mp, fsbno) == sc->sa.pag->pag_agno); /* * If we are repairing per-inode metadata, we need to read in the AGF @@ -550,7 +549,7 @@ xrep_reap_block( * the AGF buffer that the setup functions already grabbed. */ if (sc->ip) { - error = xfs_alloc_read_agf(sc->mp, sc->tp, agno, 0, &agf_bp); + error = xfs_alloc_read_agf(sc->sa.pag, sc->tp, 0, &agf_bp); if (error) return error; } else { diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 8dae0345c7df..229826b2e1c0 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -92,7 +92,7 @@ xchk_rmapbt_rec( { struct xfs_mount *mp = bs->cur->bc_mp; struct xfs_rmap_irec irec; - xfs_agnumber_t agno = bs->cur->bc_ag.pag->pag_agno; + struct xfs_perag *pag = bs->cur->bc_ag.pag; bool non_inode; bool is_unwritten; bool is_bmbt; @@ -121,8 +121,8 @@ xchk_rmapbt_rec( * Otherwise we must point somewhere past the static metadata * but before the end of the FS. Run the regular check. */ - if (!xfs_verify_agbno(mp, agno, irec.rm_startblock) || - !xfs_verify_agbno(mp, agno, irec.rm_startblock + + if (!xfs_verify_agbno(pag, irec.rm_startblock) || + !xfs_verify_agbno(pag, irec.rm_startblock + irec.rm_blockcount - 1)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); } diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c index 599ee277bba2..75311f8daeeb 100644 --- a/fs/xfs/scrub/symlink.c +++ b/fs/xfs/scrub/symlink.c @@ -41,7 +41,7 @@ xchk_symlink( if (!S_ISLNK(VFS_I(ip)->i_mode)) return -ENOENT; - ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); len = ip->i_disk_size; /* Plausible size? */ @@ -52,8 +52,8 @@ xchk_symlink( /* Inline symlink? */ if (ifp->if_format == XFS_DINODE_FMT_LOCAL) { - if (len > XFS_IFORK_DSIZE(ip) || - len > strnlen(ifp->if_u1.if_data, XFS_IFORK_DSIZE(ip))) + if (len > xfs_inode_data_fork_size(ip) || + len > strnlen(ifp->if_u1.if_data, xfs_inode_data_fork_size(ip))) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); goto out; } diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index 27265771f247..5db87b34fb6e 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -158,6 +158,7 @@ xfs_attr3_node_inactive( } child_fsb = be32_to_cpu(ichdr.btree[0].before); xfs_trans_brelse(*trans, bp); /* no locks for later trans */ + bp = NULL; /* * If this is the node level just above the leaves, simply loop @@ -211,12 +212,8 @@ xfs_attr3_node_inactive( &child_bp); if (error) return error; - error = bp->b_error; - if (error) { - xfs_trans_brelse(*trans, child_bp); - return error; - } xfs_trans_binval(*trans, child_bp); + child_bp = NULL; /* * If we're not done, re-read the parent to get the next @@ -233,6 +230,7 @@ xfs_attr3_node_inactive( bp->b_addr); child_fsb = be32_to_cpu(phdr.btree[i + 1].before); xfs_trans_brelse(*trans, bp); + bp = NULL; } /* * Atomically commit the whole invalidate stuff. @@ -338,7 +336,7 @@ xfs_attr_inactive( ASSERT(! XFS_NOT_DQATTACHED(mp, dp)); xfs_ilock(dp, lock_mode); - if (!XFS_IFORK_Q(dp)) + if (!xfs_inode_has_attr_fork(dp)) goto out_destroy_fork; xfs_iunlock(dp, lock_mode); @@ -351,7 +349,7 @@ xfs_attr_inactive( lock_mode = XFS_ILOCK_EXCL; xfs_ilock(dp, lock_mode); - if (!XFS_IFORK_Q(dp)) + if (!xfs_inode_has_attr_fork(dp)) goto out_cancel; /* @@ -362,12 +360,11 @@ xfs_attr_inactive( /* * Invalidate and truncate the attribute fork extents. Make sure the - * fork actually has attributes as otherwise the invalidation has no + * fork actually has xattr blocks as otherwise the invalidation has no * blocks to read and returns an error. In this case, just do the fork * removal below. */ - if (xfs_inode_hasattr(dp) && - dp->i_afp->if_format != XFS_DINODE_FMT_LOCAL) { + if (dp->i_af.if_nextents > 0) { error = xfs_attr3_root_inactive(&trans, dp); if (error) goto out_cancel; @@ -388,11 +385,7 @@ out_cancel: xfs_trans_cancel(trans); out_destroy_fork: /* kill the in-core attr fork before we drop the inode lock */ - if (dp->i_afp) { - xfs_idestroy_fork(dp->i_afp); - kmem_cache_free(xfs_ifork_cache, dp->i_afp); - dp->i_afp = NULL; - } + xfs_ifork_zap_attr(dp); if (lock_mode) xfs_iunlock(dp, lock_mode); return error; diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index 90a14e85e76d..99bbbe1a0e44 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -61,8 +61,7 @@ xfs_attr_shortform_list( int sbsize, nsbuf, count, i; int error = 0; - ASSERT(dp->i_afp != NULL); - sf = (struct xfs_attr_shortform *)dp->i_afp->if_u1.if_data; + sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data; ASSERT(sf != NULL); if (!sf->hdr.count) return 0; @@ -80,7 +79,7 @@ xfs_attr_shortform_list( */ if (context->bufsize == 0 || (XFS_ISRESET_CURSOR(cursor) && - (dp->i_afp->if_bytes + sf->hdr.count * 16) < context->bufsize)) { + (dp->i_af.if_bytes + sf->hdr.count * 16) < context->bufsize)) { for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) { if (XFS_IS_CORRUPT(context->dp->i_mount, !xfs_attr_namecheck(sfe->nameval, @@ -121,7 +120,7 @@ xfs_attr_shortform_list( for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) { if (unlikely( ((char *)sfe < (char *)sf) || - ((char *)sfe >= ((char *)sf + dp->i_afp->if_bytes)))) { + ((char *)sfe >= ((char *)sf + dp->i_af.if_bytes)))) { XFS_CORRUPTION_ERROR("xfs_attr_shortform_list", XFS_ERRLEVEL_LOW, context->dp->i_mount, sfe, @@ -513,7 +512,7 @@ xfs_attr_list_ilocked( */ if (!xfs_inode_hasattr(dp)) return 0; - if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL) + if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL) return xfs_attr_shortform_list(context); if (xfs_attr_is_leaf(dp)) return xfs_attr_leaf_list(context); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 85e1a26c92e8..04d0c2bff67c 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -256,7 +256,7 @@ xfs_bmap_count_blocks( xfs_filblks_t *count) { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur; xfs_extlen_t btblocks = 0; int error; @@ -439,29 +439,28 @@ xfs_getbmap( whichfork = XFS_COW_FORK; else whichfork = XFS_DATA_FORK; - ifp = XFS_IFORK_PTR(ip, whichfork); xfs_ilock(ip, XFS_IOLOCK_SHARED); switch (whichfork) { case XFS_ATTR_FORK: - if (!XFS_IFORK_Q(ip)) - goto out_unlock_iolock; + lock = xfs_ilock_attr_map_shared(ip); + if (!xfs_inode_has_attr_fork(ip)) + goto out_unlock_ilock; max_len = 1LL << 32; - lock = xfs_ilock_attr_map_shared(ip); break; case XFS_COW_FORK: + lock = XFS_ILOCK_SHARED; + xfs_ilock(ip, lock); + /* No CoW fork? Just return */ - if (!ifp) - goto out_unlock_iolock; + if (!xfs_ifork_ptr(ip, whichfork)) + goto out_unlock_ilock; if (xfs_get_cowextsz_hint(ip)) max_len = mp->m_super->s_maxbytes; else max_len = XFS_ISIZE(ip); - - lock = XFS_ILOCK_SHARED; - xfs_ilock(ip, lock); break; case XFS_DATA_FORK: if (!(iflags & BMV_IF_DELALLOC) && @@ -491,6 +490,8 @@ xfs_getbmap( break; } + ifp = xfs_ifork_ptr(ip, whichfork); + switch (ifp->if_format) { case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: @@ -1320,8 +1321,8 @@ xfs_swap_extents_check_format( * extent format... */ if (tifp->if_format == XFS_DINODE_FMT_BTREE) { - if (XFS_IFORK_Q(ip) && - XFS_BMAP_BMDR_SPACE(tifp->if_broot) > XFS_IFORK_BOFF(ip)) + if (xfs_inode_has_attr_fork(ip) && + XFS_BMAP_BMDR_SPACE(tifp->if_broot) > xfs_inode_fork_boff(ip)) return -EINVAL; if (tifp->if_nextents <= XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)) return -EINVAL; @@ -1329,8 +1330,8 @@ xfs_swap_extents_check_format( /* Reciprocal target->temp btree format checks */ if (ifp->if_format == XFS_DINODE_FMT_BTREE) { - if (XFS_IFORK_Q(tip) && - XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > XFS_IFORK_BOFF(tip)) + if (xfs_inode_has_attr_fork(tip) && + XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > xfs_inode_fork_boff(tip)) return -EINVAL; if (ifp->if_nextents <= XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK)) return -EINVAL; @@ -1506,15 +1507,15 @@ xfs_swap_extent_forks( /* * Count the number of extended attribute blocks */ - if (XFS_IFORK_Q(ip) && ip->i_afp->if_nextents > 0 && - ip->i_afp->if_format != XFS_DINODE_FMT_LOCAL) { + if (xfs_inode_has_attr_fork(ip) && ip->i_af.if_nextents > 0 && + ip->i_af.if_format != XFS_DINODE_FMT_LOCAL) { error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &junk, &aforkblks); if (error) return error; } - if (XFS_IFORK_Q(tip) && tip->i_afp->if_nextents > 0 && - tip->i_afp->if_format != XFS_DINODE_FMT_LOCAL) { + if (xfs_inode_has_attr_fork(tip) && tip->i_af.if_nextents > 0 && + tip->i_af.if_format != XFS_DINODE_FMT_LOCAL) { error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK, &junk, &taforkblks); if (error) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 5e8f40d8c052..dde346450952 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -5,6 +5,7 @@ */ #include "xfs.h" #include <linux/backing-dev.h> +#include <linux/dax.h> #include "xfs_shared.h" #include "xfs_format.h" @@ -21,7 +22,7 @@ #include "xfs_error.h" #include "xfs_ag.h" -static struct kmem_cache *xfs_buf_cache; +struct kmem_cache *xfs_buf_cache; /* * Locking orders @@ -295,6 +296,16 @@ xfs_buf_free_pages( } static void +xfs_buf_free_callback( + struct callback_head *cb) +{ + struct xfs_buf *bp = container_of(cb, struct xfs_buf, b_rcu); + + xfs_buf_free_maps(bp); + kmem_cache_free(xfs_buf_cache, bp); +} + +static void xfs_buf_free( struct xfs_buf *bp) { @@ -307,8 +318,7 @@ xfs_buf_free( else if (bp->b_flags & _XBF_KMEM) kmem_free(bp->b_addr); - xfs_buf_free_maps(bp); - kmem_cache_free(xfs_buf_cache, bp); + call_rcu(&bp->b_rcu, xfs_buf_free_callback); } static int @@ -503,100 +513,45 @@ xfs_buf_hash_destroy( rhashtable_destroy(&pag->pag_buf_hash); } -/* - * Look up a buffer in the buffer cache and return it referenced and locked - * in @found_bp. - * - * If @new_bp is supplied and we have a lookup miss, insert @new_bp into the - * cache. - * - * If XBF_TRYLOCK is set in @flags, only try to lock the buffer and return - * -EAGAIN if we fail to lock it. - * - * Return values are: - * -EFSCORRUPTED if have been supplied with an invalid address - * -EAGAIN on trylock failure - * -ENOENT if we fail to find a match and @new_bp was NULL - * 0, with @found_bp: - * - @new_bp if we inserted it into the cache - * - the buffer we found and locked. - */ static int -xfs_buf_find( +xfs_buf_map_verify( struct xfs_buftarg *btp, - struct xfs_buf_map *map, - int nmaps, - xfs_buf_flags_t flags, - struct xfs_buf *new_bp, - struct xfs_buf **found_bp) + struct xfs_buf_map *map) { - struct xfs_perag *pag; - struct xfs_buf *bp; - struct xfs_buf_map cmap = { .bm_bn = map[0].bm_bn }; xfs_daddr_t eofs; - int i; - - *found_bp = NULL; - - for (i = 0; i < nmaps; i++) - cmap.bm_len += map[i].bm_len; /* Check for IOs smaller than the sector size / not sector aligned */ - ASSERT(!(BBTOB(cmap.bm_len) < btp->bt_meta_sectorsize)); - ASSERT(!(BBTOB(cmap.bm_bn) & (xfs_off_t)btp->bt_meta_sectormask)); + ASSERT(!(BBTOB(map->bm_len) < btp->bt_meta_sectorsize)); + ASSERT(!(BBTOB(map->bm_bn) & (xfs_off_t)btp->bt_meta_sectormask)); /* * Corrupted block numbers can get through to here, unfortunately, so we * have to check that the buffer falls within the filesystem bounds. */ eofs = XFS_FSB_TO_BB(btp->bt_mount, btp->bt_mount->m_sb.sb_dblocks); - if (cmap.bm_bn < 0 || cmap.bm_bn >= eofs) { + if (map->bm_bn < 0 || map->bm_bn >= eofs) { xfs_alert(btp->bt_mount, "%s: daddr 0x%llx out of range, EOFS 0x%llx", - __func__, cmap.bm_bn, eofs); + __func__, map->bm_bn, eofs); WARN_ON(1); return -EFSCORRUPTED; } - - pag = xfs_perag_get(btp->bt_mount, - xfs_daddr_to_agno(btp->bt_mount, cmap.bm_bn)); - - spin_lock(&pag->pag_buf_lock); - bp = rhashtable_lookup_fast(&pag->pag_buf_hash, &cmap, - xfs_buf_hash_params); - if (bp) { - atomic_inc(&bp->b_hold); - goto found; - } - - /* No match found */ - if (!new_bp) { - XFS_STATS_INC(btp->bt_mount, xb_miss_locked); - spin_unlock(&pag->pag_buf_lock); - xfs_perag_put(pag); - return -ENOENT; - } - - /* the buffer keeps the perag reference until it is freed */ - new_bp->b_pag = pag; - rhashtable_insert_fast(&pag->pag_buf_hash, &new_bp->b_rhash_head, - xfs_buf_hash_params); - spin_unlock(&pag->pag_buf_lock); - *found_bp = new_bp; return 0; +} -found: - spin_unlock(&pag->pag_buf_lock); - xfs_perag_put(pag); - - if (!xfs_buf_trylock(bp)) { - if (flags & XBF_TRYLOCK) { - xfs_buf_rele(bp); - XFS_STATS_INC(btp->bt_mount, xb_busy_locked); +static int +xfs_buf_find_lock( + struct xfs_buf *bp, + xfs_buf_flags_t flags) +{ + if (flags & XBF_TRYLOCK) { + if (!xfs_buf_trylock(bp)) { + XFS_STATS_INC(bp->b_mount, xb_busy_locked); return -EAGAIN; } + } else { xfs_buf_lock(bp); - XFS_STATS_INC(btp->bt_mount, xb_get_locked_waited); + XFS_STATS_INC(bp->b_mount, xb_get_locked_waited); } /* @@ -609,57 +564,59 @@ found: bp->b_flags &= _XBF_KMEM | _XBF_PAGES; bp->b_ops = NULL; } - - trace_xfs_buf_find(bp, flags, _RET_IP_); - XFS_STATS_INC(btp->bt_mount, xb_get_locked); - *found_bp = bp; return 0; } -struct xfs_buf * -xfs_buf_incore( - struct xfs_buftarg *target, - xfs_daddr_t blkno, - size_t numblks, - xfs_buf_flags_t flags) +static inline int +xfs_buf_lookup( + struct xfs_perag *pag, + struct xfs_buf_map *map, + xfs_buf_flags_t flags, + struct xfs_buf **bpp) { - struct xfs_buf *bp; + struct xfs_buf *bp; int error; - DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); - error = xfs_buf_find(target, &map, 1, flags, NULL, &bp); - if (error) - return NULL; - return bp; + rcu_read_lock(); + bp = rhashtable_lookup(&pag->pag_buf_hash, map, xfs_buf_hash_params); + if (!bp || !atomic_inc_not_zero(&bp->b_hold)) { + rcu_read_unlock(); + return -ENOENT; + } + rcu_read_unlock(); + + error = xfs_buf_find_lock(bp, flags); + if (error) { + xfs_buf_rele(bp); + return error; + } + + trace_xfs_buf_find(bp, flags, _RET_IP_); + *bpp = bp; + return 0; } /* - * Assembles a buffer covering the specified range. The code is optimised for - * cache hits, as metadata intensive workloads will see 3 orders of magnitude - * more hits than misses. + * Insert the new_bp into the hash table. This consumes the perag reference + * taken for the lookup regardless of the result of the insert. */ -int -xfs_buf_get_map( - struct xfs_buftarg *target, +static int +xfs_buf_find_insert( + struct xfs_buftarg *btp, + struct xfs_perag *pag, + struct xfs_buf_map *cmap, struct xfs_buf_map *map, int nmaps, xfs_buf_flags_t flags, struct xfs_buf **bpp) { - struct xfs_buf *bp; struct xfs_buf *new_bp; + struct xfs_buf *bp; int error; - *bpp = NULL; - error = xfs_buf_find(target, map, nmaps, flags, NULL, &bp); - if (!error) - goto found; - if (error != -ENOENT) - return error; - - error = _xfs_buf_alloc(target, map, nmaps, flags, &new_bp); + error = _xfs_buf_alloc(btp, map, nmaps, flags, &new_bp); if (error) - return error; + goto out_drop_pag; /* * For buffers that fit entirely within a single page, first attempt to @@ -674,18 +631,94 @@ xfs_buf_get_map( goto out_free_buf; } - error = xfs_buf_find(target, map, nmaps, flags, new_bp, &bp); - if (error) + spin_lock(&pag->pag_buf_lock); + bp = rhashtable_lookup_get_insert_fast(&pag->pag_buf_hash, + &new_bp->b_rhash_head, xfs_buf_hash_params); + if (IS_ERR(bp)) { + error = PTR_ERR(bp); + spin_unlock(&pag->pag_buf_lock); goto out_free_buf; + } + if (bp) { + /* found an existing buffer */ + atomic_inc(&bp->b_hold); + spin_unlock(&pag->pag_buf_lock); + error = xfs_buf_find_lock(bp, flags); + if (error) + xfs_buf_rele(bp); + else + *bpp = bp; + goto out_free_buf; + } + + /* The new buffer keeps the perag reference until it is freed. */ + new_bp->b_pag = pag; + spin_unlock(&pag->pag_buf_lock); + *bpp = new_bp; + return 0; - if (bp != new_bp) - xfs_buf_free(new_bp); +out_free_buf: + xfs_buf_free(new_bp); +out_drop_pag: + xfs_perag_put(pag); + return error; +} -found: +/* + * Assembles a buffer covering the specified range. The code is optimised for + * cache hits, as metadata intensive workloads will see 3 orders of magnitude + * more hits than misses. + */ +int +xfs_buf_get_map( + struct xfs_buftarg *btp, + struct xfs_buf_map *map, + int nmaps, + xfs_buf_flags_t flags, + struct xfs_buf **bpp) +{ + struct xfs_perag *pag; + struct xfs_buf *bp = NULL; + struct xfs_buf_map cmap = { .bm_bn = map[0].bm_bn }; + int error; + int i; + + for (i = 0; i < nmaps; i++) + cmap.bm_len += map[i].bm_len; + + error = xfs_buf_map_verify(btp, &cmap); + if (error) + return error; + + pag = xfs_perag_get(btp->bt_mount, + xfs_daddr_to_agno(btp->bt_mount, cmap.bm_bn)); + + error = xfs_buf_lookup(pag, &cmap, flags, &bp); + if (error && error != -ENOENT) + goto out_put_perag; + + /* cache hits always outnumber misses by at least 10:1 */ + if (unlikely(!bp)) { + XFS_STATS_INC(btp->bt_mount, xb_miss_locked); + + if (flags & XBF_INCORE) + goto out_put_perag; + + /* xfs_buf_find_insert() consumes the perag reference. */ + error = xfs_buf_find_insert(btp, pag, &cmap, map, nmaps, + flags, &bp); + if (error) + return error; + } else { + XFS_STATS_INC(btp->bt_mount, xb_get_locked); + xfs_perag_put(pag); + } + + /* We do not hold a perag reference anymore. */ if (!bp->b_addr) { error = _xfs_buf_map_pages(bp, flags); if (unlikely(error)) { - xfs_warn_ratelimited(target->bt_mount, + xfs_warn_ratelimited(btp->bt_mount, "%s: failed to map %u pages", __func__, bp->b_page_count); xfs_buf_relse(bp); @@ -700,12 +733,13 @@ found: if (!(flags & XBF_READ)) xfs_buf_ioerror(bp, 0); - XFS_STATS_INC(target->bt_mount, xb_get); + XFS_STATS_INC(btp->bt_mount, xb_get); trace_xfs_buf_get(bp, flags, _RET_IP_); *bpp = bp; return 0; -out_free_buf: - xfs_buf_free(new_bp); + +out_put_perag: + xfs_perag_put(pag); return error; } @@ -1911,7 +1945,7 @@ xfs_free_buftarg( list_lru_destroy(&btp->bt_lru); blkdev_issue_flush(btp->bt_bdev); - fs_put_dax(btp->bt_daxdev); + fs_put_dax(btp->bt_daxdev, btp->bt_mount); kmem_free(btp); } @@ -1958,13 +1992,18 @@ xfs_alloc_buftarg( struct block_device *bdev) { xfs_buftarg_t *btp; + const struct dax_holder_operations *ops = NULL; +#if defined(CONFIG_FS_DAX) && defined(CONFIG_MEMORY_FAILURE) + ops = &xfs_dax_holder_operations; +#endif btp = kmem_zalloc(sizeof(*btp), KM_NOFS); btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; - btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off); + btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off, + mp, ops); /* * Buffer IO error rate limiting. Limit it to no more than 10 messages @@ -1986,7 +2025,8 @@ xfs_alloc_buftarg( btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan; btp->bt_shrinker.seeks = DEFAULT_SEEKS; btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE; - if (register_shrinker(&btp->bt_shrinker)) + if (register_shrinker(&btp->bt_shrinker, "xfs-buf:%s", + mp->m_super->s_id)) goto error_pcpu; return btp; @@ -2275,29 +2315,6 @@ xfs_buf_delwri_pushbuf( return error; } -int __init -xfs_buf_init(void) -{ - xfs_buf_cache = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0, - SLAB_HWCACHE_ALIGN | - SLAB_RECLAIM_ACCOUNT | - SLAB_MEM_SPREAD, - NULL); - if (!xfs_buf_cache) - goto out; - - return 0; - - out: - return -ENOMEM; -} - -void -xfs_buf_terminate(void) -{ - kmem_cache_destroy(xfs_buf_cache); -} - void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref) { /* diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 1ee3056ff9cf..549c60942208 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -15,6 +15,8 @@ #include <linux/uio.h> #include <linux/list_lru.h> +extern struct kmem_cache *xfs_buf_cache; + /* * Base types */ @@ -42,9 +44,11 @@ struct xfs_buf; #define _XBF_DELWRI_Q (1u << 22)/* buffer on a delwri queue */ /* flags used only as arguments to access routines */ +#define XBF_INCORE (1u << 29)/* lookup only, return if found in cache */ #define XBF_TRYLOCK (1u << 30)/* lock requested, but do not wait */ #define XBF_UNMAPPED (1u << 31)/* do not map the buffer */ + typedef unsigned int xfs_buf_flags_t; #define XFS_BUF_FLAGS \ @@ -63,6 +67,7 @@ typedef unsigned int xfs_buf_flags_t; { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ /* The following interface flags should never be set */ \ + { XBF_INCORE, "INCORE" }, \ { XBF_TRYLOCK, "TRYLOCK" }, \ { XBF_UNMAPPED, "UNMAPPED" } @@ -193,13 +198,10 @@ struct xfs_buf { int b_last_error; const struct xfs_buf_ops *b_ops; + struct rcu_head b_rcu; }; /* Finding and Reading Buffers */ -struct xfs_buf *xfs_buf_incore(struct xfs_buftarg *target, - xfs_daddr_t blkno, size_t numblks, - xfs_buf_flags_t flags); - int xfs_buf_get_map(struct xfs_buftarg *target, struct xfs_buf_map *map, int nmaps, xfs_buf_flags_t flags, struct xfs_buf **bpp); int xfs_buf_read_map(struct xfs_buftarg *target, struct xfs_buf_map *map, @@ -210,6 +212,19 @@ void xfs_buf_readahead_map(struct xfs_buftarg *target, const struct xfs_buf_ops *ops); static inline int +xfs_buf_incore( + struct xfs_buftarg *target, + xfs_daddr_t blkno, + size_t numblks, + xfs_buf_flags_t flags, + struct xfs_buf **bpp) +{ + DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); + + return xfs_buf_get_map(target, &map, 1, XBF_INCORE | flags, bpp); +} + +static inline int xfs_buf_get( struct xfs_buftarg *target, xfs_daddr_t blkno, @@ -294,10 +309,6 @@ extern int xfs_buf_delwri_submit(struct list_head *); extern int xfs_buf_delwri_submit_nowait(struct list_head *); extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *); -/* Buffer Daemon Setup Routines */ -extern int xfs_buf_init(void); -extern void xfs_buf_terminate(void); - static inline xfs_daddr_t xfs_buf_daddr(struct xfs_buf *bp) { return bp->b_maps[0].bm_bn; diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c index a7174a5b3203..e295fc8062d8 100644 --- a/fs/xfs/xfs_dir2_readdir.c +++ b/fs/xfs/xfs_dir2_readdir.c @@ -248,7 +248,7 @@ xfs_dir2_leaf_readbuf( struct xfs_inode *dp = args->dp; struct xfs_buf *bp = NULL; struct xfs_da_geometry *geo = args->geo; - struct xfs_ifork *ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK); + struct xfs_ifork *ifp = xfs_ifork_ptr(dp, XFS_DATA_FORK); struct xfs_bmbt_irec map; struct blk_plug plug; xfs_dir2_off_t new_off; diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index c6fe3f6ebb6b..bfc829c07f03 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -45,7 +45,7 @@ xfs_trim_extents( */ xfs_log_force(mp, XFS_LOG_SYNC); - error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp); + error = xfs_alloc_read_agf(pag, NULL, 0, &agbp); if (error) goto out_put_perag; agf = agbp->b_addr; diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 5a6c3c3c4de2..8fb90da89787 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -549,7 +549,7 @@ xfs_dquot_check_type( * at the same time. The non-user quota file can be switched between * group and project quota uses depending on the mount options, which * means that we can encounter the other type when we try to load quota - * defaults. Quotacheck will soon reset the the entire quota file + * defaults. Quotacheck will soon reset the entire quota file * (including the root dquot) anyway, but don't log scary corruption * reports to dmesg. */ diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 765be054dffe..27ccfcd82f04 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -11,6 +11,7 @@ #include "xfs_bit.h" #include "xfs_shared.h" #include "xfs_mount.h" +#include "xfs_ag.h" #include "xfs_defer.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" @@ -187,12 +188,12 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt) { xfs_efi_log_format_t *src_efi_fmt = buf->i_addr; uint i; - uint len = sizeof(xfs_efi_log_format_t) + - (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_t); - uint len32 = sizeof(xfs_efi_log_format_32_t) + - (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_32_t); - uint len64 = sizeof(xfs_efi_log_format_64_t) + - (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_64_t); + uint len = sizeof(xfs_efi_log_format_t) + + (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_t); + uint len32 = sizeof(xfs_efi_log_format_32_t) + + (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_32_t); + uint len64 = sizeof(xfs_efi_log_format_64_t) + + (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_64_t); if (buf->i_len == len) { memcpy((char *)dst_efi_fmt, (char*)src_efi_fmt, len); @@ -551,6 +552,7 @@ xfs_agfl_free_finish_item( xfs_agnumber_t agno; xfs_agblock_t agbno; uint next_extent; + struct xfs_perag *pag; free = container_of(item, struct xfs_extent_free_item, xefi_list); ASSERT(free->xefi_blockcount == 1); @@ -560,9 +562,11 @@ xfs_agfl_free_finish_item( trace_xfs_agfl_free_deferred(mp, agno, 0, agbno, free->xefi_blockcount); - error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); + pag = xfs_perag_get(mp, agno); + error = xfs_alloc_read_agf(pag, tp, 0, &agbp); if (!error) error = xfs_free_agfl_block(tp, agno, agbno, agbp, &oinfo); + xfs_perag_put(pag); /* * Mark the transaction dirty, even on error. This ensures the diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 8d9b14d2b912..c6c80265c0b2 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -25,6 +25,7 @@ #include "xfs_iomap.h" #include "xfs_reflink.h" +#include <linux/dax.h> #include <linux/falloc.h> #include <linux/backing-dev.h> #include <linux/mman.h> @@ -142,7 +143,7 @@ xfs_file_fsync( { struct xfs_inode *ip = XFS_I(file->f_mapping->host); struct xfs_mount *mp = ip->i_mount; - int error = 0; + int error, err2; int log_flushed = 0; trace_xfs_file_fsync(ip); @@ -163,18 +164,21 @@ xfs_file_fsync( * inode size in case of an extending write. */ if (XFS_IS_REALTIME_INODE(ip)) - blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); + error = blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev); else if (mp->m_logdev_targp != mp->m_ddev_targp) - blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); + error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); /* * Any inode that has dirty modifications in the log is pinned. The - * racy check here for a pinned inode while not catch modifications + * racy check here for a pinned inode will not catch modifications * that happen concurrently to the fsync call, but fsync semantics * only require to sync previously completed I/O. */ - if (xfs_ipincount(ip)) - error = xfs_fsync_flush_log(ip, datasync, &log_flushed); + if (xfs_ipincount(ip)) { + err2 = xfs_fsync_flush_log(ip, datasync, &log_flushed); + if (err2 && !error) + error = err2; + } /* * If we only have a single device, and the log force about was @@ -184,8 +188,11 @@ xfs_file_fsync( * commit. */ if (!log_flushed && !XFS_IS_REALTIME_INODE(ip) && - mp->m_logdev_targp == mp->m_ddev_targp) - blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); + mp->m_logdev_targp == mp->m_ddev_targp) { + err2 = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev); + if (err2 && !error) + error = err2; + } return error; } @@ -669,7 +676,7 @@ xfs_file_dax_write( pos = iocb->ki_pos; trace_xfs_file_dax_write(iocb, from); - ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops); + ret = dax_iomap_rw(iocb, from, &xfs_dax_write_iomap_ops); if (ret > 0 && iocb->ki_pos > i_size_read(inode)) { i_size_write(inode, iocb->ki_pos); error = xfs_setfilesize(ip, pos, ret); @@ -806,7 +813,7 @@ xfs_wait_dax_page( xfs_ilock(ip, XFS_MMAPLOCK_EXCL); } -static int +int xfs_break_dax_layouts( struct inode *inode, bool *retry) @@ -1253,6 +1260,31 @@ xfs_file_llseek( return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); } +#ifdef CONFIG_FS_DAX +static int +xfs_dax_fault( + struct vm_fault *vmf, + enum page_entry_size pe_size, + bool write_fault, + pfn_t *pfn) +{ + return dax_iomap_fault(vmf, pe_size, pfn, NULL, + (write_fault && !vmf->cow_page) ? + &xfs_dax_write_iomap_ops : + &xfs_read_iomap_ops); +} +#else +static int +xfs_dax_fault( + struct vm_fault *vmf, + enum page_entry_size pe_size, + bool write_fault, + pfn_t *pfn) +{ + return 0; +} +#endif + /* * Locking for serialisation of IO during page faults. This results in a lock * ordering of: @@ -1284,10 +1316,7 @@ __xfs_filemap_fault( pfn_t pfn; xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL, - (write_fault && !vmf->cow_page) ? - &xfs_direct_write_iomap_ops : - &xfs_read_iomap_ops); + ret = xfs_dax_fault(vmf, pe_size, write_fault, &pfn); if (ret & VM_FAULT_NEEDDSYNC) ret = dax_finish_sync_fault(vmf, pe_size, pfn); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c index be9bcf8a1f99..34b21a29c39b 100644 --- a/fs/xfs/xfs_filestream.c +++ b/fs/xfs/xfs_filestream.c @@ -126,7 +126,7 @@ xfs_filestream_pick_ag( pag = xfs_perag_get(mp, ag); if (!pag->pagf_init) { - err = xfs_alloc_pagf_init(mp, NULL, ag, trylock); + err = xfs_alloc_read_agf(pag, NULL, trylock, NULL); if (err) { if (err != -EAGAIN) { xfs_perag_put(pag); @@ -181,7 +181,7 @@ next_ag: if (ag != startag) continue; - /* Allow sleeping in xfs_alloc_pagf_init() on the 2nd pass. */ + /* Allow sleeping in xfs_alloc_read_agf() on the 2nd pass. */ if (trylock != 0) { trylock = 0; continue; diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index bb23199f65c3..d8337274c74d 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -642,8 +642,7 @@ __xfs_getfsmap_datadev( info->agf_bp = NULL; } - error = xfs_alloc_read_agf(mp, tp, pag->pag_agno, 0, - &info->agf_bp); + error = xfs_alloc_read_agf(pag, tp, 0, &info->agf_bp); if (error) break; diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index d4a77c53f94b..13851c0d640b 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -41,6 +41,7 @@ xfs_resizefs_init_new_ags( xfs_agnumber_t oagcount, xfs_agnumber_t nagcount, xfs_rfsblock_t delta, + struct xfs_perag *last_pag, bool *lastag_extended) { struct xfs_mount *mp = tp->t_mountp; @@ -73,7 +74,7 @@ xfs_resizefs_init_new_ags( if (delta) { *lastag_extended = true; - error = xfs_ag_extend_space(mp, tp, id, delta); + error = xfs_ag_extend_space(last_pag, tp, delta); } return error; } @@ -96,6 +97,7 @@ xfs_growfs_data_private( xfs_agnumber_t oagcount; struct xfs_trans *tp; struct aghdr_init_data id = {}; + struct xfs_perag *last_pag; nb = in->newblocks; error = xfs_sb_validate_fsb_count(&mp->m_sb, nb); @@ -128,10 +130,9 @@ xfs_growfs_data_private( return -EINVAL; oagcount = mp->m_sb.sb_agcount; - /* allocate the new per-ag structures */ if (nagcount > oagcount) { - error = xfs_initialize_perag(mp, nagcount, &nagimax); + error = xfs_initialize_perag(mp, nagcount, nb, &nagimax); if (error) return error; } else if (nagcount < oagcount) { @@ -145,15 +146,17 @@ xfs_growfs_data_private( if (error) return error; + last_pag = xfs_perag_get(mp, oagcount - 1); if (delta > 0) { error = xfs_resizefs_init_new_ags(tp, &id, oagcount, nagcount, - delta, &lastag_extended); + delta, last_pag, &lastag_extended); } else { xfs_warn_mount(mp, XFS_OPSTATE_WARNED_SHRINK, "EXPERIMENTAL online shrink feature in use. Use at your own risk!"); - error = xfs_ag_shrink_space(mp, &tp, nagcount - 1, -delta); + error = xfs_ag_shrink_space(last_pag, &tp, -delta); } + xfs_perag_put(last_pag); if (error) goto out_trans_cancel; @@ -528,6 +531,9 @@ xfs_do_force_shutdown( } else if (flags & SHUTDOWN_CORRUPT_INCORE) { tag = XFS_PTAG_SHUTDOWN_CORRUPT; why = "Corruption of in-memory data"; + } else if (flags & SHUTDOWN_CORRUPT_ONDISK) { + tag = XFS_PTAG_SHUTDOWN_CORRUPT; + why = "Corruption of on-disk metadata"; } else { tag = XFS_PTAG_SHUTDOWN_IOERROR; why = "Metadata I/O Error"; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 2609825d53ee..2bbe7916a998 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -98,8 +98,9 @@ xfs_inode_alloc( ip->i_ino = ino; ip->i_mount = mp; memset(&ip->i_imap, 0, sizeof(struct xfs_imap)); - ip->i_afp = NULL; ip->i_cowfp = NULL; + memset(&ip->i_af, 0, sizeof(ip->i_af)); + ip->i_af.if_format = XFS_DINODE_FMT_EXTENTS; memset(&ip->i_df, 0, sizeof(ip->i_df)); ip->i_flags = 0; ip->i_delayed_blks = 0; @@ -111,6 +112,8 @@ xfs_inode_alloc( INIT_WORK(&ip->i_ioend_work, xfs_end_io); INIT_LIST_HEAD(&ip->i_ioend_list); spin_lock_init(&ip->i_ioend_lock); + ip->i_next_unlinked = NULLAGINO; + ip->i_prev_unlinked = NULLAGINO; return ip; } @@ -130,10 +133,8 @@ xfs_inode_free_callback( break; } - if (ip->i_afp) { - xfs_idestroy_fork(ip->i_afp); - kmem_cache_free(xfs_ifork_cache, ip->i_afp); - } + xfs_ifork_zap_attr(ip); + if (ip->i_cowfp) { xfs_idestroy_fork(ip->i_cowfp); kmem_cache_free(xfs_ifork_cache, ip->i_cowfp); @@ -912,6 +913,7 @@ reclaim: ip->i_checked = 0; spin_unlock(&ip->i_flags_lock); + ASSERT(!ip->i_itemp || ip->i_itemp->ili_item.li_buf == NULL); xfs_iunlock(ip, XFS_ILOCK_EXCL); XFS_STATS_INC(ip->i_mount, xs_ig_reclaims); @@ -1774,7 +1776,7 @@ xfs_check_delalloc( struct xfs_inode *ip, int whichfork) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec got; struct xfs_iext_cursor icur; @@ -2219,5 +2221,5 @@ xfs_inodegc_register_shrinker( shrink->flags = SHRINKER_NONSLAB; shrink->batch = XFS_INODEGC_SHRINKER_BATCH; - return register_shrinker(shrink); + return register_shrinker(shrink, "xfs-inodegc:%s", mp->m_super->s_id); } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 3e1c62ffa4f7..28493c8e9bb2 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -20,6 +20,7 @@ #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_inode_item.h" +#include "xfs_iunlink_item.h" #include "xfs_ialloc.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" @@ -125,7 +126,7 @@ xfs_ilock_attr_map_shared( { uint lock_mode = XFS_ILOCK_SHARED; - if (ip->i_afp && xfs_need_iread_extents(ip->i_afp)) + if (xfs_inode_has_attr_fork(ip) && xfs_need_iread_extents(&ip->i_af)) lock_mode = XFS_ILOCK_EXCL; xfs_ilock(ip, lock_mode); return lock_mode; @@ -635,7 +636,7 @@ xfs_ip2xflags( flags |= FS_XFLAG_COWEXTSIZE; } - if (XFS_IFORK_Q(ip)) + if (xfs_inode_has_attr_fork(ip)) flags |= FS_XFLAG_HASATTR; return flags; } @@ -893,7 +894,7 @@ xfs_init_new_inode( */ if (init_xattrs && xfs_has_attr(mp)) { ip->i_forkoff = xfs_default_attroffset(ip) >> 3; - ip->i_afp = xfs_ifork_alloc(XFS_DINODE_FMT_EXTENTS, 0); + xfs_ifork_init_attr(ip, XFS_DINODE_FMT_EXTENTS, 0); } /* @@ -1293,8 +1294,8 @@ xfs_itruncate_clear_reflink_flags( if (!xfs_is_reflink_inode(ip)) return; - dfork = XFS_IFORK_PTR(ip, XFS_DATA_FORK); - cfork = XFS_IFORK_PTR(ip, XFS_COW_FORK); + dfork = xfs_ifork_ptr(ip, XFS_DATA_FORK); + cfork = xfs_ifork_ptr(ip, XFS_COW_FORK); if (dfork->if_bytes == 0 && cfork->if_bytes == 0) ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; if (cfork->if_bytes == 0) @@ -1643,7 +1644,7 @@ xfs_inode_needs_inactive( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *cow_ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_ifork *cow_ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); /* * If the inode is already free, then there can be nothing @@ -1762,13 +1763,12 @@ xfs_inactive( * now. The code calls a routine that recursively deconstructs the * attribute fork. If also blows away the in-core attribute fork. */ - if (XFS_IFORK_Q(ip)) { + if (xfs_inode_has_attr_fork(ip)) { error = xfs_attr_inactive(ip); if (error) goto out; } - ASSERT(!ip->i_afp); ASSERT(ip->i_forkoff == 0); /* @@ -1801,195 +1801,69 @@ out: * because we must walk that list to find the inode that points to the inode * being removed from the unlinked hash bucket list. * - * What if we modelled the unlinked list as a collection of records capturing - * "X.next_unlinked = Y" relations? If we indexed those records on Y, we'd - * have a fast way to look up unlinked list predecessors, which avoids the - * slow list walk. That's exactly what we do here (in-core) with a per-AG - * rhashtable. + * Hence we keep an in-memory double linked list to link each inode on an + * unlinked list. Because there are 64 unlinked lists per AGI, keeping pointer + * based lists would require having 64 list heads in the perag, one for each + * list. This is expensive in terms of memory (think millions of AGs) and cache + * misses on lookups. Instead, use the fact that inodes on the unlinked list + * must be referenced at the VFS level to keep them on the list and hence we + * have an existence guarantee for inodes on the unlinked list. * - * Because this is a backref cache, we ignore operational failures since the - * iunlink code can fall back to the slow bucket walk. The only errors that - * should bubble out are for obviously incorrect situations. - * - * All users of the backref cache MUST hold the AGI buffer lock to serialize - * access or have otherwise provided for concurrency control. + * Given we have an existence guarantee, we can use lockless inode cache lookups + * to resolve aginos to xfs inodes. This means we only need 8 bytes per inode + * for the double linked unlinked list, and we don't need any extra locking to + * keep the list safe as all manipulations are done under the AGI buffer lock. + * Keeping the list up to date does not require memory allocation, just finding + * the XFS inode and updating the next/prev unlinked list aginos. */ -/* Capture a "X.next_unlinked = Y" relationship. */ -struct xfs_iunlink { - struct rhash_head iu_rhash_head; - xfs_agino_t iu_agino; /* X */ - xfs_agino_t iu_next_unlinked; /* Y */ -}; - -/* Unlinked list predecessor lookup hashtable construction */ -static int -xfs_iunlink_obj_cmpfn( - struct rhashtable_compare_arg *arg, - const void *obj) -{ - const xfs_agino_t *key = arg->key; - const struct xfs_iunlink *iu = obj; - - if (iu->iu_next_unlinked != *key) - return 1; - return 0; -} - -static const struct rhashtable_params xfs_iunlink_hash_params = { - .min_size = XFS_AGI_UNLINKED_BUCKETS, - .key_len = sizeof(xfs_agino_t), - .key_offset = offsetof(struct xfs_iunlink, - iu_next_unlinked), - .head_offset = offsetof(struct xfs_iunlink, iu_rhash_head), - .automatic_shrinking = true, - .obj_cmpfn = xfs_iunlink_obj_cmpfn, -}; - /* - * Return X, where X.next_unlinked == @agino. Returns NULLAGINO if no such - * relation is found. + * Find an inode on the unlinked list. This does not take references to the + * inode as we have existence guarantees by holding the AGI buffer lock and that + * only unlinked, referenced inodes can be on the unlinked inode list. If we + * don't find the inode in cache, then let the caller handle the situation. */ -static xfs_agino_t -xfs_iunlink_lookup_backref( +static struct xfs_inode * +xfs_iunlink_lookup( struct xfs_perag *pag, xfs_agino_t agino) { - struct xfs_iunlink *iu; - - iu = rhashtable_lookup_fast(&pag->pagi_unlinked_hash, &agino, - xfs_iunlink_hash_params); - return iu ? iu->iu_agino : NULLAGINO; -} + struct xfs_inode *ip; -/* - * Take ownership of an iunlink cache entry and insert it into the hash table. - * If successful, the entry will be owned by the cache; if not, it is freed. - * Either way, the caller does not own @iu after this call. - */ -static int -xfs_iunlink_insert_backref( - struct xfs_perag *pag, - struct xfs_iunlink *iu) -{ - int error; + rcu_read_lock(); + ip = radix_tree_lookup(&pag->pag_ici_root, agino); - error = rhashtable_insert_fast(&pag->pagi_unlinked_hash, - &iu->iu_rhash_head, xfs_iunlink_hash_params); /* - * Fail loudly if there already was an entry because that's a sign of - * corruption of in-memory data. Also fail loudly if we see an error - * code we didn't anticipate from the rhashtable code. Currently we - * only anticipate ENOMEM. + * Inode not in memory or in RCU freeing limbo should not happen. + * Warn about this and let the caller handle the failure. */ - if (error) { - WARN(error != -ENOMEM, "iunlink cache insert error %d", error); - kmem_free(iu); + if (WARN_ON_ONCE(!ip || !ip->i_ino)) { + rcu_read_unlock(); + return NULL; } - /* - * Absorb any runtime errors that aren't a result of corruption because - * this is a cache and we can always fall back to bucket list scanning. - */ - if (error != 0 && error != -EEXIST) - error = 0; - return error; + ASSERT(!xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM)); + rcu_read_unlock(); + return ip; } -/* Remember that @prev_agino.next_unlinked = @this_agino. */ +/* Update the prev pointer of the next agino. */ static int -xfs_iunlink_add_backref( +xfs_iunlink_update_backref( struct xfs_perag *pag, xfs_agino_t prev_agino, - xfs_agino_t this_agino) -{ - struct xfs_iunlink *iu; - - if (XFS_TEST_ERROR(false, pag->pag_mount, XFS_ERRTAG_IUNLINK_FALLBACK)) - return 0; - - iu = kmem_zalloc(sizeof(*iu), KM_NOFS); - iu->iu_agino = prev_agino; - iu->iu_next_unlinked = this_agino; - - return xfs_iunlink_insert_backref(pag, iu); -} - -/* - * Replace X.next_unlinked = @agino with X.next_unlinked = @next_unlinked. - * If @next_unlinked is NULLAGINO, we drop the backref and exit. If there - * wasn't any such entry then we don't bother. - */ -static int -xfs_iunlink_change_backref( - struct xfs_perag *pag, - xfs_agino_t agino, - xfs_agino_t next_unlinked) + xfs_agino_t next_agino) { - struct xfs_iunlink *iu; - int error; - - /* Look up the old entry; if there wasn't one then exit. */ - iu = rhashtable_lookup_fast(&pag->pagi_unlinked_hash, &agino, - xfs_iunlink_hash_params); - if (!iu) - return 0; - - /* - * Remove the entry. This shouldn't ever return an error, but if we - * couldn't remove the old entry we don't want to add it again to the - * hash table, and if the entry disappeared on us then someone's - * violated the locking rules and we need to fail loudly. Either way - * we cannot remove the inode because internal state is or would have - * been corrupt. - */ - error = rhashtable_remove_fast(&pag->pagi_unlinked_hash, - &iu->iu_rhash_head, xfs_iunlink_hash_params); - if (error) - return error; + struct xfs_inode *ip; - /* If there is no new next entry just free our item and return. */ - if (next_unlinked == NULLAGINO) { - kmem_free(iu); + /* No update necessary if we are at the end of the list. */ + if (next_agino == NULLAGINO) return 0; - } - /* Update the entry and re-add it to the hash table. */ - iu->iu_next_unlinked = next_unlinked; - return xfs_iunlink_insert_backref(pag, iu); -} - -/* Set up the in-core predecessor structures. */ -int -xfs_iunlink_init( - struct xfs_perag *pag) -{ - return rhashtable_init(&pag->pagi_unlinked_hash, - &xfs_iunlink_hash_params); -} - -/* Free the in-core predecessor structures. */ -static void -xfs_iunlink_free_item( - void *ptr, - void *arg) -{ - struct xfs_iunlink *iu = ptr; - bool *freed_anything = arg; - - *freed_anything = true; - kmem_free(iu); -} - -void -xfs_iunlink_destroy( - struct xfs_perag *pag) -{ - bool freed_anything = false; - - rhashtable_free_and_destroy(&pag->pagi_unlinked_hash, - xfs_iunlink_free_item, &freed_anything); - - ASSERT(freed_anything == false || xfs_is_shutdown(pag->pag_mount)); + ip = xfs_iunlink_lookup(pag, next_agino); + if (!ip) + return -EFSCORRUPTED; + ip->i_prev_unlinked = prev_agino; + return 0; } /* @@ -2008,7 +1882,7 @@ xfs_iunlink_update_bucket( xfs_agino_t old_value; int offset; - ASSERT(xfs_verify_agino_or_null(tp->t_mountp, pag->pag_agno, new_agino)); + ASSERT(xfs_verify_agino_or_null(pag, new_agino)); old_value = be32_to_cpu(agi->agi_unlinked[bucket_index]); trace_xfs_iunlink_update_bucket(tp->t_mountp, pag->pag_agno, bucket_index, @@ -2031,88 +1905,53 @@ xfs_iunlink_update_bucket( return 0; } -/* Set an on-disk inode's next_unlinked pointer. */ -STATIC void -xfs_iunlink_update_dinode( - struct xfs_trans *tp, - struct xfs_perag *pag, - xfs_agino_t agino, - struct xfs_buf *ibp, - struct xfs_dinode *dip, - struct xfs_imap *imap, - xfs_agino_t next_agino) -{ - struct xfs_mount *mp = tp->t_mountp; - int offset; - - ASSERT(xfs_verify_agino_or_null(mp, pag->pag_agno, next_agino)); - - trace_xfs_iunlink_update_dinode(mp, pag->pag_agno, agino, - be32_to_cpu(dip->di_next_unlinked), next_agino); - - dip->di_next_unlinked = cpu_to_be32(next_agino); - offset = imap->im_boffset + - offsetof(struct xfs_dinode, di_next_unlinked); - - /* need to recalc the inode CRC if appropriate */ - xfs_dinode_calc_crc(mp, dip); - xfs_trans_inode_buf(tp, ibp); - xfs_trans_log_buf(tp, ibp, offset, offset + sizeof(xfs_agino_t) - 1); -} - -/* Set an in-core inode's unlinked pointer and return the old value. */ -STATIC int -xfs_iunlink_update_inode( +static int +xfs_iunlink_insert_inode( struct xfs_trans *tp, - struct xfs_inode *ip, struct xfs_perag *pag, - xfs_agino_t next_agino, - xfs_agino_t *old_next_agino) + struct xfs_buf *agibp, + struct xfs_inode *ip) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_dinode *dip; - struct xfs_buf *ibp; - xfs_agino_t old_value; + struct xfs_agi *agi = agibp->b_addr; + xfs_agino_t next_agino; + xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); + short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS; int error; - ASSERT(xfs_verify_agino_or_null(mp, pag->pag_agno, next_agino)); - - error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &ibp); - if (error) - return error; - dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset); - - /* Make sure the old pointer isn't garbage. */ - old_value = be32_to_cpu(dip->di_next_unlinked); - if (!xfs_verify_agino_or_null(mp, pag->pag_agno, old_value)) { - xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, - sizeof(*dip), __this_address); - error = -EFSCORRUPTED; - goto out; + /* + * Get the index into the agi hash table for the list this inode will + * go on. Make sure the pointer isn't garbage and that this inode + * isn't already on the list. + */ + next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]); + if (next_agino == agino || + !xfs_verify_agino_or_null(pag, next_agino)) { + xfs_buf_mark_corrupt(agibp); + return -EFSCORRUPTED; } /* - * Since we're updating a linked list, we should never find that the - * current pointer is the same as the new value, unless we're - * terminating the list. + * Update the prev pointer in the next inode to point back to this + * inode. */ - *old_next_agino = old_value; - if (old_value == next_agino) { - if (next_agino != NULLAGINO) { - xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, - dip, sizeof(*dip), __this_address); - error = -EFSCORRUPTED; - } - goto out; + error = xfs_iunlink_update_backref(pag, agino, next_agino); + if (error) + return error; + + if (next_agino != NULLAGINO) { + /* + * There is already another inode in the bucket, so point this + * inode to the current head of the list. + */ + error = xfs_iunlink_log_inode(tp, ip, pag, next_agino); + if (error) + return error; + ip->i_next_unlinked = next_agino; } - /* Ok, update the new pointer. */ - xfs_iunlink_update_dinode(tp, pag, XFS_INO_TO_AGINO(mp, ip->i_ino), - ibp, dip, &ip->i_imap, next_agino); - return 0; -out: - xfs_trans_brelse(tp, ibp); - return error; + /* Point the head of the list to point to this inode. */ + return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino); } /* @@ -2129,11 +1968,7 @@ xfs_iunlink( { struct xfs_mount *mp = tp->t_mountp; struct xfs_perag *pag; - struct xfs_agi *agi; struct xfs_buf *agibp; - xfs_agino_t next_agino; - xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); - short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS; int error; ASSERT(VFS_I(ip)->i_nlink == 0); @@ -2143,202 +1978,38 @@ xfs_iunlink( pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); /* Get the agi buffer first. It ensures lock ordering on the list. */ - error = xfs_read_agi(mp, tp, pag->pag_agno, &agibp); + error = xfs_read_agi(pag, tp, &agibp); if (error) goto out; - agi = agibp->b_addr; - - /* - * Get the index into the agi hash table for the list this inode will - * go on. Make sure the pointer isn't garbage and that this inode - * isn't already on the list. - */ - next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]); - if (next_agino == agino || - !xfs_verify_agino_or_null(mp, pag->pag_agno, next_agino)) { - xfs_buf_mark_corrupt(agibp); - error = -EFSCORRUPTED; - goto out; - } - - if (next_agino != NULLAGINO) { - xfs_agino_t old_agino; - - /* - * There is already another inode in the bucket, so point this - * inode to the current head of the list. - */ - error = xfs_iunlink_update_inode(tp, ip, pag, next_agino, - &old_agino); - if (error) - goto out; - ASSERT(old_agino == NULLAGINO); - /* - * agino has been unlinked, add a backref from the next inode - * back to agino. - */ - error = xfs_iunlink_add_backref(pag, agino, next_agino); - if (error) - goto out; - } - - /* Point the head of the list to point to this inode. */ - error = xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino); + error = xfs_iunlink_insert_inode(tp, pag, agibp, ip); out: xfs_perag_put(pag); return error; } -/* Return the imap, dinode pointer, and buffer for an inode. */ -STATIC int -xfs_iunlink_map_ino( - struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agino_t agino, - struct xfs_imap *imap, - struct xfs_dinode **dipp, - struct xfs_buf **bpp) -{ - struct xfs_mount *mp = tp->t_mountp; - int error; - - imap->im_blkno = 0; - error = xfs_imap(mp, tp, XFS_AGINO_TO_INO(mp, agno, agino), imap, 0); - if (error) { - xfs_warn(mp, "%s: xfs_imap returned error %d.", - __func__, error); - return error; - } - - error = xfs_imap_to_bp(mp, tp, imap, bpp); - if (error) { - xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.", - __func__, error); - return error; - } - - *dipp = xfs_buf_offset(*bpp, imap->im_boffset); - return 0; -} - -/* - * Walk the unlinked chain from @head_agino until we find the inode that - * points to @target_agino. Return the inode number, map, dinode pointer, - * and inode cluster buffer of that inode as @agino, @imap, @dipp, and @bpp. - * - * @tp, @pag, @head_agino, and @target_agino are input parameters. - * @agino, @imap, @dipp, and @bpp are all output parameters. - * - * Do not call this function if @target_agino is the head of the list. - */ -STATIC int -xfs_iunlink_map_prev( - struct xfs_trans *tp, - struct xfs_perag *pag, - xfs_agino_t head_agino, - xfs_agino_t target_agino, - xfs_agino_t *agino, - struct xfs_imap *imap, - struct xfs_dinode **dipp, - struct xfs_buf **bpp) -{ - struct xfs_mount *mp = tp->t_mountp; - xfs_agino_t next_agino; - int error; - - ASSERT(head_agino != target_agino); - *bpp = NULL; - - /* See if our backref cache can find it faster. */ - *agino = xfs_iunlink_lookup_backref(pag, target_agino); - if (*agino != NULLAGINO) { - error = xfs_iunlink_map_ino(tp, pag->pag_agno, *agino, imap, - dipp, bpp); - if (error) - return error; - - if (be32_to_cpu((*dipp)->di_next_unlinked) == target_agino) - return 0; - - /* - * If we get here the cache contents were corrupt, so drop the - * buffer and fall back to walking the bucket list. - */ - xfs_trans_brelse(tp, *bpp); - *bpp = NULL; - WARN_ON_ONCE(1); - } - - trace_xfs_iunlink_map_prev_fallback(mp, pag->pag_agno); - - /* Otherwise, walk the entire bucket until we find it. */ - next_agino = head_agino; - while (next_agino != target_agino) { - xfs_agino_t unlinked_agino; - - if (*bpp) - xfs_trans_brelse(tp, *bpp); - - *agino = next_agino; - error = xfs_iunlink_map_ino(tp, pag->pag_agno, next_agino, imap, - dipp, bpp); - if (error) - return error; - - unlinked_agino = be32_to_cpu((*dipp)->di_next_unlinked); - /* - * Make sure this pointer is valid and isn't an obvious - * infinite loop. - */ - if (!xfs_verify_agino(mp, pag->pag_agno, unlinked_agino) || - next_agino == unlinked_agino) { - XFS_CORRUPTION_ERROR(__func__, - XFS_ERRLEVEL_LOW, mp, - *dipp, sizeof(**dipp)); - error = -EFSCORRUPTED; - return error; - } - next_agino = unlinked_agino; - } - - return 0; -} - -/* - * Pull the on-disk inode from the AGI unlinked list. - */ -STATIC int -xfs_iunlink_remove( +static int +xfs_iunlink_remove_inode( struct xfs_trans *tp, struct xfs_perag *pag, + struct xfs_buf *agibp, struct xfs_inode *ip) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_agi *agi; - struct xfs_buf *agibp; - struct xfs_buf *last_ibp; - struct xfs_dinode *last_dip = NULL; + struct xfs_agi *agi = agibp->b_addr; xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); - xfs_agino_t next_agino; xfs_agino_t head_agino; short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS; int error; trace_xfs_iunlink_remove(ip); - /* Get the agi buffer first. It ensures lock ordering on the list. */ - error = xfs_read_agi(mp, tp, pag->pag_agno, &agibp); - if (error) - return error; - agi = agibp->b_addr; - /* * Get the index into the agi hash table for the list this inode will * go on. Make sure the head pointer isn't garbage. */ head_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]); - if (!xfs_verify_agino(mp, pag->pag_agno, head_agino)) { + if (!xfs_verify_agino(pag, head_agino)) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, agi, sizeof(*agi)); return -EFSCORRUPTED; @@ -2349,52 +2020,60 @@ xfs_iunlink_remove( * the old pointer value so that we can update whatever was previous * to us in the list to point to whatever was next in the list. */ - error = xfs_iunlink_update_inode(tp, ip, pag, NULLAGINO, &next_agino); + error = xfs_iunlink_log_inode(tp, ip, pag, NULLAGINO); if (error) return error; /* - * If there was a backref pointing from the next inode back to this - * one, remove it because we've removed this inode from the list. - * - * Later, if this inode was in the middle of the list we'll update - * this inode's backref to point from the next inode. + * Update the prev pointer in the next inode to point back to previous + * inode in the chain. */ - if (next_agino != NULLAGINO) { - error = xfs_iunlink_change_backref(pag, next_agino, NULLAGINO); - if (error) - return error; - } + error = xfs_iunlink_update_backref(pag, ip->i_prev_unlinked, + ip->i_next_unlinked); + if (error) + return error; if (head_agino != agino) { - struct xfs_imap imap; - xfs_agino_t prev_agino; + struct xfs_inode *prev_ip; - /* We need to search the list for the inode being freed. */ - error = xfs_iunlink_map_prev(tp, pag, head_agino, agino, - &prev_agino, &imap, &last_dip, &last_ibp); - if (error) - return error; + prev_ip = xfs_iunlink_lookup(pag, ip->i_prev_unlinked); + if (!prev_ip) + return -EFSCORRUPTED; - /* Point the previous inode on the list to the next inode. */ - xfs_iunlink_update_dinode(tp, pag, prev_agino, last_ibp, - last_dip, &imap, next_agino); - - /* - * Now we deal with the backref for this inode. If this inode - * pointed at a real inode, change the backref that pointed to - * us to point to our old next. If this inode was the end of - * the list, delete the backref that pointed to us. Note that - * change_backref takes care of deleting the backref if - * next_agino is NULLAGINO. - */ - return xfs_iunlink_change_backref(agibp->b_pag, agino, - next_agino); + error = xfs_iunlink_log_inode(tp, prev_ip, pag, + ip->i_next_unlinked); + prev_ip->i_next_unlinked = ip->i_next_unlinked; + } else { + /* Point the head of the list to the next unlinked inode. */ + error = xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, + ip->i_next_unlinked); } - /* Point the head of the list to the next unlinked inode. */ - return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, - next_agino); + ip->i_next_unlinked = NULLAGINO; + ip->i_prev_unlinked = NULLAGINO; + return error; +} + +/* + * Pull the on-disk inode from the AGI unlinked list. + */ +STATIC int +xfs_iunlink_remove( + struct xfs_trans *tp, + struct xfs_perag *pag, + struct xfs_inode *ip) +{ + struct xfs_buf *agibp; + int error; + + trace_xfs_iunlink_remove(ip); + + /* Get the agi buffer first. It ensures lock ordering on the list. */ + error = xfs_read_agi(pag, tp, &agibp); + if (error) + return error; + + return xfs_iunlink_remove_inode(tp, pag, agibp, ip); } /* @@ -3032,10 +2711,12 @@ out_trans_abort: static int xfs_rename_alloc_whiteout( struct user_namespace *mnt_userns, + struct xfs_name *src_name, struct xfs_inode *dp, struct xfs_inode **wip) { struct xfs_inode *tmpfile; + struct qstr name; int error; error = xfs_create_tmpfile(mnt_userns, dp, S_IFCHR | WHITEOUT_MODE, @@ -3043,6 +2724,15 @@ xfs_rename_alloc_whiteout( if (error) return error; + name.name = src_name->name; + name.len = src_name->len; + error = xfs_inode_init_security(VFS_I(tmpfile), VFS_I(dp), &name); + if (error) { + xfs_finish_inode_setup(tmpfile); + xfs_irele(tmpfile); + return error; + } + /* * Prepare the tmpfile inode as if it were created through the VFS. * Complete the inode setup and flag it as linkable. nlink is already @@ -3093,7 +2783,8 @@ xfs_rename( * appropriately. */ if (flags & RENAME_WHITEOUT) { - error = xfs_rename_alloc_whiteout(mnt_userns, target_dp, &wip); + error = xfs_rename_alloc_whiteout(mnt_userns, src_name, + target_dp, &wip); if (error) return error; @@ -3229,11 +2920,13 @@ retry: if (inodes[i] == wip || (inodes[i] == target_ip && (VFS_I(target_ip)->i_nlink == 1 || src_is_directory))) { - struct xfs_buf *bp; - xfs_agnumber_t agno; + struct xfs_perag *pag; + struct xfs_buf *bp; - agno = XFS_INO_TO_AGNO(mp, inodes[i]->i_ino); - error = xfs_read_agi(mp, tp, agno, &bp); + pag = xfs_perag_get(mp, + XFS_INO_TO_AGNO(mp, inodes[i]->i_ino)); + error = xfs_read_agi(pag, tp, &bp); + xfs_perag_put(pag); if (error) goto out_trans_cancel; } @@ -3452,13 +3145,13 @@ xfs_iflush( goto flush_out; } } - if (XFS_TEST_ERROR(ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp) > + if (XFS_TEST_ERROR(ip->i_df.if_nextents + xfs_ifork_nextents(&ip->i_af) > ip->i_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: detected corrupt incore inode %llu, " "total extents = %llu nblocks = %lld, ptr "PTR_FMT, __func__, ip->i_ino, - ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp), + ip->i_df.if_nextents + xfs_ifork_nextents(&ip->i_af), ip->i_nblocks, ip); goto flush_out; } @@ -3488,7 +3181,8 @@ xfs_iflush( if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL && xfs_ifork_verify_local_data(ip)) goto flush_out; - if (ip->i_afp && ip->i_afp->if_format == XFS_DINODE_FMT_LOCAL && + if (xfs_inode_has_attr_fork(ip) && + ip->i_af.if_format == XFS_DINODE_FMT_LOCAL && xfs_ifork_verify_local_attr(ip)) goto flush_out; @@ -3506,7 +3200,7 @@ xfs_iflush( } xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK); - if (XFS_IFORK_Q(ip)) + if (xfs_inode_has_attr_fork(ip)) xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK); /* @@ -3753,6 +3447,50 @@ retry: return 0; } +static int +xfs_mmaplock_two_inodes_and_break_dax_layout( + struct xfs_inode *ip1, + struct xfs_inode *ip2) +{ + int error; + bool retry; + struct page *page; + + if (ip1->i_ino > ip2->i_ino) + swap(ip1, ip2); + +again: + retry = false; + /* Lock the first inode */ + xfs_ilock(ip1, XFS_MMAPLOCK_EXCL); + error = xfs_break_dax_layouts(VFS_I(ip1), &retry); + if (error || retry) { + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + if (error == 0 && retry) + goto again; + return error; + } + + if (ip1 == ip2) + return 0; + + /* Nested lock the second inode */ + xfs_ilock(ip2, xfs_lock_inumorder(XFS_MMAPLOCK_EXCL, 1)); + /* + * We cannot use xfs_break_dax_layouts() directly here because it may + * need to unlock & lock the XFS_MMAPLOCK_EXCL which is not suitable + * for this nested lock case. + */ + page = dax_layout_busy_page(VFS_I(ip2)->i_mapping); + if (page && page_ref_count(page) != 1) { + xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + goto again; + } + + return 0; +} + /* * Lock two inodes so that userspace cannot initiate I/O via file syscalls or * mmap activity. @@ -3767,8 +3505,19 @@ xfs_ilock2_io_mmap( ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2)); if (ret) return ret; - filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping, - VFS_I(ip2)->i_mapping); + + if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) { + ret = xfs_mmaplock_two_inodes_and_break_dax_layout(ip1, ip2); + if (ret) { + inode_unlock(VFS_I(ip2)); + if (ip1 != ip2) + inode_unlock(VFS_I(ip1)); + return ret; + } + } else + filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping, + VFS_I(ip2)->i_mapping); + return 0; } @@ -3778,8 +3527,14 @@ xfs_iunlock2_io_mmap( struct xfs_inode *ip1, struct xfs_inode *ip2) { - filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping, - VFS_I(ip2)->i_mapping); + if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) { + xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); + if (ip1 != ip2) + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + } else + filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping, + VFS_I(ip2)->i_mapping); + inode_unlock(VFS_I(ip2)); if (ip1 != ip2) inode_unlock(VFS_I(ip1)); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 7be6f8e705ab..fa780f08dc89 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -33,9 +33,9 @@ typedef struct xfs_inode { struct xfs_imap i_imap; /* location for xfs_imap() */ /* Extent information. */ - struct xfs_ifork *i_afp; /* attribute fork pointer */ struct xfs_ifork *i_cowfp; /* copy on write extents */ struct xfs_ifork i_df; /* data fork */ + struct xfs_ifork i_af; /* attribute fork */ /* Transaction and locking information. */ struct xfs_inode_log_item *i_itemp; /* logging information */ @@ -68,6 +68,10 @@ typedef struct xfs_inode { uint64_t i_diflags2; /* XFS_DIFLAG2_... */ struct timespec64 i_crtime; /* time created */ + /* unlinked list pointers */ + xfs_agino_t i_next_unlinked; + xfs_agino_t i_prev_unlinked; + /* VFS inode */ struct inode i_vnode; /* embedded VFS inode */ @@ -77,6 +81,66 @@ typedef struct xfs_inode { struct list_head i_ioend_list; } xfs_inode_t; +static inline bool xfs_inode_has_attr_fork(struct xfs_inode *ip) +{ + return ip->i_forkoff > 0; +} + +static inline struct xfs_ifork * +xfs_ifork_ptr( + struct xfs_inode *ip, + int whichfork) +{ + switch (whichfork) { + case XFS_DATA_FORK: + return &ip->i_df; + case XFS_ATTR_FORK: + if (!xfs_inode_has_attr_fork(ip)) + return NULL; + return &ip->i_af; + case XFS_COW_FORK: + return ip->i_cowfp; + default: + ASSERT(0); + return NULL; + } +} + +static inline unsigned int xfs_inode_fork_boff(struct xfs_inode *ip) +{ + return ip->i_forkoff << 3; +} + +static inline unsigned int xfs_inode_data_fork_size(struct xfs_inode *ip) +{ + if (xfs_inode_has_attr_fork(ip)) + return xfs_inode_fork_boff(ip); + + return XFS_LITINO(ip->i_mount); +} + +static inline unsigned int xfs_inode_attr_fork_size(struct xfs_inode *ip) +{ + if (xfs_inode_has_attr_fork(ip)) + return XFS_LITINO(ip->i_mount) - xfs_inode_fork_boff(ip); + return 0; +} + +static inline unsigned int +xfs_inode_fork_size( + struct xfs_inode *ip, + int whichfork) +{ + switch (whichfork) { + case XFS_DATA_FORK: + return xfs_inode_data_fork_size(ip); + case XFS_ATTR_FORK: + return xfs_inode_attr_fork_size(ip); + default: + return 0; + } +} + /* Convert from vfs inode to xfs inode */ static inline struct xfs_inode *XFS_I(struct inode *inode) { @@ -467,6 +531,7 @@ xfs_itruncate_extents( } /* from xfs_file.c */ +int xfs_break_dax_layouts(struct inode *inode, bool *retry); int xfs_break_layouts(struct inode *inode, uint *iolock, enum layout_break_reason reason); @@ -505,9 +570,6 @@ extern struct kmem_cache *xfs_inode_cache; bool xfs_inode_needs_inactive(struct xfs_inode *ip); -int xfs_iunlink_init(struct xfs_perag *pag); -void xfs_iunlink_destroy(struct xfs_perag *pag); - void xfs_end_io(struct work_struct *work); int xfs_ilock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 721def0639fd..6e19ece916bf 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -57,7 +57,7 @@ xfs_inode_item_data_fork_size( ip->i_df.if_nextents > 0 && ip->i_df.if_bytes > 0) { /* worst case, doesn't subtract delalloc extents */ - *nbytes += XFS_IFORK_DSIZE(ip); + *nbytes += xfs_inode_data_fork_size(ip); *nvecs += 1; } break; @@ -92,27 +92,27 @@ xfs_inode_item_attr_fork_size( { struct xfs_inode *ip = iip->ili_inode; - switch (ip->i_afp->if_format) { + switch (ip->i_af.if_format) { case XFS_DINODE_FMT_EXTENTS: if ((iip->ili_fields & XFS_ILOG_AEXT) && - ip->i_afp->if_nextents > 0 && - ip->i_afp->if_bytes > 0) { + ip->i_af.if_nextents > 0 && + ip->i_af.if_bytes > 0) { /* worst case, doesn't subtract unused space */ - *nbytes += XFS_IFORK_ASIZE(ip); + *nbytes += xfs_inode_attr_fork_size(ip); *nvecs += 1; } break; case XFS_DINODE_FMT_BTREE: if ((iip->ili_fields & XFS_ILOG_ABROOT) && - ip->i_afp->if_broot_bytes > 0) { - *nbytes += ip->i_afp->if_broot_bytes; + ip->i_af.if_broot_bytes > 0) { + *nbytes += ip->i_af.if_broot_bytes; *nvecs += 1; } break; case XFS_DINODE_FMT_LOCAL: if ((iip->ili_fields & XFS_ILOG_ADATA) && - ip->i_afp->if_bytes > 0) { - *nbytes += xlog_calc_iovec_len(ip->i_afp->if_bytes); + ip->i_af.if_bytes > 0) { + *nbytes += xlog_calc_iovec_len(ip->i_af.if_bytes); *nvecs += 1; } break; @@ -143,7 +143,7 @@ xfs_inode_item_size( xfs_log_dinode_size(ip->i_mount); xfs_inode_item_data_fork_size(iip, nvecs, nbytes); - if (XFS_IFORK_Q(ip)) + if (xfs_inode_has_attr_fork(ip)) xfs_inode_item_attr_fork_size(iip, nvecs, nbytes); } @@ -237,18 +237,18 @@ xfs_inode_item_format_attr_fork( struct xfs_inode *ip = iip->ili_inode; size_t data_bytes; - switch (ip->i_afp->if_format) { + switch (ip->i_af.if_format) { case XFS_DINODE_FMT_EXTENTS: iip->ili_fields &= ~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT); if ((iip->ili_fields & XFS_ILOG_AEXT) && - ip->i_afp->if_nextents > 0 && - ip->i_afp->if_bytes > 0) { + ip->i_af.if_nextents > 0 && + ip->i_af.if_bytes > 0) { struct xfs_bmbt_rec *p; - ASSERT(xfs_iext_count(ip->i_afp) == - ip->i_afp->if_nextents); + ASSERT(xfs_iext_count(&ip->i_af) == + ip->i_af.if_nextents); p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_EXT); data_bytes = xfs_iextents_copy(ip, p, XFS_ATTR_FORK); @@ -265,13 +265,13 @@ xfs_inode_item_format_attr_fork( ~(XFS_ILOG_ADATA | XFS_ILOG_AEXT); if ((iip->ili_fields & XFS_ILOG_ABROOT) && - ip->i_afp->if_broot_bytes > 0) { - ASSERT(ip->i_afp->if_broot != NULL); + ip->i_af.if_broot_bytes > 0) { + ASSERT(ip->i_af.if_broot != NULL); xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_BROOT, - ip->i_afp->if_broot, - ip->i_afp->if_broot_bytes); - ilf->ilf_asize = ip->i_afp->if_broot_bytes; + ip->i_af.if_broot, + ip->i_af.if_broot_bytes); + ilf->ilf_asize = ip->i_af.if_broot_bytes; ilf->ilf_size++; } else { iip->ili_fields &= ~XFS_ILOG_ABROOT; @@ -282,12 +282,12 @@ xfs_inode_item_format_attr_fork( ~(XFS_ILOG_AEXT | XFS_ILOG_ABROOT); if ((iip->ili_fields & XFS_ILOG_ADATA) && - ip->i_afp->if_bytes > 0) { - ASSERT(ip->i_afp->if_u1.if_data != NULL); + ip->i_af.if_bytes > 0) { + ASSERT(ip->i_af.if_u1.if_data != NULL); xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL, - ip->i_afp->if_u1.if_data, - ip->i_afp->if_bytes); - ilf->ilf_asize = (unsigned)ip->i_afp->if_bytes; + ip->i_af.if_u1.if_data, + ip->i_af.if_bytes); + ilf->ilf_asize = (unsigned)ip->i_af.if_bytes; ilf->ilf_size++; } else { iip->ili_fields &= ~XFS_ILOG_ADATA; @@ -355,11 +355,11 @@ xfs_inode_to_log_dinode_iext_counters( { if (xfs_inode_has_large_extent_counts(ip)) { to->di_big_nextents = xfs_ifork_nextents(&ip->i_df); - to->di_big_anextents = xfs_ifork_nextents(ip->i_afp); + to->di_big_anextents = xfs_ifork_nextents(&ip->i_af); to->di_nrext64_pad = 0; } else { to->di_nextents = xfs_ifork_nextents(&ip->i_df); - to->di_anextents = xfs_ifork_nextents(ip->i_afp); + to->di_anextents = xfs_ifork_nextents(&ip->i_af); } } @@ -390,7 +390,7 @@ xfs_inode_to_log_dinode( to->di_nblocks = ip->i_nblocks; to->di_extsize = ip->i_extsize; to->di_forkoff = ip->i_forkoff; - to->di_aformat = xfs_ifork_format(ip->i_afp); + to->di_aformat = xfs_ifork_format(&ip->i_af); to->di_flags = ip->i_diflags; xfs_copy_dm_fields_to_log_dinode(ip, to); @@ -480,7 +480,7 @@ xfs_inode_item_format( xfs_inode_item_format_core(ip, lv, &vecp); xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp); - if (XFS_IFORK_Q(ip)) { + if (xfs_inode_has_attr_fork(ip)) { xfs_inode_item_format_attr_fork(iip, ilf, lv, &vecp); } else { iip->ili_fields &= diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 0d67ff8a8961..1f783e979629 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -955,6 +955,7 @@ xfs_ioc_ag_geometry( struct xfs_mount *mp, void __user *arg) { + struct xfs_perag *pag; struct xfs_ag_geometry ageo; int error; @@ -965,7 +966,12 @@ xfs_ioc_ag_geometry( if (memchr_inv(&ageo.ag_reserved, 0, sizeof(ageo.ag_reserved))) return -EINVAL; - error = xfs_ag_get_geometry(mp, ageo.ag_number, &ageo); + pag = xfs_perag_get(mp, ageo.ag_number); + if (!pag) + return -EINVAL; + + error = xfs_ag_get_geometry(pag, &ageo); + xfs_perag_put(pag); if (error) return error; @@ -985,7 +991,7 @@ xfs_fill_fsxattr( struct fileattr *fa) { struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); fileattr_fill_xflags(fa, xfs_ip2xflags(ip)); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 5d50fed291b4..07da03976ec1 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -159,7 +159,7 @@ xfs_iomap_eof_align_last_fsb( struct xfs_inode *ip, xfs_fileoff_t end_fsb) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); xfs_extlen_t extsz = xfs_get_extsz_hint(ip); xfs_extlen_t align = xfs_eof_alignment(ip); struct xfs_bmbt_irec irec; @@ -370,7 +370,7 @@ xfs_iomap_prealloc_size( struct xfs_iext_cursor ncur = *icur; struct xfs_bmbt_irec prev, got; struct xfs_mount *mp = ip->i_mount; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); int64_t freesp; xfs_fsblock_t qblocks; @@ -773,7 +773,8 @@ xfs_direct_write_iomap_begin( /* may drop and re-acquire the ilock */ error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared, - &lockmode, flags & IOMAP_DIRECT); + &lockmode, + (flags & IOMAP_DIRECT) || IS_DAX(inode)); if (error) goto out_unlock; if (shared) @@ -868,6 +869,33 @@ const struct iomap_ops xfs_direct_write_iomap_ops = { }; static int +xfs_dax_write_iomap_end( + struct inode *inode, + loff_t pos, + loff_t length, + ssize_t written, + unsigned flags, + struct iomap *iomap) +{ + struct xfs_inode *ip = XFS_I(inode); + + if (!xfs_is_cow_inode(ip)) + return 0; + + if (!written) { + xfs_reflink_cancel_cow_range(ip, pos, length, true); + return 0; + } + + return xfs_reflink_end_cow(ip, pos, written); +} + +const struct iomap_ops xfs_dax_write_iomap_ops = { + .iomap_begin = xfs_direct_write_iomap_begin, + .iomap_end = xfs_dax_write_iomap_end, +}; + +static int xfs_buffered_write_iomap_begin( struct inode *inode, loff_t offset, @@ -1310,12 +1338,12 @@ xfs_xattr_iomap_begin( lockmode = xfs_ilock_attr_map_shared(ip); /* if there are no attribute fork or extents, return ENOENT */ - if (!XFS_IFORK_Q(ip) || !ip->i_afp->if_nextents) { + if (!xfs_inode_has_attr_fork(ip) || !ip->i_af.if_nextents) { error = -ENOENT; goto out_unlock; } - ASSERT(ip->i_afp->if_format != XFS_DINODE_FMT_LOCAL); + ASSERT(ip->i_af.if_format != XFS_DINODE_FMT_LOCAL); error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, XFS_BMAPI_ATTRFORK); out_unlock: diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index e88dc162c785..c782e8c0479c 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -51,5 +51,6 @@ extern const struct iomap_ops xfs_direct_write_iomap_ops; extern const struct iomap_ops xfs_read_iomap_ops; extern const struct iomap_ops xfs_seek_iomap_ops; extern const struct iomap_ops xfs_xattr_iomap_ops; +extern const struct iomap_ops xfs_dax_write_iomap_ops; #endif /* __XFS_IOMAP_H__*/ diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index a7402f6ea510..45518b8c613c 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -75,9 +75,8 @@ xfs_initxattrs( * these attrs can be journalled at inode creation time (along with the * inode, of course, such that log replay can't cause these to be lost). */ - -STATIC int -xfs_init_security( +int +xfs_inode_init_security( struct inode *inode, struct inode *dir, const struct qstr *qstr) @@ -122,7 +121,7 @@ xfs_cleanup_inode( /* Oh, the horror. * If we can't add the ACL or we fail in - * xfs_init_security we must back out. + * xfs_inode_init_security we must back out. * ENOSPC can hit here, among other things. */ xfs_dentry_to_name(&teardown, dentry); @@ -208,7 +207,7 @@ xfs_generic_create( inode = VFS_I(ip); - error = xfs_init_security(inode, dir, &dentry->d_name); + error = xfs_inode_init_security(inode, dir, &dentry->d_name); if (unlikely(error)) goto out_cleanup_inode; @@ -424,7 +423,7 @@ xfs_vn_symlink( inode = VFS_I(cip); - error = xfs_init_security(inode, dir, &dentry->d_name); + error = xfs_inode_init_security(inode, dir, &dentry->d_name); if (unlikely(error)) goto out_cleanup_inode; @@ -1282,7 +1281,7 @@ xfs_setup_inode( * If there is no attribute fork no ACL can exist on this inode, * and it can't have any file capabilities attached to it either. */ - if (!XFS_IFORK_Q(ip)) { + if (!xfs_inode_has_attr_fork(ip)) { inode_has_no_xattr(inode); cache_no_acl(inode); } diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h index 278949056048..cb5fc68c9ea0 100644 --- a/fs/xfs/xfs_iops.h +++ b/fs/xfs/xfs_iops.h @@ -17,4 +17,7 @@ extern void xfs_setattr_time(struct xfs_inode *ip, struct iattr *iattr); int xfs_vn_setattr_size(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *vap); +int xfs_inode_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr); + #endif /* __XFS_IOPS_H__ */ diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index f74c9fff72bb..36312b00b164 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -111,8 +111,8 @@ xfs_bulkstat_one_int( buf->bs_extents64 = nextents; xfs_bulkstat_health(ip, buf); - buf->bs_aextents = xfs_ifork_nextents(ip->i_afp); - buf->bs_forkoff = XFS_IFORK_BOFF(ip); + buf->bs_aextents = xfs_ifork_nextents(&ip->i_af); + buf->bs_forkoff = xfs_inode_fork_boff(ip); buf->bs_version = XFS_BULKSTAT_VERSION_V5; if (xfs_has_v3inodes(mp)) { diff --git a/fs/xfs/xfs_iunlink_item.c b/fs/xfs/xfs_iunlink_item.c new file mode 100644 index 000000000000..43005ce8bd48 --- /dev/null +++ b/fs/xfs/xfs_iunlink_item.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020-2022, Red Hat, Inc. + * All Rights Reserved. + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_trans.h" +#include "xfs_trans_priv.h" +#include "xfs_ag.h" +#include "xfs_iunlink_item.h" +#include "xfs_trace.h" +#include "xfs_error.h" + +struct kmem_cache *xfs_iunlink_cache; + +static inline struct xfs_iunlink_item *IUL_ITEM(struct xfs_log_item *lip) +{ + return container_of(lip, struct xfs_iunlink_item, item); +} + +static void +xfs_iunlink_item_release( + struct xfs_log_item *lip) +{ + struct xfs_iunlink_item *iup = IUL_ITEM(lip); + + xfs_perag_put(iup->pag); + kmem_cache_free(xfs_iunlink_cache, IUL_ITEM(lip)); +} + + +static uint64_t +xfs_iunlink_item_sort( + struct xfs_log_item *lip) +{ + return IUL_ITEM(lip)->ip->i_ino; +} + +/* + * Look up the inode cluster buffer and log the on-disk unlinked inode change + * we need to make. + */ +static int +xfs_iunlink_log_dinode( + struct xfs_trans *tp, + struct xfs_iunlink_item *iup) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_inode *ip = iup->ip; + struct xfs_dinode *dip; + struct xfs_buf *ibp; + int offset; + int error; + + error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &ibp); + if (error) + return error; + /* + * Don't log the unlinked field on stale buffers as this may be the + * transaction that frees the inode cluster and relogging the buffer + * here will incorrectly remove the stale state. + */ + if (ibp->b_flags & XBF_STALE) + goto out; + + dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset); + + /* Make sure the old pointer isn't garbage. */ + if (be32_to_cpu(dip->di_next_unlinked) != iup->old_agino) { + xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, + sizeof(*dip), __this_address); + error = -EFSCORRUPTED; + goto out; + } + + trace_xfs_iunlink_update_dinode(mp, iup->pag->pag_agno, + XFS_INO_TO_AGINO(mp, ip->i_ino), + be32_to_cpu(dip->di_next_unlinked), iup->next_agino); + + dip->di_next_unlinked = cpu_to_be32(iup->next_agino); + offset = ip->i_imap.im_boffset + + offsetof(struct xfs_dinode, di_next_unlinked); + + xfs_dinode_calc_crc(mp, dip); + xfs_trans_inode_buf(tp, ibp); + xfs_trans_log_buf(tp, ibp, offset, offset + sizeof(xfs_agino_t) - 1); + return 0; +out: + xfs_trans_brelse(tp, ibp); + return error; +} + +/* + * On precommit, we grab the inode cluster buffer for the inode number we were + * passed, then update the next unlinked field for that inode in the buffer and + * log the buffer. This ensures that the inode cluster buffer was logged in the + * correct order w.r.t. other inode cluster buffers. We can then remove the + * iunlink item from the transaction and release it as it is has now served it's + * purpose. + */ +static int +xfs_iunlink_item_precommit( + struct xfs_trans *tp, + struct xfs_log_item *lip) +{ + struct xfs_iunlink_item *iup = IUL_ITEM(lip); + int error; + + error = xfs_iunlink_log_dinode(tp, iup); + list_del(&lip->li_trans); + xfs_iunlink_item_release(lip); + return error; +} + +static const struct xfs_item_ops xfs_iunlink_item_ops = { + .iop_release = xfs_iunlink_item_release, + .iop_sort = xfs_iunlink_item_sort, + .iop_precommit = xfs_iunlink_item_precommit, +}; + + +/* + * Initialize the inode log item for a newly allocated (in-core) inode. + * + * Inode extents can only reside within an AG. Hence specify the starting + * block for the inode chunk by offset within an AG as well as the + * length of the allocated extent. + * + * This joins the item to the transaction and marks it dirty so + * that we don't need a separate call to do this, nor does the + * caller need to know anything about the iunlink item. + */ +int +xfs_iunlink_log_inode( + struct xfs_trans *tp, + struct xfs_inode *ip, + struct xfs_perag *pag, + xfs_agino_t next_agino) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_iunlink_item *iup; + + ASSERT(xfs_verify_agino_or_null(pag, next_agino)); + ASSERT(xfs_verify_agino_or_null(pag, ip->i_next_unlinked)); + + /* + * Since we're updating a linked list, we should never find that the + * current pointer is the same as the new value, unless we're + * terminating the list. + */ + if (ip->i_next_unlinked == next_agino) { + if (next_agino != NULLAGINO) + return -EFSCORRUPTED; + return 0; + } + + iup = kmem_cache_zalloc(xfs_iunlink_cache, GFP_KERNEL | __GFP_NOFAIL); + xfs_log_item_init(mp, &iup->item, XFS_LI_IUNLINK, + &xfs_iunlink_item_ops); + + iup->ip = ip; + iup->next_agino = next_agino; + iup->old_agino = ip->i_next_unlinked; + + atomic_inc(&pag->pag_ref); + iup->pag = pag; + + xfs_trans_add_item(tp, &iup->item); + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &iup->item.li_flags); + return 0; +} + diff --git a/fs/xfs/xfs_iunlink_item.h b/fs/xfs/xfs_iunlink_item.h new file mode 100644 index 000000000000..c793cdcaccde --- /dev/null +++ b/fs/xfs/xfs_iunlink_item.h @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020-2022, Red Hat, Inc. + * All Rights Reserved. + */ +#ifndef XFS_IUNLINK_ITEM_H +#define XFS_IUNLINK_ITEM_H 1 + +struct xfs_trans; +struct xfs_inode; +struct xfs_perag; + +/* in memory log item structure */ +struct xfs_iunlink_item { + struct xfs_log_item item; + struct xfs_inode *ip; + struct xfs_perag *pag; + xfs_agino_t next_agino; + xfs_agino_t old_agino; +}; + +extern struct kmem_cache *xfs_iunlink_cache; + +int xfs_iunlink_log_inode(struct xfs_trans *tp, struct xfs_inode *ip, + struct xfs_perag *pag, xfs_agino_t next_agino); + +#endif /* XFS_IUNLINK_ITEM_H */ diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index ae904b21e9cc..386b0307aed8 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -57,7 +57,8 @@ xlog_grant_push_ail( STATIC void xlog_sync( struct xlog *log, - struct xlog_in_core *iclog); + struct xlog_in_core *iclog, + struct xlog_ticket *ticket); #if defined(DEBUG) STATIC void xlog_verify_grant_tail( @@ -567,7 +568,8 @@ xlog_state_shutdown_callbacks( int xlog_state_release_iclog( struct xlog *log, - struct xlog_in_core *iclog) + struct xlog_in_core *iclog, + struct xlog_ticket *ticket) { xfs_lsn_t tail_lsn; bool last_ref; @@ -614,7 +616,7 @@ xlog_state_release_iclog( trace_xlog_iclog_syncing(iclog, _RET_IP_); spin_unlock(&log->l_icloglock); - xlog_sync(log, iclog); + xlog_sync(log, iclog, ticket); spin_lock(&log->l_icloglock); return 0; } @@ -881,7 +883,7 @@ xlog_force_iclog( iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; if (iclog->ic_state == XLOG_STATE_ACTIVE) xlog_state_switch_iclogs(iclog->ic_log, iclog, 0); - return xlog_state_release_iclog(iclog->ic_log, iclog); + return xlog_state_release_iclog(iclog->ic_log, iclog, NULL); } /* @@ -944,6 +946,8 @@ xlog_write_unmount_record( .lv_niovecs = 1, .lv_iovecp = ®, }; + LIST_HEAD(lv_chain); + list_add(&vec.lv_list, &lv_chain); BUILD_BUG_ON((sizeof(struct xlog_op_header) + sizeof(struct xfs_unmount_log_format)) != @@ -952,7 +956,7 @@ xlog_write_unmount_record( /* account for space used by record data */ ticket->t_curr_res -= sizeof(unmount_rec); - return xlog_write(log, NULL, &vec, ticket, reg.i_len); + return xlog_write(log, NULL, &lv_chain, ticket, reg.i_len); } /* @@ -1921,9 +1925,17 @@ xlog_write_iclog( * device cache first to ensure all metadata writeback covered * by the LSN in this iclog is on stable storage. This is slow, * but it *must* complete before we issue the external log IO. + * + * If the flush fails, we cannot conclude that past metadata + * writeback from the log succeeded. Repeating the flush is + * not possible, hence we must shut down with log IO error to + * avoid shutdown re-entering this path and erroring out again. */ - if (log->l_targ != log->l_mp->m_ddev_targp) - blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev); + if (log->l_targ != log->l_mp->m_ddev_targp && + blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) { + xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); + return; + } } if (iclog->ic_flags & XLOG_ICL_NEED_FUA) iclog->ic_bio.bi_opf |= REQ_FUA; @@ -2000,7 +2012,7 @@ xlog_calc_iclog_size( } /* - * Flush out the in-core log (iclog) to the on-disk log in an asynchronous + * Flush out the in-core log (iclog) to the on-disk log in an asynchronous * fashion. Previously, we should have moved the current iclog * ptr in the log to point to the next available iclog. This allows further * write to continue while this code syncs out an iclog ready to go. @@ -2025,7 +2037,8 @@ xlog_calc_iclog_size( STATIC void xlog_sync( struct xlog *log, - struct xlog_in_core *iclog) + struct xlog_in_core *iclog, + struct xlog_ticket *ticket) { unsigned int count; /* byte count of bwrite */ unsigned int roundoff; /* roundoff to BB or stripe */ @@ -2037,12 +2050,20 @@ xlog_sync( count = xlog_calc_iclog_size(log, iclog, &roundoff); - /* move grant heads by roundoff in sync */ - xlog_grant_add_space(log, &log->l_reserve_head.grant, roundoff); - xlog_grant_add_space(log, &log->l_write_head.grant, roundoff); + /* + * If we have a ticket, account for the roundoff via the ticket + * reservation to avoid touching the hot grant heads needlessly. + * Otherwise, we have to move grant heads directly. + */ + if (ticket) { + ticket->t_curr_res -= roundoff; + } else { + xlog_grant_add_space(log, &log->l_reserve_head.grant, roundoff); + xlog_grant_add_space(log, &log->l_write_head.grant, roundoff); + } /* put cycle number in every block */ - xlog_pack_data(log, iclog, roundoff); + xlog_pack_data(log, iclog, roundoff); /* real byte length */ size = iclog->ic_offset; @@ -2275,7 +2296,7 @@ xlog_write_get_more_iclog_space( spin_lock(&log->l_icloglock); ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC); xlog_state_finish_copy(log, iclog, *record_cnt, *data_cnt); - error = xlog_state_release_iclog(log, iclog); + error = xlog_state_release_iclog(log, iclog, ticket); spin_unlock(&log->l_icloglock); if (error) return error; @@ -2471,13 +2492,13 @@ int xlog_write( struct xlog *log, struct xfs_cil_ctx *ctx, - struct xfs_log_vec *log_vector, + struct list_head *lv_chain, struct xlog_ticket *ticket, uint32_t len) { struct xlog_in_core *iclog = NULL; - struct xfs_log_vec *lv = log_vector; + struct xfs_log_vec *lv; uint32_t record_cnt = 0; uint32_t data_cnt = 0; int error = 0; @@ -2505,7 +2526,7 @@ xlog_write( if (ctx) xlog_cil_set_ctx_write_state(ctx, iclog); - while (lv) { + list_for_each_entry(lv, lv_chain, lv_list) { /* * If the entire log vec does not fit in the iclog, punt it to * the partial copy loop which can handle this case. @@ -2526,7 +2547,6 @@ xlog_write( xlog_write_full(lv, ticket, iclog, &log_offset, &len, &record_cnt, &data_cnt); } - lv = lv->lv_next; } ASSERT(len == 0); @@ -2538,7 +2558,7 @@ xlog_write( */ spin_lock(&log->l_icloglock); xlog_state_finish_copy(log, iclog, record_cnt, 0); - error = xlog_state_release_iclog(log, iclog); + error = xlog_state_release_iclog(log, iclog, ticket); spin_unlock(&log->l_icloglock); return error; @@ -2958,7 +2978,7 @@ restart: * reference to the iclog. */ if (!atomic_add_unless(&iclog->ic_refcnt, -1, 1)) - error = xlog_state_release_iclog(log, iclog); + error = xlog_state_release_iclog(log, iclog, ticket); spin_unlock(&log->l_icloglock); if (error) return error; @@ -3406,7 +3426,8 @@ xfs_log_ticket_get( static int xlog_calc_unit_res( struct xlog *log, - int unit_bytes) + int unit_bytes, + int *niclogs) { int iclog_space; uint num_headers; @@ -3486,6 +3507,8 @@ xlog_calc_unit_res( /* roundoff padding for transaction data and one for commit record */ unit_bytes += 2 * log->l_iclog_roundoff; + if (niclogs) + *niclogs = num_headers; return unit_bytes; } @@ -3494,7 +3517,7 @@ xfs_log_calc_unit_res( struct xfs_mount *mp, int unit_bytes) { - return xlog_calc_unit_res(mp->m_log, unit_bytes); + return xlog_calc_unit_res(mp->m_log, unit_bytes, NULL); } /* @@ -3512,7 +3535,7 @@ xlog_ticket_alloc( tic = kmem_cache_zalloc(xfs_log_ticket_cache, GFP_NOFS | __GFP_NOFAIL); - unit_res = xlog_calc_unit_res(log, unit_bytes); + unit_res = xlog_calc_unit_res(log, unit_bytes, &tic->t_iclog_hdrs); atomic_set(&tic->t_ref, 1); tic->t_task = current; diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index f3ce046a7d45..2728886c2963 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -9,7 +9,8 @@ struct xfs_cil_ctx; struct xfs_log_vec { - struct xfs_log_vec *lv_next; /* next lv in build list */ + struct list_head lv_list; /* CIL lv chain ptrs */ + uint32_t lv_order_id; /* chain ordering info */ int lv_niovecs; /* number of iovecs in lv */ struct xfs_log_iovec *lv_iovecp; /* iovec array */ struct xfs_log_item *lv_item; /* owner */ diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index db6cb7800251..eccbfb99e894 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -44,9 +44,20 @@ xlog_cil_ticket_alloc( * transaction overhead reservation from the first transaction commit. */ tic->t_curr_res = 0; + tic->t_iclog_hdrs = 0; return tic; } +static inline void +xlog_cil_set_iclog_hdr_count(struct xfs_cil *cil) +{ + struct xlog *log = cil->xc_log; + + atomic_set(&cil->xc_iclog_hdrs, + (XLOG_CIL_BLOCKING_SPACE_LIMIT(log) / + (log->l_iclog_size - log->l_iclog_hsize))); +} + /* * Check if the current log item was first committed in this sequence. * We can't rely on just the log item being in the CIL, we have to check @@ -61,7 +72,7 @@ xlog_item_in_current_chkpt( struct xfs_cil *cil, struct xfs_log_item *lip) { - if (list_empty(&lip->li_cil)) + if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) return false; /* @@ -93,15 +104,88 @@ xlog_cil_ctx_alloc(void) ctx = kmem_zalloc(sizeof(*ctx), KM_NOFS); INIT_LIST_HEAD(&ctx->committing); INIT_LIST_HEAD(&ctx->busy_extents); + INIT_LIST_HEAD(&ctx->log_items); + INIT_LIST_HEAD(&ctx->lv_chain); INIT_WORK(&ctx->push_work, xlog_cil_push_work); return ctx; } +/* + * Aggregate the CIL per cpu structures into global counts, lists, etc and + * clear the percpu state ready for the next context to use. This is called + * from the push code with the context lock held exclusively, hence nothing else + * will be accessing or modifying the per-cpu counters. + */ +static void +xlog_cil_push_pcp_aggregate( + struct xfs_cil *cil, + struct xfs_cil_ctx *ctx) +{ + struct xlog_cil_pcp *cilpcp; + int cpu; + + for_each_online_cpu(cpu) { + cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); + + ctx->ticket->t_curr_res += cilpcp->space_reserved; + cilpcp->space_reserved = 0; + + if (!list_empty(&cilpcp->busy_extents)) { + list_splice_init(&cilpcp->busy_extents, + &ctx->busy_extents); + } + if (!list_empty(&cilpcp->log_items)) + list_splice_init(&cilpcp->log_items, &ctx->log_items); + + /* + * We're in the middle of switching cil contexts. Reset the + * counter we use to detect when the current context is nearing + * full. + */ + cilpcp->space_used = 0; + } +} + +/* + * Aggregate the CIL per-cpu space used counters into the global atomic value. + * This is called when the per-cpu counter aggregation will first pass the soft + * limit threshold so we can switch to atomic counter aggregation for accurate + * detection of hard limit traversal. + */ +static void +xlog_cil_insert_pcp_aggregate( + struct xfs_cil *cil, + struct xfs_cil_ctx *ctx) +{ + struct xlog_cil_pcp *cilpcp; + int cpu; + int count = 0; + + /* Trigger atomic updates then aggregate only for the first caller */ + if (!test_and_clear_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags)) + return; + + for_each_online_cpu(cpu) { + int old, prev; + + cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); + do { + old = cilpcp->space_used; + prev = cmpxchg(&cilpcp->space_used, old, 0); + } while (old != prev); + count += old; + } + atomic_add(count, &ctx->space_used); +} + static void xlog_cil_ctx_switch( struct xfs_cil *cil, struct xfs_cil_ctx *ctx) { + xlog_cil_set_iclog_hdr_count(cil); + set_bit(XLOG_CIL_EMPTY, &cil->xc_flags); + set_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags); ctx->sequence = ++cil->xc_current_sequence; ctx->cil = cil; cil->xc_ctx = ctx; @@ -123,6 +207,7 @@ xlog_cil_init_post_recovery( { log->l_cilp->xc_ctx->ticket = xlog_cil_ticket_alloc(log); log->l_cilp->xc_ctx->sequence = 1; + xlog_cil_set_iclog_hdr_count(log->l_cilp); } static inline int @@ -254,6 +339,7 @@ xlog_cil_alloc_shadow_bufs( memset(lv, 0, xlog_cil_iovec_space(niovecs)); + INIT_LIST_HEAD(&lv->lv_list); lv->lv_item = lip; lv->lv_size = buf_size; if (ordered) @@ -269,7 +355,6 @@ xlog_cil_alloc_shadow_bufs( else lv->lv_buf_len = 0; lv->lv_bytes = 0; - lv->lv_next = NULL; } /* Ensure the lv is set up according to ->iop_size */ @@ -396,7 +481,6 @@ xlog_cil_insert_format_items( if (lip->li_lv && shadow->lv_size <= lip->li_lv->lv_size) { /* same or smaller, optimise common overwrite case */ lv = lip->li_lv; - lv->lv_next = NULL; if (ordered) goto insert; @@ -434,6 +518,23 @@ insert: } /* + * The use of lockless waitqueue_active() requires that the caller has + * serialised itself against the wakeup call in xlog_cil_push_work(). That + * can be done by either holding the push lock or the context lock. + */ +static inline bool +xlog_cil_over_hard_limit( + struct xlog *log, + int32_t space_used) +{ + if (waitqueue_active(&log->l_cilp->xc_push_wait)) + return true; + if (space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) + return true; + return false; +} + +/* * Insert the log items into the CIL and calculate the difference in space * consumed by the item. Add the space to the checkpoint ticket and calculate * if the change requires additional log metadata. If it does, take that space @@ -450,8 +551,10 @@ xlog_cil_insert_items( struct xfs_cil_ctx *ctx = cil->xc_ctx; struct xfs_log_item *lip; int len = 0; - int iclog_space; int iovhdr_res = 0, split_res = 0, ctx_res = 0; + int space_used; + int order; + struct xlog_cil_pcp *cilpcp; ASSERT(tp); @@ -461,93 +564,135 @@ xlog_cil_insert_items( */ xlog_cil_insert_format_items(log, tp, &len); - spin_lock(&cil->xc_cil_lock); + /* + * Subtract the space released by intent cancelation from the space we + * consumed so that we remove it from the CIL space and add it back to + * the current transaction reservation context. + */ + len -= released_space; - /* attach the transaction to the CIL if it has any busy extents */ - if (!list_empty(&tp->t_busy)) - list_splice_init(&tp->t_busy, &ctx->busy_extents); + /* + * Grab the per-cpu pointer for the CIL before we start any accounting. + * That ensures that we are running with pre-emption disabled and so we + * can't be scheduled away between split sample/update operations that + * are done without outside locking to serialise them. + */ + cilpcp = get_cpu_ptr(cil->xc_pcp); /* - * Now transfer enough transaction reservation to the context ticket - * for the checkpoint. The context ticket is special - the unit - * reservation has to grow as well as the current reservation as we - * steal from tickets so we can correctly determine the space used - * during the transaction commit. + * We need to take the CIL checkpoint unit reservation on the first + * commit into the CIL. Test the XLOG_CIL_EMPTY bit first so we don't + * unnecessarily do an atomic op in the fast path here. We can clear the + * XLOG_CIL_EMPTY bit as we are under the xc_ctx_lock here and that + * needs to be held exclusively to reset the XLOG_CIL_EMPTY bit. */ - if (ctx->ticket->t_curr_res == 0) { + if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags) && + test_and_clear_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) ctx_res = ctx->ticket->t_unit_res; - ctx->ticket->t_curr_res = ctx_res; - tp->t_ticket->t_curr_res -= ctx_res; - } - /* do we need space for more log record headers? */ - iclog_space = log->l_iclog_size - log->l_iclog_hsize; - if (len > 0 && (ctx->space_used / iclog_space != - (ctx->space_used + len) / iclog_space)) { - split_res = (len + iclog_space - 1) / iclog_space; - /* need to take into account split region headers, too */ - split_res *= log->l_iclog_hsize + sizeof(struct xlog_op_header); - ctx->ticket->t_unit_res += split_res; - ctx->ticket->t_curr_res += split_res; - tp->t_ticket->t_curr_res -= split_res; - ASSERT(tp->t_ticket->t_curr_res >= len); + /* + * Check if we need to steal iclog headers. atomic_read() is not a + * locked atomic operation, so we can check the value before we do any + * real atomic ops in the fast path. If we've already taken the CIL unit + * reservation from this commit, we've already got one iclog header + * space reserved so we have to account for that otherwise we risk + * overrunning the reservation on this ticket. + * + * If the CIL is already at the hard limit, we might need more header + * space that originally reserved. So steal more header space from every + * commit that occurs once we are over the hard limit to ensure the CIL + * push won't run out of reservation space. + * + * This can steal more than we need, but that's OK. + * + * The cil->xc_ctx_lock provides the serialisation necessary for safely + * calling xlog_cil_over_hard_limit() in this context. + */ + space_used = atomic_read(&ctx->space_used) + cilpcp->space_used + len; + if (atomic_read(&cil->xc_iclog_hdrs) > 0 || + xlog_cil_over_hard_limit(log, space_used)) { + split_res = log->l_iclog_hsize + + sizeof(struct xlog_op_header); + if (ctx_res) + ctx_res += split_res * (tp->t_ticket->t_iclog_hdrs - 1); + else + ctx_res = split_res * tp->t_ticket->t_iclog_hdrs; + atomic_sub(tp->t_ticket->t_iclog_hdrs, &cil->xc_iclog_hdrs); } - tp->t_ticket->t_curr_res -= len; - tp->t_ticket->t_curr_res += released_space; - ctx->space_used += len; - ctx->space_used -= released_space; + cilpcp->space_reserved += ctx_res; /* - * If we've overrun the reservation, dump the tx details before we move - * the log items. Shutdown is imminent... + * Accurately account when over the soft limit, otherwise fold the + * percpu count into the global count if over the per-cpu threshold. */ - if (WARN_ON(tp->t_ticket->t_curr_res < 0)) { - xfs_warn(log->l_mp, "Transaction log reservation overrun:"); - xfs_warn(log->l_mp, - " log items: %d bytes (iov hdrs: %d bytes)", - len, iovhdr_res); - xfs_warn(log->l_mp, " split region headers: %d bytes", - split_res); - xfs_warn(log->l_mp, " ctx ticket: %d bytes", ctx_res); - xlog_print_trans(tp); + if (!test_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags)) { + atomic_add(len, &ctx->space_used); + } else if (cilpcp->space_used + len > + (XLOG_CIL_SPACE_LIMIT(log) / num_online_cpus())) { + space_used = atomic_add_return(cilpcp->space_used + len, + &ctx->space_used); + cilpcp->space_used = 0; + + /* + * If we just transitioned over the soft limit, we need to + * transition to the global atomic counter. + */ + if (space_used >= XLOG_CIL_SPACE_LIMIT(log)) + xlog_cil_insert_pcp_aggregate(cil, ctx); + } else { + cilpcp->space_used += len; } + /* attach the transaction to the CIL if it has any busy extents */ + if (!list_empty(&tp->t_busy)) + list_splice_init(&tp->t_busy, &cilpcp->busy_extents); /* - * Now (re-)position everything modified at the tail of the CIL. + * Now update the order of everything modified in the transaction + * and insert items into the CIL if they aren't already there. * We do this here so we only need to take the CIL lock once during * the transaction commit. */ + order = atomic_inc_return(&ctx->order_id); list_for_each_entry(lip, &tp->t_items, li_trans) { - /* Skip items which aren't dirty in this transaction. */ if (!test_bit(XFS_LI_DIRTY, &lip->li_flags)) continue; - /* - * Only move the item if it isn't already at the tail. This is - * to prevent a transient list_empty() state when reinserting - * an item that is already the only item in the CIL. - */ - if (!list_is_last(&lip->li_cil, &cil->xc_cil)) - list_move_tail(&lip->li_cil, &cil->xc_cil); + lip->li_order_id = order; + if (!list_empty(&lip->li_cil)) + continue; + list_add_tail(&lip->li_cil, &cilpcp->log_items); } + put_cpu_ptr(cilpcp); - spin_unlock(&cil->xc_cil_lock); - - if (tp->t_ticket->t_curr_res < 0) + /* + * If we've overrun the reservation, dump the tx details before we move + * the log items. Shutdown is imminent... + */ + tp->t_ticket->t_curr_res -= ctx_res + len; + if (WARN_ON(tp->t_ticket->t_curr_res < 0)) { + xfs_warn(log->l_mp, "Transaction log reservation overrun:"); + xfs_warn(log->l_mp, + " log items: %d bytes (iov hdrs: %d bytes)", + len, iovhdr_res); + xfs_warn(log->l_mp, " split region headers: %d bytes", + split_res); + xfs_warn(log->l_mp, " ctx ticket: %d bytes", ctx_res); + xlog_print_trans(tp); xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); + } } static void xlog_cil_free_logvec( - struct xfs_log_vec *log_vector) + struct list_head *lv_chain) { struct xfs_log_vec *lv; - for (lv = log_vector; lv; ) { - struct xfs_log_vec *next = lv->lv_next; + while (!list_empty(lv_chain)) { + lv = list_first_entry(lv_chain, struct xfs_log_vec, lv_list); + list_del_init(&lv->lv_list); kmem_free(lv); - lv = next; } } @@ -647,7 +792,7 @@ xlog_cil_committed( spin_unlock(&ctx->cil->xc_push_lock); } - xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, ctx->lv_chain, + xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, &ctx->lv_chain, ctx->start_lsn, abort); xfs_extent_busy_sort(&ctx->busy_extents); @@ -658,7 +803,7 @@ xlog_cil_committed( list_del(&ctx->committing); spin_unlock(&ctx->cil->xc_push_lock); - xlog_cil_free_logvec(ctx->lv_chain); + xlog_cil_free_logvec(&ctx->lv_chain); if (!list_empty(&ctx->busy_extents)) xlog_discard_busy_extents(mp, ctx); @@ -817,7 +962,6 @@ restart: static int xlog_cil_write_chain( struct xfs_cil_ctx *ctx, - struct xfs_log_vec *chain, uint32_t chain_len) { struct xlog *log = ctx->cil->xc_log; @@ -826,7 +970,7 @@ xlog_cil_write_chain( error = xlog_cil_order_write(ctx->cil, ctx->sequence, _START_RECORD); if (error) return error; - return xlog_write(log, ctx, chain, ctx->ticket, chain_len); + return xlog_write(log, ctx, &ctx->lv_chain, ctx->ticket, chain_len); } /* @@ -855,6 +999,8 @@ xlog_cil_write_commit_record( .lv_iovecp = ®, }; int error; + LIST_HEAD(lv_chain); + list_add(&vec.lv_list, &lv_chain); if (xlog_is_shutdown(log)) return -EIO; @@ -865,7 +1011,7 @@ xlog_cil_write_commit_record( /* account for space used by record data */ ctx->ticket->t_curr_res -= reg.i_len; - error = xlog_write(log, ctx, &vec, ctx->ticket, reg.i_len); + error = xlog_write(log, ctx, &lv_chain, ctx->ticket, reg.i_len); if (error) xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); return error; @@ -931,12 +1077,31 @@ xlog_cil_build_trans_hdr( lvhdr->lv_niovecs = 2; lvhdr->lv_iovecp = &hdr->lhdr[0]; lvhdr->lv_bytes = hdr->lhdr[0].i_len + hdr->lhdr[1].i_len; - lvhdr->lv_next = ctx->lv_chain; tic->t_curr_res -= lvhdr->lv_bytes; } /* + * CIL item reordering compare function. We want to order in ascending ID order, + * but we want to leave items with the same ID in the order they were added to + * the list. This is important for operations like reflink where we log 4 order + * dependent intents in a single transaction when we overwrite an existing + * shared extent with a new shared extent. i.e. BUI(unmap), CUI(drop), + * CUI (inc), BUI(remap)... + */ +static int +xlog_cil_order_cmp( + void *priv, + const struct list_head *a, + const struct list_head *b) +{ + struct xfs_log_vec *l1 = container_of(a, struct xfs_log_vec, lv_list); + struct xfs_log_vec *l2 = container_of(b, struct xfs_log_vec, lv_list); + + return l1->lv_order_id > l2->lv_order_id; +} + +/* * Pull all the log vectors off the items in the CIL, and remove the items from * the CIL. We don't need the CIL lock here because it's only needed on the * transaction commit side which is currently locked out by the flush lock. @@ -947,18 +1112,16 @@ xlog_cil_build_trans_hdr( */ static void xlog_cil_build_lv_chain( - struct xfs_cil *cil, struct xfs_cil_ctx *ctx, struct list_head *whiteouts, uint32_t *num_iovecs, uint32_t *num_bytes) { - struct xfs_log_vec *lv = NULL; - - while (!list_empty(&cil->xc_cil)) { + while (!list_empty(&ctx->log_items)) { struct xfs_log_item *item; + struct xfs_log_vec *lv; - item = list_first_entry(&cil->xc_cil, + item = list_first_entry(&ctx->log_items, struct xfs_log_item, li_cil); if (test_bit(XFS_LI_WHITEOUT, &item->li_flags)) { @@ -967,18 +1130,18 @@ xlog_cil_build_lv_chain( continue; } - list_del_init(&item->li_cil); - if (!ctx->lv_chain) - ctx->lv_chain = item->li_lv; - else - lv->lv_next = item->li_lv; lv = item->li_lv; - item->li_lv = NULL; - *num_iovecs += lv->lv_niovecs; + lv->lv_order_id = item->li_order_id; /* we don't write ordered log vectors */ if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) *num_bytes += lv->lv_bytes; + *num_iovecs += lv->lv_niovecs; + list_add_tail(&lv->lv_list, &ctx->lv_chain); + + list_del_init(&item->li_cil); + item->li_order_id = 0; + item->li_lv = NULL; } } @@ -1022,10 +1185,11 @@ xlog_cil_push_work( int num_bytes = 0; int error = 0; struct xlog_cil_trans_hdr thdr; - struct xfs_log_vec lvhdr = { NULL }; + struct xfs_log_vec lvhdr = {}; xfs_csn_t push_seq; bool push_commit_stable; LIST_HEAD (whiteouts); + struct xlog_ticket *ticket; new_ctx = xlog_cil_ctx_alloc(); new_ctx->ticket = xlog_cil_ticket_alloc(log); @@ -1049,12 +1213,14 @@ xlog_cil_push_work( if (waitqueue_active(&cil->xc_push_wait)) wake_up_all(&cil->xc_push_wait); + xlog_cil_push_pcp_aggregate(cil, ctx); + /* * Check if we've anything to push. If there is nothing, then we don't * move on to a new sequence number and so we have to be able to push * this sequence again later. */ - if (list_empty(&cil->xc_cil)) { + if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) { cil->xc_push_seq = 0; spin_unlock(&cil->xc_push_lock); goto out_skip; @@ -1094,7 +1260,7 @@ xlog_cil_push_work( list_add(&ctx->committing, &cil->xc_committing); spin_unlock(&cil->xc_push_lock); - xlog_cil_build_lv_chain(cil, ctx, &whiteouts, &num_iovecs, &num_bytes); + xlog_cil_build_lv_chain(ctx, &whiteouts, &num_iovecs, &num_bytes); /* * Switch the contexts so we can drop the context lock and move out @@ -1127,14 +1293,30 @@ xlog_cil_push_work( up_write(&cil->xc_ctx_lock); /* + * Sort the log vector chain before we add the transaction headers. + * This ensures we always have the transaction headers at the start + * of the chain. + */ + list_sort(NULL, &ctx->lv_chain, xlog_cil_order_cmp); + + /* * Build a checkpoint transaction header and write it to the log to * begin the transaction. We need to account for the space used by the * transaction header here as it is not accounted for in xlog_write(). + * Add the lvhdr to the head of the lv chain we pass to xlog_write() so + * it gets written into the iclog first. */ xlog_cil_build_trans_hdr(ctx, &thdr, &lvhdr, num_iovecs); num_bytes += lvhdr.lv_bytes; + list_add(&lvhdr.lv_list, &ctx->lv_chain); - error = xlog_cil_write_chain(ctx, &lvhdr, num_bytes); + /* + * Take the lvhdr back off the lv_chain immediately after calling + * xlog_cil_write_chain() as it should not be passed to log IO + * completion. + */ + error = xlog_cil_write_chain(ctx, num_bytes); + list_del(&lvhdr.lv_list); if (error) goto out_abort_free_ticket; @@ -1142,7 +1324,14 @@ xlog_cil_push_work( if (error) goto out_abort_free_ticket; - xfs_log_ticket_ungrant(log, ctx->ticket); + /* + * Grab the ticket from the ctx so we can ungrant it after releasing the + * commit_iclog. The ctx may be freed by the time we return from + * releasing the commit_iclog (i.e. checkpoint has been completed and + * callback run) so we can't reference the ctx after the call to + * xlog_state_release_iclog(). + */ + ticket = ctx->ticket; /* * If the checkpoint spans multiple iclogs, wait for all previous iclogs @@ -1192,12 +1381,14 @@ xlog_cil_push_work( if (push_commit_stable && ctx->commit_iclog->ic_state == XLOG_STATE_ACTIVE) xlog_state_switch_iclogs(log, ctx->commit_iclog, 0); - xlog_state_release_iclog(log, ctx->commit_iclog); + ticket = ctx->ticket; + xlog_state_release_iclog(log, ctx->commit_iclog, ticket); /* Not safe to reference ctx now! */ spin_unlock(&log->l_icloglock); xlog_cil_cleanup_whiteouts(&whiteouts); + xfs_log_ticket_ungrant(log, ticket); return; out_skip: @@ -1207,17 +1398,19 @@ out_skip: return; out_abort_free_ticket: - xfs_log_ticket_ungrant(log, ctx->ticket); ASSERT(xlog_is_shutdown(log)); xlog_cil_cleanup_whiteouts(&whiteouts); if (!ctx->commit_iclog) { + xfs_log_ticket_ungrant(log, ctx->ticket); xlog_cil_committed(ctx); return; } spin_lock(&log->l_icloglock); - xlog_state_release_iclog(log, ctx->commit_iclog); + ticket = ctx->ticket; + xlog_state_release_iclog(log, ctx->commit_iclog, ticket); /* Not safe to reference ctx now! */ spin_unlock(&log->l_icloglock); + xfs_log_ticket_ungrant(log, ticket); } /* @@ -1232,18 +1425,27 @@ xlog_cil_push_background( struct xlog *log) __releases(cil->xc_ctx_lock) { struct xfs_cil *cil = log->l_cilp; + int space_used = atomic_read(&cil->xc_ctx->space_used); /* * The cil won't be empty because we are called while holding the - * context lock so whatever we added to the CIL will still be there + * context lock so whatever we added to the CIL will still be there. */ - ASSERT(!list_empty(&cil->xc_cil)); + ASSERT(!test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)); /* - * Don't do a background push if we haven't used up all the - * space available yet. + * We are done if: + * - we haven't used up all the space available yet; or + * - we've already queued up a push; and + * - we're not over the hard limit; and + * - nothing has been over the hard limit. + * + * If so, we don't need to take the push lock as there's nothing to do. */ - if (cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log)) { + if (space_used < XLOG_CIL_SPACE_LIMIT(log) || + (cil->xc_push_seq == cil->xc_current_sequence && + space_used < XLOG_CIL_BLOCKING_SPACE_LIMIT(log) && + !waitqueue_active(&cil->xc_push_wait))) { up_read(&cil->xc_ctx_lock); return; } @@ -1270,12 +1472,11 @@ xlog_cil_push_background( * dipping back down under the hard limit. * * The ctx->xc_push_lock provides the serialisation necessary for safely - * using the lockless waitqueue_active() check in this context. + * calling xlog_cil_over_hard_limit() in this context. */ - if (cil->xc_ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log) || - waitqueue_active(&cil->xc_push_wait)) { + if (xlog_cil_over_hard_limit(log, space_used)) { trace_xfs_log_cil_wait(log, cil->xc_ctx->ticket); - ASSERT(cil->xc_ctx->space_used < log->l_logsize); + ASSERT(space_used < log->l_logsize); xlog_wait(&cil->xc_push_wait, &cil->xc_push_lock); return; } @@ -1334,7 +1535,8 @@ xlog_cil_push_now( * If the CIL is empty or we've already pushed the sequence then * there's no more work that we need to do. */ - if (list_empty(&cil->xc_cil) || push_seq <= cil->xc_push_seq) { + if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags) || + push_seq <= cil->xc_push_seq) { spin_unlock(&cil->xc_push_lock); return; } @@ -1352,7 +1554,7 @@ xlog_cil_empty( bool empty = false; spin_lock(&cil->xc_push_lock); - if (list_empty(&cil->xc_cil)) + if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) empty = true; spin_unlock(&cil->xc_push_lock); return empty; @@ -1483,7 +1685,7 @@ xlog_cil_flush( * If the CIL is empty, make sure that any previous checkpoint that may * still be in an active iclog is pushed to stable storage. */ - if (list_empty(&log->l_cilp->xc_cil)) + if (test_bit(XLOG_CIL_EMPTY, &log->l_cilp->xc_flags)) xfs_log_force(log->l_mp, 0); } @@ -1568,7 +1770,7 @@ restart: * we would have found the context on the committing list. */ if (sequence == cil->xc_current_sequence && - !list_empty(&cil->xc_cil)) { + !test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) { spin_unlock(&cil->xc_push_lock); goto restart; } @@ -1589,14 +1791,48 @@ out_shutdown: } /* + * Move dead percpu state to the relevant CIL context structures. + * + * We have to lock the CIL context here to ensure that nothing is modifying + * the percpu state, either addition or removal. Both of these are done under + * the CIL context lock, so grabbing that exclusively here will ensure we can + * safely drain the cilpcp for the CPU that is dying. + */ +void +xlog_cil_pcp_dead( + struct xlog *log, + unsigned int cpu) +{ + struct xfs_cil *cil = log->l_cilp; + struct xlog_cil_pcp *cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); + struct xfs_cil_ctx *ctx; + + down_write(&cil->xc_ctx_lock); + ctx = cil->xc_ctx; + if (ctx->ticket) + ctx->ticket->t_curr_res += cilpcp->space_reserved; + cilpcp->space_reserved = 0; + + if (!list_empty(&cilpcp->log_items)) + list_splice_init(&cilpcp->log_items, &ctx->log_items); + if (!list_empty(&cilpcp->busy_extents)) + list_splice_init(&cilpcp->busy_extents, &ctx->busy_extents); + atomic_add(cilpcp->space_used, &ctx->space_used); + cilpcp->space_used = 0; + up_write(&cil->xc_ctx_lock); +} + +/* * Perform initial CIL structure initialisation. */ int xlog_cil_init( - struct xlog *log) + struct xlog *log) { - struct xfs_cil *cil; - struct xfs_cil_ctx *ctx; + struct xfs_cil *cil; + struct xfs_cil_ctx *ctx; + struct xlog_cil_pcp *cilpcp; + int cpu; cil = kmem_zalloc(sizeof(*cil), KM_MAYFAIL); if (!cil) @@ -1611,22 +1847,31 @@ xlog_cil_init( if (!cil->xc_push_wq) goto out_destroy_cil; - INIT_LIST_HEAD(&cil->xc_cil); + cil->xc_log = log; + cil->xc_pcp = alloc_percpu(struct xlog_cil_pcp); + if (!cil->xc_pcp) + goto out_destroy_wq; + + for_each_possible_cpu(cpu) { + cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); + INIT_LIST_HEAD(&cilpcp->busy_extents); + INIT_LIST_HEAD(&cilpcp->log_items); + } + INIT_LIST_HEAD(&cil->xc_committing); - spin_lock_init(&cil->xc_cil_lock); spin_lock_init(&cil->xc_push_lock); init_waitqueue_head(&cil->xc_push_wait); init_rwsem(&cil->xc_ctx_lock); init_waitqueue_head(&cil->xc_start_wait); init_waitqueue_head(&cil->xc_commit_wait); - cil->xc_log = log; log->l_cilp = cil; ctx = xlog_cil_ctx_alloc(); xlog_cil_ctx_switch(cil, ctx); - return 0; +out_destroy_wq: + destroy_workqueue(cil->xc_push_wq); out_destroy_cil: kmem_free(cil); return -ENOMEM; @@ -1636,14 +1881,17 @@ void xlog_cil_destroy( struct xlog *log) { - if (log->l_cilp->xc_ctx) { - if (log->l_cilp->xc_ctx->ticket) - xfs_log_ticket_put(log->l_cilp->xc_ctx->ticket); - kmem_free(log->l_cilp->xc_ctx); + struct xfs_cil *cil = log->l_cilp; + + if (cil->xc_ctx) { + if (cil->xc_ctx->ticket) + xfs_log_ticket_put(cil->xc_ctx->ticket); + kmem_free(cil->xc_ctx); } - ASSERT(list_empty(&log->l_cilp->xc_cil)); - destroy_workqueue(log->l_cilp->xc_push_wq); - kmem_free(log->l_cilp); + ASSERT(test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)); + free_percpu(cil->xc_pcp); + destroy_workqueue(cil->xc_push_wq); + kmem_free(cil); } diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 686c01eb3661..1bd2963e8fbd 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -143,15 +143,16 @@ enum xlog_iclog_state { #define XLOG_COVER_OPS 5 typedef struct xlog_ticket { - struct list_head t_queue; /* reserve/write queue */ - struct task_struct *t_task; /* task that owns this ticket */ - xlog_tid_t t_tid; /* transaction identifier : 4 */ - atomic_t t_ref; /* ticket reference count : 4 */ - int t_curr_res; /* current reservation in bytes : 4 */ - int t_unit_res; /* unit reservation in bytes : 4 */ - char t_ocnt; /* original count : 1 */ - char t_cnt; /* current count : 1 */ - uint8_t t_flags; /* properties of reservation : 1 */ + struct list_head t_queue; /* reserve/write queue */ + struct task_struct *t_task; /* task that owns this ticket */ + xlog_tid_t t_tid; /* transaction identifier */ + atomic_t t_ref; /* ticket reference count */ + int t_curr_res; /* current reservation */ + int t_unit_res; /* unit reservation */ + char t_ocnt; /* original unit count */ + char t_cnt; /* current unit count */ + uint8_t t_flags; /* properties of reservation */ + int t_iclog_hdrs; /* iclog hdrs in t_curr_res */ } xlog_ticket_t; /* @@ -221,13 +222,25 @@ struct xfs_cil_ctx { xfs_lsn_t commit_lsn; /* chkpt commit record lsn */ struct xlog_in_core *commit_iclog; struct xlog_ticket *ticket; /* chkpt ticket */ - int space_used; /* aggregate size of regions */ + atomic_t space_used; /* aggregate size of regions */ struct list_head busy_extents; /* busy extents in chkpt */ - struct xfs_log_vec *lv_chain; /* logvecs being pushed */ + struct list_head log_items; /* log items in chkpt */ + struct list_head lv_chain; /* logvecs being pushed */ struct list_head iclog_entry; struct list_head committing; /* ctx committing list */ struct work_struct discard_endio_work; struct work_struct push_work; + atomic_t order_id; +}; + +/* + * Per-cpu CIL tracking items + */ +struct xlog_cil_pcp { + int32_t space_used; + uint32_t space_reserved; + struct list_head busy_extents; + struct list_head log_items; }; /* @@ -248,8 +261,8 @@ struct xfs_cil_ctx { */ struct xfs_cil { struct xlog *xc_log; - struct list_head xc_cil; - spinlock_t xc_cil_lock; + unsigned long xc_flags; + atomic_t xc_iclog_hdrs; struct workqueue_struct *xc_push_wq; struct rw_semaphore xc_ctx_lock ____cacheline_aligned_in_smp; @@ -263,8 +276,17 @@ struct xfs_cil { wait_queue_head_t xc_start_wait; xfs_csn_t xc_current_sequence; wait_queue_head_t xc_push_wait; /* background push throttle */ + + void __percpu *xc_pcp; /* percpu CIL structures */ +#ifdef CONFIG_HOTPLUG_CPU + struct list_head xc_pcp_list; +#endif } ____cacheline_aligned_in_smp; +/* xc_flags bit values */ +#define XLOG_CIL_EMPTY 1 +#define XLOG_CIL_PCP_SPACE 2 + /* * The amount of log space we allow the CIL to aggregate is difficult to size. * Whatever we choose, we have to make sure we can get a reservation for the @@ -486,14 +508,15 @@ struct xlog_ticket *xlog_ticket_alloc(struct xlog *log, int unit_bytes, void xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket); void xlog_print_trans(struct xfs_trans *); int xlog_write(struct xlog *log, struct xfs_cil_ctx *ctx, - struct xfs_log_vec *log_vector, struct xlog_ticket *tic, + struct list_head *lv_chain, struct xlog_ticket *tic, uint32_t len); void xfs_log_ticket_ungrant(struct xlog *log, struct xlog_ticket *ticket); void xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket); void xlog_state_switch_iclogs(struct xlog *log, struct xlog_in_core *iclog, int eventual_size); -int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog); +int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog, + struct xlog_ticket *ticket); /* * When we crack an atomic LSN, we sample it first so that the value will not @@ -682,4 +705,9 @@ xlog_kvmalloc( return p; } +/* + * CIL CPU dead notifier + */ +void xlog_cil_pcp_dead(struct xlog *log, unsigned int cpu); + #endif /* __XFS_LOG_PRIV_H__ */ diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 940c8107cbd4..17e923b9c5fa 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2629,21 +2629,21 @@ xlog_recover_cancel_intents( */ STATIC void xlog_recover_clear_agi_bucket( - xfs_mount_t *mp, - xfs_agnumber_t agno, - int bucket) + struct xfs_perag *pag, + int bucket) { - xfs_trans_t *tp; - xfs_agi_t *agi; - struct xfs_buf *agibp; - int offset; - int error; + struct xfs_mount *mp = pag->pag_mount; + struct xfs_trans *tp; + struct xfs_agi *agi; + struct xfs_buf *agibp; + int offset; + int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_clearagi, 0, 0, 0, &tp); if (error) goto out_error; - error = xfs_read_agi(mp, tp, agno, &agibp); + error = xfs_read_agi(pag, tp, &agibp); if (error) goto out_abort; @@ -2662,60 +2662,62 @@ xlog_recover_clear_agi_bucket( out_abort: xfs_trans_cancel(tp); out_error: - xfs_warn(mp, "%s: failed to clear agi %d. Continuing.", __func__, agno); + xfs_warn(mp, "%s: failed to clear agi %d. Continuing.", __func__, + pag->pag_agno); return; } -STATIC xfs_agino_t -xlog_recover_process_one_iunlink( - struct xfs_mount *mp, - xfs_agnumber_t agno, - xfs_agino_t agino, - int bucket) +static int +xlog_recover_iunlink_bucket( + struct xfs_perag *pag, + struct xfs_agi *agi, + int bucket) { - struct xfs_buf *ibp; - struct xfs_dinode *dip; - struct xfs_inode *ip; - xfs_ino_t ino; - int error; - - ino = XFS_AGINO_TO_INO(mp, agno, agino); - error = xfs_iget(mp, NULL, ino, 0, 0, &ip); - if (error) - goto fail; + struct xfs_mount *mp = pag->pag_mount; + struct xfs_inode *prev_ip = NULL; + struct xfs_inode *ip; + xfs_agino_t prev_agino, agino; + int error = 0; - /* - * Get the on disk inode to find the next inode in the bucket. - */ - error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &ibp); - if (error) - goto fail_iput; - dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset); + agino = be32_to_cpu(agi->agi_unlinked[bucket]); + while (agino != NULLAGINO) { + error = xfs_iget(mp, NULL, + XFS_AGINO_TO_INO(mp, pag->pag_agno, agino), + 0, 0, &ip); + if (error) + break; - xfs_iflags_clear(ip, XFS_IRECOVERY); - ASSERT(VFS_I(ip)->i_nlink == 0); - ASSERT(VFS_I(ip)->i_mode != 0); + ASSERT(VFS_I(ip)->i_nlink == 0); + ASSERT(VFS_I(ip)->i_mode != 0); + xfs_iflags_clear(ip, XFS_IRECOVERY); + agino = ip->i_next_unlinked; - /* setup for the next pass */ - agino = be32_to_cpu(dip->di_next_unlinked); - xfs_buf_relse(ibp); + if (prev_ip) { + ip->i_prev_unlinked = prev_agino; + xfs_irele(prev_ip); - xfs_irele(ip); - return agino; + /* + * Ensure the inode is removed from the unlinked list + * before we continue so that it won't race with + * building the in-memory list here. This could be + * serialised with the agibp lock, but that just + * serialises via lockstepping and it's much simpler + * just to flush the inodegc queue and wait for it to + * complete. + */ + xfs_inodegc_flush(mp); + } - fail_iput: - xfs_irele(ip); - fail: - /* - * We can't read in the inode this bucket points to, or this inode - * is messed up. Just ditch this bucket of inodes. We will lose - * some inodes and space, but at least we won't hang. - * - * Call xlog_recover_clear_agi_bucket() to perform a transaction to - * clear the inode pointer in the bucket. - */ - xlog_recover_clear_agi_bucket(mp, agno, bucket); - return NULLAGINO; + prev_agino = agino; + prev_ip = ip; + } + + if (prev_ip) { + ip->i_prev_unlinked = prev_agino; + xfs_irele(prev_ip); + } + xfs_inodegc_flush(mp); + return error; } /* @@ -2741,59 +2743,70 @@ xlog_recover_process_one_iunlink( * scheduled on this CPU to ensure other scheduled work can run without undue * latency. */ -STATIC void -xlog_recover_process_iunlinks( - struct xlog *log) +static void +xlog_recover_iunlink_ag( + struct xfs_perag *pag) { - struct xfs_mount *mp = log->l_mp; - struct xfs_perag *pag; - xfs_agnumber_t agno; struct xfs_agi *agi; struct xfs_buf *agibp; - xfs_agino_t agino; int bucket; int error; - for_each_perag(mp, agno, pag) { - error = xfs_read_agi(mp, NULL, pag->pag_agno, &agibp); + error = xfs_read_agi(pag, NULL, &agibp); + if (error) { + /* + * AGI is b0rked. Don't process it. + * + * We should probably mark the filesystem as corrupt after we've + * recovered all the ag's we can.... + */ + return; + } + + /* + * Unlock the buffer so that it can be acquired in the normal course of + * the transaction to truncate and free each inode. Because we are not + * racing with anyone else here for the AGI buffer, we don't even need + * to hold it locked to read the initial unlinked bucket entries out of + * the buffer. We keep buffer reference though, so that it stays pinned + * in memory while we need the buffer. + */ + agi = agibp->b_addr; + xfs_buf_unlock(agibp); + + for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++) { + error = xlog_recover_iunlink_bucket(pag, agi, bucket); if (error) { /* - * AGI is b0rked. Don't process it. - * - * We should probably mark the filesystem as corrupt - * after we've recovered all the ag's we can.... + * Bucket is unrecoverable, so only a repair scan can + * free the remaining unlinked inodes. Just empty the + * bucket and remaining inodes on it unreferenced and + * unfreeable. */ - continue; + xfs_inodegc_flush(pag->pag_mount); + xlog_recover_clear_agi_bucket(pag, bucket); } - /* - * Unlock the buffer so that it can be acquired in the normal - * course of the transaction to truncate and free each inode. - * Because we are not racing with anyone else here for the AGI - * buffer, we don't even need to hold it locked to read the - * initial unlinked bucket entries out of the buffer. We keep - * buffer reference though, so that it stays pinned in memory - * while we need the buffer. - */ - agi = agibp->b_addr; - xfs_buf_unlock(agibp); - - for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++) { - agino = be32_to_cpu(agi->agi_unlinked[bucket]); - while (agino != NULLAGINO) { - agino = xlog_recover_process_one_iunlink(mp, - pag->pag_agno, agino, bucket); - cond_resched(); - } - } - xfs_buf_rele(agibp); } + xfs_buf_rele(agibp); +} + +static void +xlog_recover_process_iunlinks( + struct xlog *log) +{ + struct xfs_perag *pag; + xfs_agnumber_t agno; + + for_each_perag(log->l_mp, agno, pag) + xlog_recover_iunlink_ag(pag); + /* * Flush the pending unlinked inodes to ensure that the inactivations * are fully completed on disk and the incore inodes can be reclaimed * before we signal that recovery is complete. */ - xfs_inodegc_flush(mp); + xfs_inodegc_flush(log->l_mp); } STATIC void @@ -3313,7 +3326,8 @@ xlog_do_recover( /* re-initialise in-core superblock and geometry structures */ mp->m_features |= xfs_sb_version_to_features(sbp); xfs_reinit_percpu_counters(mp); - error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi); + error = xfs_initialize_perag(mp, sbp->sb_agcount, sbp->sb_dblocks, + &mp->m_maxagi); if (error) { xfs_warn(mp, "Failed post-recovery per-ag init: %d", error); return error; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index daa8d29c46b4..f10c88cee116 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -778,7 +778,8 @@ xfs_mountfs( /* * Allocate and initialize the per-ag data. */ - error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi); + error = xfs_initialize_perag(mp, sbp->sb_agcount, mp->m_sb.sb_dblocks, + &mp->m_maxagi); if (error) { xfs_warn(mp, "Failed per-ag init: %d", error); goto out_free_dir; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index d2eaebd85abf..8aca2cc173ac 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -454,6 +454,7 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, uint32_t flags, char *fname, #define SHUTDOWN_LOG_IO_ERROR (1u << 1) /* write attempt to the log failed */ #define SHUTDOWN_FORCE_UMOUNT (1u << 2) /* shutdown from a forced unmount */ #define SHUTDOWN_CORRUPT_INCORE (1u << 3) /* corrupt in-memory structures */ +#define SHUTDOWN_CORRUPT_ONDISK (1u << 4) /* corrupt metadata on device */ #define XFS_SHUTDOWN_STRINGS \ { SHUTDOWN_META_IO_ERROR, "metadata_io" }, \ diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c new file mode 100644 index 000000000000..69d9c83ea4b2 --- /dev/null +++ b/fs/xfs/xfs_notify_failure.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Fujitsu. All Rights Reserved. + */ + +#include "xfs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_alloc.h" +#include "xfs_bit.h" +#include "xfs_btree.h" +#include "xfs_inode.h" +#include "xfs_icache.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtalloc.h" +#include "xfs_trans.h" +#include "xfs_ag.h" + +#include <linux/mm.h> +#include <linux/dax.h> + +struct failure_info { + xfs_agblock_t startblock; + xfs_extlen_t blockcount; + int mf_flags; +}; + +static pgoff_t +xfs_failure_pgoff( + struct xfs_mount *mp, + const struct xfs_rmap_irec *rec, + const struct failure_info *notify) +{ + loff_t pos = XFS_FSB_TO_B(mp, rec->rm_offset); + + if (notify->startblock > rec->rm_startblock) + pos += XFS_FSB_TO_B(mp, + notify->startblock - rec->rm_startblock); + return pos >> PAGE_SHIFT; +} + +static unsigned long +xfs_failure_pgcnt( + struct xfs_mount *mp, + const struct xfs_rmap_irec *rec, + const struct failure_info *notify) +{ + xfs_agblock_t end_rec; + xfs_agblock_t end_notify; + xfs_agblock_t start_cross; + xfs_agblock_t end_cross; + + start_cross = max(rec->rm_startblock, notify->startblock); + + end_rec = rec->rm_startblock + rec->rm_blockcount; + end_notify = notify->startblock + notify->blockcount; + end_cross = min(end_rec, end_notify); + + return XFS_FSB_TO_B(mp, end_cross - start_cross) >> PAGE_SHIFT; +} + +static int +xfs_dax_failure_fn( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *data) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_inode *ip; + struct failure_info *notify = data; + int error = 0; + + if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) || + (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) { + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } + + /* Get files that incore, filter out others that are not in use. */ + error = xfs_iget(mp, cur->bc_tp, rec->rm_owner, XFS_IGET_INCORE, + 0, &ip); + /* Continue the rmap query if the inode isn't incore */ + if (error == -ENODATA) + return 0; + if (error) + return error; + + error = mf_dax_kill_procs(VFS_I(ip)->i_mapping, + xfs_failure_pgoff(mp, rec, notify), + xfs_failure_pgcnt(mp, rec, notify), + notify->mf_flags); + xfs_irele(ip); + return error; +} + +static int +xfs_dax_notify_ddev_failure( + struct xfs_mount *mp, + xfs_daddr_t daddr, + xfs_daddr_t bblen, + int mf_flags) +{ + struct xfs_trans *tp = NULL; + struct xfs_btree_cur *cur = NULL; + struct xfs_buf *agf_bp = NULL; + int error = 0; + xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, daddr); + xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno); + xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp, daddr + bblen); + xfs_agnumber_t end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno); + + error = xfs_trans_alloc_empty(mp, &tp); + if (error) + return error; + + for (; agno <= end_agno; agno++) { + struct xfs_rmap_irec ri_low = { }; + struct xfs_rmap_irec ri_high; + struct failure_info notify; + struct xfs_agf *agf; + xfs_agblock_t agend; + struct xfs_perag *pag; + + pag = xfs_perag_get(mp, agno); + error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); + if (error) { + xfs_perag_put(pag); + break; + } + + cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag); + + /* + * Set the rmap range from ri_low to ri_high, which represents + * a [start, end] where we looking for the files or metadata. + */ + memset(&ri_high, 0xFF, sizeof(ri_high)); + ri_low.rm_startblock = XFS_FSB_TO_AGBNO(mp, fsbno); + if (agno == end_agno) + ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno); + + agf = agf_bp->b_addr; + agend = min(be32_to_cpu(agf->agf_length), + ri_high.rm_startblock); + notify.startblock = ri_low.rm_startblock; + notify.blockcount = agend - ri_low.rm_startblock; + + error = xfs_rmap_query_range(cur, &ri_low, &ri_high, + xfs_dax_failure_fn, ¬ify); + xfs_btree_del_cursor(cur, error); + xfs_trans_brelse(tp, agf_bp); + xfs_perag_put(pag); + if (error) + break; + + fsbno = XFS_AGB_TO_FSB(mp, agno + 1, 0); + } + + xfs_trans_cancel(tp); + return error; +} + +static int +xfs_dax_notify_failure( + struct dax_device *dax_dev, + u64 offset, + u64 len, + int mf_flags) +{ + struct xfs_mount *mp = dax_holder(dax_dev); + u64 ddev_start; + u64 ddev_end; + + if (!(mp->m_sb.sb_flags & SB_BORN)) { + xfs_warn(mp, "filesystem is not ready for notify_failure()!"); + return -EIO; + } + + if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) { + xfs_warn(mp, + "notify_failure() not supported on realtime device!"); + return -EOPNOTSUPP; + } + + if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev && + mp->m_logdev_targp != mp->m_ddev_targp) { + xfs_err(mp, "ondisk log corrupt, shutting down fs!"); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } + + if (!xfs_has_rmapbt(mp)) { + xfs_warn(mp, "notify_failure() needs rmapbt enabled!"); + return -EOPNOTSUPP; + } + + ddev_start = mp->m_ddev_targp->bt_dax_part_off; + ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1; + + /* Ignore the range out of filesystem area */ + if (offset + len < ddev_start) + return -ENXIO; + if (offset > ddev_end) + return -ENXIO; + + /* Calculate the real range when it touches the boundary */ + if (offset > ddev_start) + offset -= ddev_start; + else { + len -= ddev_start - offset; + offset = 0; + } + if (offset + len > ddev_end) + len -= ddev_end - offset; + + return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len), + mf_flags); +} + +const struct dax_holder_operations xfs_dax_holder_operations = { + .notify_failure = xfs_dax_notify_failure, +}; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index abf08bbf34a9..18bb4ec4d7c9 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -677,7 +677,8 @@ xfs_qm_init_quotainfo( qinf->qi_shrinker.seeks = DEFAULT_SEEKS; qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE; - error = register_shrinker(&qinf->qi_shrinker); + error = register_shrinker(&qinf->qi_shrinker, "xfs-qm:%s", + mp->m_super->s_id); if (error) goto out_free_inos; @@ -1154,7 +1155,7 @@ xfs_qm_dqusage_adjust( ASSERT(ip->i_delayed_blks == 0); if (XFS_IS_REALTIME_INODE(ip)) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); error = xfs_iread_extents(tp, ip, XFS_DATA_FORK); if (error) @@ -1229,10 +1230,14 @@ xfs_qm_flush_one( */ if (!xfs_dqflock_nowait(dqp)) { /* buf is pinned in-core by delwri list */ - bp = xfs_buf_incore(mp->m_ddev_targp, dqp->q_blkno, - mp->m_quotainfo->qi_dqchunklen, 0); - if (!bp) { - error = -EINVAL; + error = xfs_buf_incore(mp->m_ddev_targp, dqp->q_blkno, + mp->m_quotainfo->qi_dqchunklen, 0, &bp); + if (error) + goto out_unlock; + + if (!(bp->b_flags & _XBF_DELWRI_Q)) { + error = -EAGAIN; + xfs_buf_relse(bp); goto out_unlock; } xfs_buf_unlock(bp); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index e7a7c00d93be..251f20ddd368 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -125,11 +125,10 @@ * shared blocks. If there are no shared extents, fbno and flen will * be set to NULLAGBLOCK and 0, respectively. */ -int +static int xfs_reflink_find_shared( - struct xfs_mount *mp, + struct xfs_perag *pag, struct xfs_trans *tp, - xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno, @@ -140,11 +139,11 @@ xfs_reflink_find_shared( struct xfs_btree_cur *cur; int error; - error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); + error = xfs_alloc_read_agf(pag, tp, 0, &agbp); if (error) return error; - cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agbp->b_pag); + cur = xfs_refcountbt_init_cursor(pag->pag_mount, tp, agbp, pag); error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen, find_end_of_shared); @@ -171,7 +170,8 @@ xfs_reflink_trim_around_shared( struct xfs_bmbt_irec *irec, bool *shared) { - xfs_agnumber_t agno; + struct xfs_mount *mp = ip->i_mount; + struct xfs_perag *pag; xfs_agblock_t agbno; xfs_extlen_t aglen; xfs_agblock_t fbno; @@ -186,12 +186,13 @@ xfs_reflink_trim_around_shared( trace_xfs_reflink_trim_around_shared(ip, irec); - agno = XFS_FSB_TO_AGNO(ip->i_mount, irec->br_startblock); - agbno = XFS_FSB_TO_AGBNO(ip->i_mount, irec->br_startblock); + pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, irec->br_startblock)); + agbno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock); aglen = irec->br_blockcount; - error = xfs_reflink_find_shared(ip->i_mount, NULL, agno, agbno, - aglen, &fbno, &flen, true); + error = xfs_reflink_find_shared(pag, NULL, agbno, aglen, &fbno, &flen, + true); + xfs_perag_put(pag); if (error) return error; @@ -340,9 +341,41 @@ xfs_find_trim_cow_extent( return 0; } -/* Allocate all CoW reservations covering a range of blocks in a file. */ -int -xfs_reflink_allocate_cow( +static int +xfs_reflink_convert_unwritten( + struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, + struct xfs_bmbt_irec *cmap, + bool convert_now) +{ + xfs_fileoff_t offset_fsb = imap->br_startoff; + xfs_filblks_t count_fsb = imap->br_blockcount; + int error; + + /* + * cmap might larger than imap due to cowextsize hint. + */ + xfs_trim_extent(cmap, offset_fsb, count_fsb); + + /* + * COW fork extents are supposed to remain unwritten until we're ready + * to initiate a disk write. For direct I/O we are going to write the + * data and need the conversion, but for buffered writes we're done. + */ + if (!convert_now || cmap->br_state == XFS_EXT_NORM) + return 0; + + trace_xfs_reflink_convert_cow(ip, cmap); + + error = xfs_reflink_convert_cow_locked(ip, offset_fsb, count_fsb); + if (!error) + cmap->br_state = XFS_EXT_NORM; + + return error; +} + +static int +xfs_reflink_fill_cow_hole( struct xfs_inode *ip, struct xfs_bmbt_irec *imap, struct xfs_bmbt_irec *cmap, @@ -351,25 +384,12 @@ xfs_reflink_allocate_cow( bool convert_now) { struct xfs_mount *mp = ip->i_mount; - xfs_fileoff_t offset_fsb = imap->br_startoff; - xfs_filblks_t count_fsb = imap->br_blockcount; struct xfs_trans *tp; - int nimaps, error = 0; - bool found; xfs_filblks_t resaligned; - xfs_extlen_t resblks = 0; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - if (!ip->i_cowfp) { - ASSERT(!xfs_is_reflink_inode(ip)); - xfs_ifork_init_cow(ip); - } - - error = xfs_find_trim_cow_extent(ip, imap, cmap, shared, &found); - if (error || !*shared) - return error; - if (found) - goto convert; + xfs_extlen_t resblks; + int nimaps; + int error; + bool found; resaligned = xfs_aligned_fsb_count(imap->br_startoff, imap->br_blockcount, xfs_get_cowextsz_hint(ip)); @@ -385,17 +405,17 @@ xfs_reflink_allocate_cow( *lockmode = XFS_ILOCK_EXCL; - /* - * Check for an overlapping extent again now that we dropped the ilock. - */ error = xfs_find_trim_cow_extent(ip, imap, cmap, shared, &found); if (error || !*shared) goto out_trans_cancel; + if (found) { xfs_trans_cancel(tp); goto convert; } + ASSERT(cmap->br_startoff > imap->br_startoff); + /* Allocate the entire reservation as unwritten blocks. */ nimaps = 1; error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount, @@ -415,26 +435,135 @@ xfs_reflink_allocate_cow( */ if (nimaps == 0) return -ENOSPC; + convert: - xfs_trim_extent(cmap, offset_fsb, count_fsb); - /* - * COW fork extents are supposed to remain unwritten until we're ready - * to initiate a disk write. For direct I/O we are going to write the - * data and need the conversion, but for buffered writes we're done. - */ - if (!convert_now || cmap->br_state == XFS_EXT_NORM) - return 0; - trace_xfs_reflink_convert_cow(ip, cmap); - error = xfs_reflink_convert_cow_locked(ip, offset_fsb, count_fsb); - if (!error) - cmap->br_state = XFS_EXT_NORM; + return xfs_reflink_convert_unwritten(ip, imap, cmap, convert_now); + +out_trans_cancel: + xfs_trans_cancel(tp); return error; +} + +static int +xfs_reflink_fill_delalloc( + struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, + struct xfs_bmbt_irec *cmap, + bool *shared, + uint *lockmode, + bool convert_now) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp; + int nimaps; + int error; + bool found; + + do { + xfs_iunlock(ip, *lockmode); + *lockmode = 0; + + error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, 0, 0, + false, &tp); + if (error) + return error; + + *lockmode = XFS_ILOCK_EXCL; + + error = xfs_find_trim_cow_extent(ip, imap, cmap, shared, + &found); + if (error || !*shared) + goto out_trans_cancel; + + if (found) { + xfs_trans_cancel(tp); + break; + } + + ASSERT(isnullstartblock(cmap->br_startblock) || + cmap->br_startblock == DELAYSTARTBLOCK); + + /* + * Replace delalloc reservation with an unwritten extent. + */ + nimaps = 1; + error = xfs_bmapi_write(tp, ip, cmap->br_startoff, + cmap->br_blockcount, + XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, 0, + cmap, &nimaps); + if (error) + goto out_trans_cancel; + + xfs_inode_set_cowblocks_tag(ip); + error = xfs_trans_commit(tp); + if (error) + return error; + + /* + * Allocation succeeded but the requested range was not even + * partially satisfied? Bail out! + */ + if (nimaps == 0) + return -ENOSPC; + } while (cmap->br_startoff + cmap->br_blockcount <= imap->br_startoff); + + return xfs_reflink_convert_unwritten(ip, imap, cmap, convert_now); out_trans_cancel: xfs_trans_cancel(tp); return error; } +/* Allocate all CoW reservations covering a range of blocks in a file. */ +int +xfs_reflink_allocate_cow( + struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, + struct xfs_bmbt_irec *cmap, + bool *shared, + uint *lockmode, + bool convert_now) +{ + int error; + bool found; + + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + if (!ip->i_cowfp) { + ASSERT(!xfs_is_reflink_inode(ip)); + xfs_ifork_init_cow(ip); + } + + error = xfs_find_trim_cow_extent(ip, imap, cmap, shared, &found); + if (error || !*shared) + return error; + + /* CoW fork has a real extent */ + if (found) + return xfs_reflink_convert_unwritten(ip, imap, cmap, + convert_now); + + /* + * CoW fork does not have an extent and data extent is shared. + * Allocate a real extent in the CoW fork. + */ + if (cmap->br_startoff > imap->br_startoff) + return xfs_reflink_fill_cow_hole(ip, imap, cmap, shared, + lockmode, convert_now); + + /* + * CoW fork has a delalloc reservation. Replace it with a real extent. + * There may or may not be a data fork mapping. + */ + if (isnullstartblock(cmap->br_startblock) || + cmap->br_startblock == DELAYSTARTBLOCK) + return xfs_reflink_fill_delalloc(ip, imap, cmap, shared, + lockmode, convert_now); + + /* Shouldn't get here. */ + ASSERT(0); + return -EFSCORRUPTED; +} + /* * Cancel CoW reservations for some block range of an inode. * @@ -452,7 +581,7 @@ xfs_reflink_cancel_cow_blocks( xfs_fileoff_t end_fsb, bool cancel_real) { - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); struct xfs_bmbt_irec got, del; struct xfs_iext_cursor icur; int error = 0; @@ -593,7 +722,7 @@ xfs_reflink_end_cow_extent( struct xfs_bmbt_irec got, del, data; struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; - struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); unsigned int resblks; int nmaps; int error; @@ -1363,12 +1492,16 @@ xfs_reflink_remap_prep( if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) goto out_unlock; - /* Don't share DAX file data for now. */ - if (IS_DAX(inode_in) || IS_DAX(inode_out)) + /* Don't share DAX file data with non-DAX file. */ + if (IS_DAX(inode_in) != IS_DAX(inode_out)) goto out_unlock; - ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, - len, remap_flags); + if (!IS_DAX(inode_in)) + ret = generic_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags); + else + ret = dax_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags, &xfs_read_iomap_ops); if (ret || *len == 0) goto out_unlock; @@ -1420,16 +1553,11 @@ xfs_reflink_inode_has_shared_extents( struct xfs_bmbt_irec got; struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp; - xfs_agnumber_t agno; - xfs_agblock_t agbno; - xfs_extlen_t aglen; - xfs_agblock_t rbno; - xfs_extlen_t rlen; struct xfs_iext_cursor icur; bool found; int error; - ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); error = xfs_iread_extents(tp, ip, XFS_DATA_FORK); if (error) return error; @@ -1437,17 +1565,25 @@ xfs_reflink_inode_has_shared_extents( *has_shared = false; found = xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got); while (found) { + struct xfs_perag *pag; + xfs_agblock_t agbno; + xfs_extlen_t aglen; + xfs_agblock_t rbno; + xfs_extlen_t rlen; + if (isnullstartblock(got.br_startblock) || got.br_state != XFS_EXT_NORM) goto next; - agno = XFS_FSB_TO_AGNO(mp, got.br_startblock); + + pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, got.br_startblock)); agbno = XFS_FSB_TO_AGBNO(mp, got.br_startblock); aglen = got.br_blockcount; - - error = xfs_reflink_find_shared(mp, tp, agno, agbno, aglen, + error = xfs_reflink_find_shared(pag, tp, agbno, aglen, &rbno, &rlen, false); + xfs_perag_put(pag); if (error) return error; + /* Is there still a shared block here? */ if (rbno != NULLAGBLOCK) { *has_shared = true; diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index bea65f2fe657..65c5dfe17ecf 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -16,9 +16,6 @@ static inline bool xfs_is_cow_inode(struct xfs_inode *ip) return xfs_is_reflink_inode(ip) || xfs_is_always_cow_inode(ip); } -extern int xfs_reflink_find_shared(struct xfs_mount *mp, struct xfs_trans *tp, - xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_extlen_t aglen, - xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_maximal); extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip, struct xfs_bmbt_irec *irec, bool *shared); int xfs_bmap_trim_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap, diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index aa977c7ea370..9ac59814bbb6 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -40,6 +40,7 @@ #include "xfs_defer.h" #include "xfs_attr_item.h" #include "xfs_xattr.h" +#include "xfs_iunlink_item.h" #include <linux/magic.h> #include <linux/fs_context.h> @@ -350,8 +351,10 @@ xfs_setup_dax_always( goto disable_dax; } - if (xfs_has_reflink(mp)) { - xfs_alert(mp, "DAX and reflink cannot be used together!"); + if (xfs_has_reflink(mp) && + bdev_is_partition(mp->m_ddev_targp->bt_bdev)) { + xfs_alert(mp, + "DAX and reflink cannot work with multi-partitions!"); return -EINVAL; } @@ -1966,11 +1969,19 @@ xfs_init_caches(void) { int error; + xfs_buf_cache = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0, + SLAB_HWCACHE_ALIGN | + SLAB_RECLAIM_ACCOUNT | + SLAB_MEM_SPREAD, + NULL); + if (!xfs_buf_cache) + goto out; + xfs_log_ticket_cache = kmem_cache_create("xfs_log_ticket", sizeof(struct xlog_ticket), 0, 0, NULL); if (!xfs_log_ticket_cache) - goto out; + goto out_destroy_buf_cache; error = xfs_btree_init_cur_caches(); if (error) @@ -2096,8 +2107,16 @@ xfs_init_caches(void) if (!xfs_attri_cache) goto out_destroy_attrd_cache; + xfs_iunlink_cache = kmem_cache_create("xfs_iul_item", + sizeof(struct xfs_iunlink_item), + 0, 0, NULL); + if (!xfs_iunlink_cache) + goto out_destroy_attri_cache; + return 0; + out_destroy_attri_cache: + kmem_cache_destroy(xfs_attri_cache); out_destroy_attrd_cache: kmem_cache_destroy(xfs_attrd_cache); out_destroy_bui_cache: @@ -2136,6 +2155,8 @@ xfs_init_caches(void) xfs_btree_destroy_cur_caches(); out_destroy_log_ticket_cache: kmem_cache_destroy(xfs_log_ticket_cache); + out_destroy_buf_cache: + kmem_cache_destroy(xfs_buf_cache); out: return -ENOMEM; } @@ -2148,6 +2169,7 @@ xfs_destroy_caches(void) * destroy caches. */ rcu_barrier(); + kmem_cache_destroy(xfs_iunlink_cache); kmem_cache_destroy(xfs_attri_cache); kmem_cache_destroy(xfs_attrd_cache); kmem_cache_destroy(xfs_bui_cache); @@ -2168,6 +2190,7 @@ xfs_destroy_caches(void) xfs_defer_destroy_item_caches(); xfs_btree_destroy_cur_caches(); kmem_cache_destroy(xfs_log_ticket_cache); + kmem_cache_destroy(xfs_buf_cache); } STATIC int __init @@ -2213,6 +2236,7 @@ xfs_cpu_dead( list_for_each_entry_safe(mp, n, &xfs_mount_list, m_mount_list) { spin_unlock(&xfs_mount_list_lock); xfs_inodegc_cpu_dead(mp, cpu); + xlog_cil_pcp_dead(mp->m_log, cpu); spin_lock(&xfs_mount_list_lock); } spin_unlock(&xfs_mount_list_lock); @@ -2272,13 +2296,9 @@ init_xfs_fs(void) if (error) goto out_destroy_wq; - error = xfs_buf_init(); - if (error) - goto out_mru_cache_uninit; - error = xfs_init_procfs(); if (error) - goto out_buf_terminate; + goto out_mru_cache_uninit; error = xfs_sysctl_register(); if (error) @@ -2335,8 +2355,6 @@ init_xfs_fs(void) xfs_sysctl_unregister(); out_cleanup_procfs: xfs_cleanup_procfs(); - out_buf_terminate: - xfs_buf_terminate(); out_mru_cache_uninit: xfs_mru_cache_uninit(); out_destroy_wq: @@ -2362,7 +2380,6 @@ exit_xfs_fs(void) kset_unregister(xfs_kset); xfs_sysctl_unregister(); xfs_cleanup_procfs(); - xfs_buf_terminate(); xfs_mru_cache_uninit(); xfs_destroy_workqueues(); xfs_destroy_caches(); diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index 3cd5a51bace1..364e2c2648a8 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -92,6 +92,7 @@ extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *, extern const struct export_operations xfs_export_operations; extern const struct quotactl_ops xfs_quotactl_operations; +extern const struct dax_holder_operations xfs_dax_holder_operations; extern void xfs_reinit_percpu_counters(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 4145ba872547..8389f3ef88ef 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -256,7 +256,7 @@ xfs_symlink( /* * If the symlink will fit into the inode, write it inline. */ - if (pathlen <= XFS_IFORK_DSIZE(ip)) { + if (pathlen <= xfs_inode_data_fork_size(ip)) { xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen); ip->i_disk_size = pathlen; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 0fa1b7a2918c..f9057af6e0c8 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -2171,7 +2171,7 @@ DECLARE_EVENT_CLASS(xfs_swap_extent_class, __entry->format = ip->i_df.if_format; __entry->nex = ip->i_df.if_nextents; __entry->broot_size = ip->i_df.if_broot_bytes; - __entry->fork_off = XFS_IFORK_BOFF(ip); + __entry->fork_off = xfs_inode_fork_boff(ip); ), TP_printk("dev %d:%d ino 0x%llx (%s), %s format, num_extents %llu, " "broot size %d, forkoff 0x%x", @@ -3672,7 +3672,6 @@ DEFINE_EVENT(xfs_ag_inode_class, name, \ TP_ARGS(ip)) DEFINE_AGINODE_EVENT(xfs_iunlink); DEFINE_AGINODE_EVENT(xfs_iunlink_remove); -DEFINE_AG_EVENT(xfs_iunlink_map_prev_fallback); DECLARE_EVENT_CLASS(xfs_fs_corrupt_class, TP_PROTO(struct xfs_mount *mp, unsigned int flags), diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 82cf0189c0db..7bd16fbff534 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -760,7 +760,7 @@ xfs_log_item_batch_insert( void xfs_trans_committed_bulk( struct xfs_ail *ailp, - struct xfs_log_vec *log_vector, + struct list_head *lv_chain, xfs_lsn_t commit_lsn, bool aborted) { @@ -775,7 +775,7 @@ xfs_trans_committed_bulk( spin_unlock(&ailp->ail_lock); /* unpin all the log items */ - for (lv = log_vector; lv; lv = lv->lv_next ) { + list_for_each_entry(lv, lv_chain, lv_list) { struct xfs_log_item *lip = lv->lv_item; xfs_lsn_t item_lsn; @@ -845,6 +845,90 @@ xfs_trans_committed_bulk( } /* + * Sort transaction items prior to running precommit operations. This will + * attempt to order the items such that they will always be locked in the same + * order. Items that have no sort function are moved to the end of the list + * and so are locked last. + * + * This may need refinement as different types of objects add sort functions. + * + * Function is more complex than it needs to be because we are comparing 64 bit + * values and the function only returns 32 bit values. + */ +static int +xfs_trans_precommit_sort( + void *unused_arg, + const struct list_head *a, + const struct list_head *b) +{ + struct xfs_log_item *lia = container_of(a, + struct xfs_log_item, li_trans); + struct xfs_log_item *lib = container_of(b, + struct xfs_log_item, li_trans); + int64_t diff; + + /* + * If both items are non-sortable, leave them alone. If only one is + * sortable, move the non-sortable item towards the end of the list. + */ + if (!lia->li_ops->iop_sort && !lib->li_ops->iop_sort) + return 0; + if (!lia->li_ops->iop_sort) + return 1; + if (!lib->li_ops->iop_sort) + return -1; + + diff = lia->li_ops->iop_sort(lia) - lib->li_ops->iop_sort(lib); + if (diff < 0) + return -1; + if (diff > 0) + return 1; + return 0; +} + +/* + * Run transaction precommit functions. + * + * If there is an error in any of the callouts, then stop immediately and + * trigger a shutdown to abort the transaction. There is no recovery possible + * from errors at this point as the transaction is dirty.... + */ +static int +xfs_trans_run_precommits( + struct xfs_trans *tp) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_log_item *lip, *n; + int error = 0; + + /* + * Sort the item list to avoid ABBA deadlocks with other transactions + * running precommit operations that lock multiple shared items such as + * inode cluster buffers. + */ + list_sort(NULL, &tp->t_items, xfs_trans_precommit_sort); + + /* + * Precommit operations can remove the log item from the transaction + * if the log item exists purely to delay modifications until they + * can be ordered against other operations. Hence we have to use + * list_for_each_entry_safe() here. + */ + list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) { + if (!test_bit(XFS_LI_DIRTY, &lip->li_flags)) + continue; + if (lip->li_ops->iop_precommit) { + error = lip->li_ops->iop_precommit(tp, lip); + if (error) + break; + } + } + if (error) + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return error; +} + +/* * Commit the given transaction to the log. * * XFS disk error handling mechanism is not based on a typical @@ -869,6 +953,13 @@ __xfs_trans_commit( trace_xfs_trans_commit(tp, _RET_IP_); + error = xfs_trans_run_precommits(tp); + if (error) { + if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) + xfs_defer_cancel(tp); + goto out_unreserve; + } + /* * Finish deferred items on final commit. Only permanent transactions * should ever have deferred ops. diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 9561f193e7e1..55819785941c 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -45,6 +45,7 @@ struct xfs_log_item { struct xfs_log_vec *li_lv; /* active log vector */ struct xfs_log_vec *li_lv_shadow; /* standby vector */ xfs_csn_t li_seq; /* CIL commit seq */ + uint32_t li_order_id; /* CIL commit order */ }; /* @@ -71,10 +72,12 @@ struct xfs_item_ops { void (*iop_format)(struct xfs_log_item *, struct xfs_log_vec *); void (*iop_pin)(struct xfs_log_item *); void (*iop_unpin)(struct xfs_log_item *, int remove); - uint (*iop_push)(struct xfs_log_item *, struct list_head *); + uint64_t (*iop_sort)(struct xfs_log_item *lip); + int (*iop_precommit)(struct xfs_trans *tp, struct xfs_log_item *lip); void (*iop_committing)(struct xfs_log_item *lip, xfs_csn_t seq); - void (*iop_release)(struct xfs_log_item *); xfs_lsn_t (*iop_committed)(struct xfs_log_item *, xfs_lsn_t); + uint (*iop_push)(struct xfs_log_item *, struct list_head *); + void (*iop_release)(struct xfs_log_item *); int (*iop_recover)(struct xfs_log_item *lip, struct list_head *capture_list); bool (*iop_match)(struct xfs_log_item *item, uint64_t id); diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index f0d79a9050ba..d5400150358e 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -19,7 +19,8 @@ void xfs_trans_add_item(struct xfs_trans *, struct xfs_log_item *); void xfs_trans_del_item(struct xfs_log_item *); void xfs_trans_unreserve_and_mod_sb(struct xfs_trans *tp); -void xfs_trans_committed_bulk(struct xfs_ail *ailp, struct xfs_log_vec *lv, +void xfs_trans_committed_bulk(struct xfs_ail *ailp, + struct list_head *lv_chain, xfs_lsn_t commit_lsn, bool aborted); /* * AIL traversal cursor. diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 511bb9fa3750..860f0b1032c6 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -231,13 +231,6 @@ static const struct iomap_writeback_ops zonefs_writeback_ops = { .map_blocks = zonefs_write_map_blocks, }; -static int zonefs_writepage(struct page *page, struct writeback_control *wbc) -{ - struct iomap_writepage_ctx wpc = { }; - - return iomap_writepage(page, wbc, &wpc, &zonefs_writeback_ops); -} - static int zonefs_writepages(struct address_space *mapping, struct writeback_control *wbc) { @@ -265,7 +258,6 @@ static int zonefs_swap_activate(struct swap_info_struct *sis, static const struct address_space_operations zonefs_file_aops = { .read_folio = zonefs_read_folio, .readahead = zonefs_readahead, - .writepage = zonefs_writepage, .writepages = zonefs_writepages, .dirty_folio = filemap_dirty_folio, .release_folio = iomap_release_folio, |