diff options
Diffstat (limited to 'fs')
155 files changed, 2886 insertions, 1747 deletions
diff --git a/fs/9p/fid.c b/fs/9p/fid.c index 3d681a2c2731..9d9de62592be 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -39,6 +39,48 @@ void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid) } /** + * v9fs_fid_find_inode - search for an open fid off of the inode list + * @inode: return a fid pointing to a specific inode + * @uid: return a fid belonging to the specified user + * + */ + +static struct p9_fid *v9fs_fid_find_inode(struct inode *inode, kuid_t uid) +{ + struct hlist_head *h; + struct p9_fid *fid, *ret = NULL; + + p9_debug(P9_DEBUG_VFS, " inode: %p\n", inode); + + spin_lock(&inode->i_lock); + h = (struct hlist_head *)&inode->i_private; + hlist_for_each_entry(fid, h, ilist) { + if (uid_eq(fid->uid, uid)) { + refcount_inc(&fid->count); + ret = fid; + break; + } + } + spin_unlock(&inode->i_lock); + return ret; +} + +/** + * v9fs_open_fid_add - add an open fid to an inode + * @dentry: inode that the fid is being added to + * @fid: fid to add + * + */ + +void v9fs_open_fid_add(struct inode *inode, struct p9_fid *fid) +{ + spin_lock(&inode->i_lock); + hlist_add_head(&fid->ilist, (struct hlist_head *)&inode->i_private); + spin_unlock(&inode->i_lock); +} + + +/** * v9fs_fid_find - retrieve a fid that belongs to the specified uid * @dentry: dentry to look for fid in * @uid: return fid that belongs to the specified user @@ -54,13 +96,18 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any) dentry, dentry, from_kuid(&init_user_ns, uid), any); ret = NULL; + + if (d_inode(dentry)) + ret = v9fs_fid_find_inode(d_inode(dentry), uid); + /* we'll recheck under lock if there's anything to look in */ - if (dentry->d_fsdata) { + if (!ret && dentry->d_fsdata) { struct hlist_head *h = (struct hlist_head *)&dentry->d_fsdata; spin_lock(&dentry->d_lock); hlist_for_each_entry(fid, h, dlist) { if (any || uid_eq(fid->uid, uid)) { ret = fid; + refcount_inc(&ret->count); break; } } @@ -122,7 +169,10 @@ 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 */ - fid = p9_client_walk(fid, 1, &dentry->d_name.name, 1); + struct p9_fid *ofid = fid; + + fid = p9_client_walk(ofid, 1, &dentry->d_name.name, 1); + p9_client_clunk(ofid); goto fid_out; } up_read(&v9ses->rename_sem); @@ -147,8 +197,10 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry, v9fs_fid_add(dentry->d_sb->s_root, fid); } /* If we are root ourself just return that */ - if (dentry->d_sb->s_root == dentry) + if (dentry->d_sb->s_root == dentry) { + refcount_inc(&fid->count); return fid; + } /* * Do a multipath walk with attached root. * When walking parent we need to make sure we @@ -195,6 +247,7 @@ fid_out: fid = ERR_PTR(-ENOENT); } else { __add_fid(dentry, fid); + refcount_inc(&fid->count); spin_unlock(&dentry->d_lock); } } @@ -245,11 +298,13 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry) struct p9_fid *v9fs_writeback_fid(struct dentry *dentry) { int err; - struct p9_fid *fid; + struct p9_fid *fid, *ofid; - fid = clone_fid(v9fs_fid_lookup_with_uid(dentry, GLOBAL_ROOT_UID, 0)); + ofid = v9fs_fid_lookup_with_uid(dentry, GLOBAL_ROOT_UID, 0); + fid = clone_fid(ofid); if (IS_ERR(fid)) goto error_out; + p9_client_clunk(ofid); /* * writeback fid will only be used to write back the * dirty pages. We always request for the open fid in read-write diff --git a/fs/9p/fid.h b/fs/9p/fid.h index 928b1093f511..f7f33509e169 100644 --- a/fs/9p/fid.h +++ b/fs/9p/fid.h @@ -15,12 +15,21 @@ static inline struct p9_fid *v9fs_parent_fid(struct dentry *dentry) } 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); static inline struct p9_fid *clone_fid(struct p9_fid *fid) { return IS_ERR(fid) ? fid : p9_client_walk(fid, 0, NULL, 1); } static inline struct p9_fid *v9fs_fid_clone(struct dentry *dentry) { - return clone_fid(v9fs_fid_lookup(dentry)); + struct p9_fid *fid, *nfid; + + fid = v9fs_fid_lookup(dentry); + if (!fid || IS_ERR(fid)) + return fid; + + nfid = clone_fid(fid); + p9_client_clunk(fid); + return nfid; } #endif diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index 7d6f69aefd45..4b4292123b3d 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -85,6 +85,8 @@ 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); + if (retval == -ENOENT) return 0; if (retval < 0) diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 674d22bf4f6f..b6a5a0be444d 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -210,8 +210,12 @@ int v9fs_dir_release(struct inode *inode, struct file *filp) fid = filp->private_data; p9_debug(P9_DEBUG_VFS, "inode: %p filp: %p fid: %d\n", inode, filp, fid ? fid->fid : -1); - if (fid) + if (fid) { + spin_lock(&inode->i_lock); + hlist_del(&fid->ilist); + spin_unlock(&inode->i_lock); p9_client_clunk(fid); + } return 0; } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index be5768949cb1..649f04f112dc 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -46,7 +46,7 @@ int v9fs_file_open(struct inode *inode, struct file *file) int err; struct v9fs_inode *v9inode; struct v9fs_session_info *v9ses; - struct p9_fid *fid; + struct p9_fid *fid, *writeback_fid; int omode; p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, file); @@ -85,17 +85,18 @@ int v9fs_file_open(struct inode *inode, struct file *file) * because we want write after unlink usecase * to work. */ - fid = v9fs_writeback_fid(file_dentry(file)); + writeback_fid = v9fs_writeback_fid(file_dentry(file)); if (IS_ERR(fid)) { err = PTR_ERR(fid); mutex_unlock(&v9inode->v_mutex); goto out_error; } - v9inode->writeback_fid = (void *) fid; + v9inode->writeback_fid = (void *) writeback_fid; } mutex_unlock(&v9inode->v_mutex); if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) v9fs_cache_inode_set_cookie(inode, file); + v9fs_open_fid_add(inode, fid); return 0; out_error: p9_client_clunk(file->private_data); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index ae0c38ad1fcb..4a937fac1acb 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -256,6 +256,7 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, inode->i_rdev = rdev; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_mapping->a_ops = &v9fs_addr_operations; + inode->i_private = NULL; switch (mode & S_IFMT) { case S_IFIFO: @@ -550,6 +551,7 @@ 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); if (retval == -EOPNOTSUPP) { /* Try the one based on path */ v9fid = v9fs_fid_clone(dentry); @@ -570,6 +572,10 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags) v9fs_invalidate_inode_attr(inode); v9fs_invalidate_inode_attr(dir); + + /* invalidate all fids associated with dentry */ + /* NOTE: This will not include open fids */ + dentry->d_op->d_release(dentry); } return retval; } @@ -590,14 +596,12 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir, { int err; const unsigned char *name; - struct p9_fid *dfid, *ofid, *fid; + struct p9_fid *dfid, *ofid = NULL, *fid = NULL; struct inode *inode; p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry); err = 0; - ofid = NULL; - fid = NULL; name = dentry->d_name.name; dfid = v9fs_parent_fid(dentry); if (IS_ERR(dfid)) { @@ -611,12 +615,14 @@ 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); } 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; } @@ -628,6 +634,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir, p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); fid = NULL; + p9_client_clunk(dfid); goto error; } /* @@ -638,11 +645,13 @@ 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); d_instantiate(dentry, inode); } + p9_client_clunk(dfid); return ofid; error: if (ofid) @@ -755,6 +764,7 @@ 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); if (fid == ERR_PTR(-ENOENT)) inode = NULL; else if (IS_ERR(fid)) @@ -792,6 +802,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, struct v9fs_session_info *v9ses; struct p9_fid *fid, *inode_fid; struct dentry *res = NULL; + struct inode *inode; if (d_in_lookup(dentry)) { res = v9fs_vfs_lookup(dir, dentry, 0); @@ -820,7 +831,8 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, } v9fs_invalidate_inode_attr(dir); - v9inode = V9FS_I(d_inode(dentry)); + inode = d_inode(dentry); + v9inode = V9FS_I(inode); mutex_lock(&v9inode->v_mutex); if ((v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) && !v9inode->writeback_fid && @@ -848,6 +860,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, file->private_data = fid; if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) v9fs_cache_inode_set_cookie(d_inode(dentry), file); + v9fs_open_fid_add(inode, fid); file->f_mode |= FMODE_CREATED; out: @@ -902,7 +915,7 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *old_inode; struct inode *new_inode; struct v9fs_session_info *v9ses; - struct p9_fid *oldfid; + struct p9_fid *oldfid, *dfid; struct p9_fid *olddirfid; struct p9_fid *newdirfid; struct p9_wstat wstat; @@ -919,13 +932,20 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (IS_ERR(oldfid)) return PTR_ERR(oldfid); - olddirfid = clone_fid(v9fs_parent_fid(old_dentry)); + dfid = v9fs_parent_fid(old_dentry); + olddirfid = clone_fid(dfid); + if (dfid && !IS_ERR(dfid)) + p9_client_clunk(dfid); + if (IS_ERR(olddirfid)) { retval = PTR_ERR(olddirfid); goto done; } - newdirfid = clone_fid(v9fs_parent_fid(new_dentry)); + dfid = v9fs_parent_fid(new_dentry); + newdirfid = clone_fid(dfid); + p9_client_clunk(dfid); + if (IS_ERR(newdirfid)) { retval = PTR_ERR(newdirfid); goto clunk_olddir; @@ -982,6 +1002,7 @@ clunk_olddir: p9_client_clunk(olddirfid); done: + p9_client_clunk(oldfid); return retval; } @@ -1014,6 +1035,7 @@ v9fs_vfs_getattr(const struct path *path, struct kstat *stat, return PTR_ERR(fid); st = p9_client_stat(fid); + p9_client_clunk(fid); if (IS_ERR(st)) return PTR_ERR(st); @@ -1034,7 +1056,7 @@ v9fs_vfs_getattr(const struct path *path, struct kstat *stat, static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) { - int retval; + int retval, use_dentry = 0; struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL; struct p9_wstat wstat; @@ -1050,8 +1072,10 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) fid = iattr->ia_file->private_data; WARN_ON(!fid); } - if (!fid) + if (!fid) { fid = v9fs_fid_lookup(dentry); + use_dentry = 1; + } if(IS_ERR(fid)) return PTR_ERR(fid); @@ -1081,6 +1105,10 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) filemap_write_and_wait(d_inode(dentry)->i_mapping); retval = p9_client_wstat(fid, &wstat); + + if (use_dentry) + p9_client_clunk(fid); + if (retval < 0) return retval; @@ -1205,6 +1233,7 @@ static const char *v9fs_vfs_get_link(struct dentry *dentry, return ERR_PTR(-EBADF); st = p9_client_stat(fid); + p9_client_clunk(fid); if (IS_ERR(st)) return ERR_CAST(st); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 0028eccb665a..823c2eb5f1bf 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -296,6 +296,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, /* 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); @@ -342,6 +343,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, file->private_data = ofid; if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) v9fs_cache_inode_set_cookie(inode, file); + v9fs_open_fid_add(inode, ofid); file->f_mode |= FMODE_CREATED; out: v9fs_put_acl(dacl, pacl); @@ -407,7 +409,6 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir, err = p9_client_mkdir_dotl(dfid, name, mode, gid, &qid); if (err < 0) goto error; - fid = p9_client_walk(dfid, 1, &name, 1); if (IS_ERR(fid)) { err = PTR_ERR(fid); @@ -451,6 +452,7 @@ error: if (fid) p9_client_clunk(fid); v9fs_put_acl(dacl, pacl); + p9_client_clunk(dfid); return err; } @@ -478,6 +480,7 @@ v9fs_vfs_getattr_dotl(const struct path *path, struct kstat *stat, */ st = p9_client_getattr_dotl(fid, P9_STATS_ALL); + p9_client_clunk(fid); if (IS_ERR(st)) return PTR_ERR(st); @@ -539,7 +542,7 @@ static int v9fs_mapped_iattr_valid(int iattr_valid) int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) { - int retval; + int retval, use_dentry = 0; struct p9_fid *fid = NULL; struct p9_iattr_dotl p9attr; struct inode *inode = d_inode(dentry); @@ -564,8 +567,10 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) fid = iattr->ia_file->private_data; WARN_ON(!fid); } - if (!fid) + if (!fid) { fid = v9fs_fid_lookup(dentry); + use_dentry = 1; + } if (IS_ERR(fid)) return PTR_ERR(fid); @@ -574,8 +579,11 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) filemap_write_and_wait(inode->i_mapping); retval = p9_client_setattr(fid, &p9attr); - if (retval < 0) + if (retval < 0) { + if (use_dentry) + p9_client_clunk(fid); return retval; + } if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size != i_size_read(inode)) @@ -587,9 +595,15 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) if (iattr->ia_valid & ATTR_MODE) { /* We also want to update ACL when we update mode bits */ retval = v9fs_acl_chmod(inode, fid); - if (retval < 0) + if (retval < 0) { + if (use_dentry) + p9_client_clunk(fid); return retval; + } } + if (use_dentry) + p9_client_clunk(fid); + return 0; } @@ -741,6 +755,7 @@ error: if (fid) p9_client_clunk(fid); + p9_client_clunk(dfid); return err; } @@ -769,11 +784,15 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, return PTR_ERR(dfid); oldfid = v9fs_fid_lookup(old_dentry); - if (IS_ERR(oldfid)) + if (IS_ERR(oldfid)) { + p9_client_clunk(dfid); return PTR_ERR(oldfid); + } err = p9_client_link(dfid, oldfid, dentry->d_name.name); + p9_client_clunk(dfid); + p9_client_clunk(oldfid); if (err < 0) { p9_debug(P9_DEBUG_VFS, "p9_client_link failed %d\n", err); return err; @@ -788,6 +807,7 @@ 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); } ihold(d_inode(old_dentry)); d_instantiate(dentry, d_inode(old_dentry)); @@ -886,6 +906,8 @@ error: if (fid) p9_client_clunk(fid); v9fs_put_acl(dacl, pacl); + p9_client_clunk(dfid); + return err; } @@ -914,6 +936,7 @@ 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); 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 9a21269b7234..5fce6e30bc5a 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -268,6 +268,7 @@ static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf) } res = simple_statfs(dentry, buf); done: + p9_client_clunk(fid); return res; } diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index ac8ff8ca4c11..87217dd0433e 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -71,14 +71,17 @@ ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name, void *buffer, size_t buffer_size) { struct p9_fid *fid; + int ret; p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu\n", name, buffer_size); fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) return PTR_ERR(fid); + ret = v9fs_fid_xattr_get(fid, name, buffer, buffer_size); + p9_client_clunk(fid); - return v9fs_fid_xattr_get(fid, name, buffer, buffer_size); + return ret; } /* @@ -96,8 +99,15 @@ ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name, int v9fs_xattr_set(struct dentry *dentry, const char *name, const void *value, size_t value_len, int flags) { - struct p9_fid *fid = v9fs_fid_lookup(dentry); - return v9fs_fid_xattr_set(fid, name, value, value_len, flags); + int ret; + struct p9_fid *fid; + + fid = v9fs_fid_lookup(dentry); + if (IS_ERR(fid)) + return PTR_ERR(fid); + ret = v9fs_fid_xattr_set(fid, name, value, value_len, flags); + p9_client_clunk(fid); + return ret; } int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name, diff --git a/fs/Kconfig b/fs/Kconfig index aa4c12282301..da524c4d7b7e 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -203,7 +203,7 @@ config TMPFS_XATTR config TMPFS_INODE64 bool "Use 64-bit ino_t by default in tmpfs" - depends on TMPFS && 64BIT + depends on TMPFS && 64BIT && !(S390 || ALPHA) default n help tmpfs has historically used only inode numbers as wide as an unsigned diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 885da6d983b4..c6f1c8c1934e 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -29,7 +29,7 @@ config BINFMT_ELF latest version). config COMPAT_BINFMT_ELF - bool + def_bool y depends on COMPAT && BINFMT_ELF select ELFCORE @@ -45,7 +45,7 @@ config ARCH_USE_GNU_PROPERTY config BINFMT_ELF_FDPIC bool "Kernel support for FDPIC ELF binaries" default y if !BINFMT_ELF - depends on (ARM || (SUPERH && !MMU) || C6X) + depends on (ARM || (SUPERH && !MMU)) select ELFCORE help ELF FDPIC binaries are based on ELF, but allow the individual load diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 9068d5578a26..7bd659ad959e 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -350,7 +350,7 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, unsigned blkoff) { union afs_xdr_dirent *dire; - unsigned offset, next, curr; + unsigned offset, next, curr, nr_slots; size_t nlen; int tmp; @@ -363,13 +363,12 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, offset < AFS_DIR_SLOTS_PER_BLOCK; offset = next ) { - next = offset + 1; - /* skip entries marked unused in the bitmap */ if (!(block->hdr.bitmap[offset / 8] & (1 << (offset % 8)))) { _debug("ENT[%zu.%u]: unused", blkoff / sizeof(union afs_xdr_dir_block), offset); + next = offset + 1; if (offset >= curr) ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); @@ -381,35 +380,39 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, nlen = strnlen(dire->u.name, sizeof(*block) - offset * sizeof(union afs_xdr_dirent)); + if (nlen > AFSNAMEMAX - 1) { + _debug("ENT[%zu]: name too long (len %u/%zu)", + blkoff / sizeof(union afs_xdr_dir_block), + offset, nlen); + return afs_bad(dvnode, afs_file_error_dir_name_too_long); + } _debug("ENT[%zu.%u]: %s %zu \"%s\"", blkoff / sizeof(union afs_xdr_dir_block), offset, (offset < curr ? "skip" : "fill"), nlen, dire->u.name); - /* work out where the next possible entry is */ - for (tmp = nlen; tmp > 15; tmp -= sizeof(union afs_xdr_dirent)) { - if (next >= AFS_DIR_SLOTS_PER_BLOCK) { - _debug("ENT[%zu.%u]:" - " %u travelled beyond end dir block" - " (len %u/%zu)", - blkoff / sizeof(union afs_xdr_dir_block), - offset, next, tmp, nlen); - return afs_bad(dvnode, afs_file_error_dir_over_end); - } - if (!(block->hdr.bitmap[next / 8] & - (1 << (next % 8)))) { - _debug("ENT[%zu.%u]:" - " %u unmarked extension (len %u/%zu)", + nr_slots = afs_dir_calc_slots(nlen); + next = offset + nr_slots; + if (next > AFS_DIR_SLOTS_PER_BLOCK) { + _debug("ENT[%zu.%u]:" + " %u extends beyond end dir block" + " (len %zu)", + blkoff / sizeof(union afs_xdr_dir_block), + offset, next, nlen); + return afs_bad(dvnode, afs_file_error_dir_over_end); + } + + /* Check that the name-extension dirents are all allocated */ + for (tmp = 1; tmp < nr_slots; tmp++) { + unsigned int ix = offset + tmp; + if (!(block->hdr.bitmap[ix / 8] & (1 << (ix % 8)))) { + _debug("ENT[%zu.u]:" + " %u unmarked extension (%u/%u)", blkoff / sizeof(union afs_xdr_dir_block), - offset, next, tmp, nlen); + offset, tmp, nr_slots); return afs_bad(dvnode, afs_file_error_dir_unmarked_ext); } - - _debug("ENT[%zu.%u]: ext %u/%zu", - blkoff / sizeof(union afs_xdr_dir_block), - next, tmp, nlen); - next++; } /* skip if starts before the current position */ diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index 2ffe09abae7f..f4600c1353ad 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -215,8 +215,7 @@ void afs_edit_dir_add(struct afs_vnode *vnode, } /* Work out how many slots we're going to need. */ - need_slots = round_up(12 + name->len + 1 + 4, AFS_DIR_DIRENT_SIZE); - need_slots /= AFS_DIR_DIRENT_SIZE; + need_slots = afs_dir_calc_slots(name->len); meta_page = kmap(page0); meta = &meta_page->blocks[0]; @@ -393,8 +392,7 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, } /* Work out how many slots we're going to discard. */ - need_slots = round_up(12 + name->len + 1 + 4, AFS_DIR_DIRENT_SIZE); - need_slots /= AFS_DIR_DIRENT_SIZE; + need_slots = afs_dir_calc_slots(name->len); meta_page = kmap(page0); meta = &meta_page->blocks[0]; diff --git a/fs/afs/main.c b/fs/afs/main.c index accdd8970e7c..b2975256dadb 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -193,7 +193,7 @@ static int __init afs_init(void) goto error_cache; #endif - ret = register_pernet_subsys(&afs_net_ops); + ret = register_pernet_device(&afs_net_ops); if (ret < 0) goto error_net; @@ -213,7 +213,7 @@ static int __init afs_init(void) error_proc: afs_fs_exit(); error_fs: - unregister_pernet_subsys(&afs_net_ops); + unregister_pernet_device(&afs_net_ops); error_net: #ifdef CONFIG_AFS_FSCACHE fscache_unregister_netfs(&afs_cache_netfs); @@ -244,7 +244,7 @@ static void __exit afs_exit(void) proc_remove(afs_proc_symlink); afs_fs_exit(); - unregister_pernet_subsys(&afs_net_ops); + unregister_pernet_device(&afs_net_ops); #ifdef CONFIG_AFS_FSCACHE fscache_unregister_netfs(&afs_cache_netfs); #endif diff --git a/fs/afs/xdr_fs.h b/fs/afs/xdr_fs.h index 94f1f398eefa..8ca868164507 100644 --- a/fs/afs/xdr_fs.h +++ b/fs/afs/xdr_fs.h @@ -54,10 +54,16 @@ union afs_xdr_dirent { __be16 hash_next; __be32 vnode; __be32 unique; - u8 name[16]; - u8 overflow[4]; /* if any char of the name (inc - * NUL) reaches here, consume - * the next dirent too */ + u8 name[]; + /* When determining the number of dirent slots needed to + * represent a directory entry, name should be assumed to be 16 + * bytes, due to a now-standardised (mis)calculation, but it is + * in fact 20 bytes in size. afs_dir_calc_slots() should be + * used for this. + * + * For names longer than (16 or) 20 bytes, extra slots should + * be annexed to this one using the extended_name format. + */ } u; u8 extended_name[32]; } __packed; @@ -96,4 +102,15 @@ struct afs_xdr_dir_page { union afs_xdr_dir_block blocks[AFS_DIR_BLOCKS_PER_PAGE]; }; +/* + * Calculate the number of dirent slots required for any given name length. + * The calculation is made assuming the part of the name in the first slot is + * 16 bytes, rather than 20, but this miscalculation is now standardised. + */ +static inline unsigned int afs_dir_calc_slots(size_t name_len) +{ + name_len++; /* NUL-terminated */ + return 1 + ((name_len + 15) / AFS_DIR_DIRENT_SIZE); +} + #endif /* XDR_FS_H */ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 950bc177238a..4c1550b13899 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1495,7 +1495,7 @@ static void fill_note(struct memelfnote *note, const char *name, int type, * fill up all the fields in prstatus from the given task struct, except * registers which need to be filled up separately. */ -static void fill_prstatus(struct elf_prstatus *prstatus, +static void fill_prstatus(struct elf_prstatus_common *prstatus, struct task_struct *p, long signr) { prstatus->pr_info.si_signo = prstatus->pr_cursig = signr; @@ -1717,11 +1717,11 @@ static void do_thread_regset_writeback(struct task_struct *task, } #ifndef PRSTATUS_SIZE -#define PRSTATUS_SIZE(S, R) sizeof(S) +#define PRSTATUS_SIZE sizeof(struct elf_prstatus) #endif #ifndef SET_PR_FPVALID -#define SET_PR_FPVALID(S, V, R) ((S)->pr_fpvalid = (V)) +#define SET_PR_FPVALID(S) ((S)->pr_fpvalid = 1) #endif static int fill_thread_core_info(struct elf_thread_core_info *t, @@ -1729,7 +1729,6 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, long signr, size_t *total) { unsigned int i; - int regset0_size; /* * NT_PRSTATUS is the one special case, because the regset data @@ -1737,14 +1736,12 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, * than being the whole note contents. We fill the reset in here. * We assume that regset 0 is NT_PRSTATUS. */ - fill_prstatus(&t->prstatus, t->task, signr); - regset0_size = regset_get(t->task, &view->regsets[0], + fill_prstatus(&t->prstatus.common, t->task, signr); + regset_get(t->task, &view->regsets[0], sizeof(t->prstatus.pr_reg), &t->prstatus.pr_reg); - if (regset0_size < 0) - return 0; fill_note(&t->notes[0], "CORE", NT_PRSTATUS, - PRSTATUS_SIZE(t->prstatus, regset0_size), &t->prstatus); + PRSTATUS_SIZE, &t->prstatus); *total += notesize(&t->notes[0]); do_thread_regset_writeback(t->task, &view->regsets[0]); @@ -1772,7 +1769,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, continue; if (is_fpreg) - SET_PR_FPVALID(&t->prstatus, 1, regset0_size); + SET_PR_FPVALID(&t->prstatus); fill_note(&t->notes[i], is_fpreg ? "CORE" : "LINUX", note_type, ret, data); @@ -1961,7 +1958,7 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t) struct task_struct *p = t->thread; t->num_notes = 0; - fill_prstatus(&t->prstatus, p, signr); + fill_prstatus(&t->prstatus.common, p, signr); elf_core_copy_task_regs(p, &t->prstatus.pr_reg); fill_note(&t->notes[0], "CORE", NT_PRSTATUS, sizeof(t->prstatus), @@ -2040,7 +2037,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, } /* now collect the dump for the current */ memset(info->prstatus, 0, sizeof(*info->prstatus)); - fill_prstatus(info->prstatus, current, siginfo->si_signo); + fill_prstatus(&info->prstatus->common, current, siginfo->si_signo); elf_core_copy_regs(&info->prstatus->pr_reg, regs); /* Set up header */ diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index be4062b8ba75..03d81a14bcbf 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1191,18 +1191,7 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, struct elf_prstatus_fdpic { - struct elf_siginfo pr_info; /* Info associated with signal */ - short pr_cursig; /* Current signal */ - unsigned long pr_sigpend; /* Set of pending signals */ - unsigned long pr_sighold; /* Set of held signals */ - pid_t pr_pid; - pid_t pr_ppid; - pid_t pr_pgrp; - pid_t pr_sid; - struct __kernel_old_timeval pr_utime; /* User time */ - struct __kernel_old_timeval pr_stime; /* System time */ - struct __kernel_old_timeval pr_cutime; /* Cumulative user time */ - struct __kernel_old_timeval pr_cstime; /* Cumulative system time */ + struct elf_prstatus_common common; elf_gregset_t pr_reg; /* GP registers */ /* When using FDPIC, the loadmap addresses need to be communicated * to GDB in order for GDB to do the necessary relocations. The @@ -1301,7 +1290,7 @@ static inline void fill_note(struct memelfnote *note, const char *name, int type * fill up all the fields in prstatus from the given task struct, except * registers which need to be filled up separately. */ -static void fill_prstatus(struct elf_prstatus_fdpic *prstatus, +static void fill_prstatus(struct elf_prstatus_common *prstatus, struct task_struct *p, long signr) { prstatus->pr_info.si_signo = prstatus->pr_cursig = signr; @@ -1332,9 +1321,6 @@ static void fill_prstatus(struct elf_prstatus_fdpic *prstatus, } prstatus->pr_cutime = ns_to_kernel_old_timeval(p->signal->cutime); prstatus->pr_cstime = ns_to_kernel_old_timeval(p->signal->cstime); - - prstatus->pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap; - prstatus->pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap; } static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, @@ -1405,7 +1391,9 @@ static struct elf_thread_status *elf_dump_thread_status(long signr, struct task_ if (!t) return t; - fill_prstatus(&t->prstatus, p, signr); + fill_prstatus(&t->prstatus.common, p, signr); + t->prstatus.pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap; + t->prstatus.pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap; regset_get(p, &view->regsets[0], sizeof(t->prstatus.pr_reg), &t->prstatus.pr_reg); diff --git a/fs/block_dev.c b/fs/block_dev.c index 9e56ee1f2652..235b5042672e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1,9 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * linux/fs/block_dev.c - * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE + * Copyright (C) 2016 - 2020 Christoph Hellwig */ #include <linux/init.h> @@ -131,7 +130,15 @@ EXPORT_SYMBOL(truncate_bdev_range); static void set_init_blocksize(struct block_device *bdev) { - bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev)); + unsigned int bsize = bdev_logical_block_size(bdev); + loff_t size = i_size_read(bdev->bd_inode); + + while (bsize < PAGE_SIZE) { + if (size & bsize) + break; + bsize <<= 1; + } + bdev->bd_inode->i_blkbits = blksize_bits(bsize); } int set_blocksize(struct block_device *bdev, int size) @@ -606,6 +613,8 @@ int thaw_bdev(struct block_device *bdev) error = thaw_super(sb); if (error) bdev->bd_fsfreeze_count++; + else + bdev->bd_fsfreeze_sb = NULL; out: mutex_unlock(&bdev->bd_fsfreeze_mutex); return error; @@ -775,8 +784,11 @@ static struct kmem_cache * bdev_cachep __read_mostly; static struct inode *bdev_alloc_inode(struct super_block *sb) { struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL); + if (!ei) return NULL; + memset(&ei->bdev, 0, sizeof(ei->bdev)); + ei->bdev.bd_bdi = &noop_backing_dev_info; return &ei->vfs_inode; } @@ -870,14 +882,12 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) mapping_set_gfp_mask(&inode->i_data, GFP_USER); bdev = I_BDEV(inode); - memset(bdev, 0, sizeof(*bdev)); mutex_init(&bdev->bd_mutex); mutex_init(&bdev->bd_fsfreeze_mutex); spin_lock_init(&bdev->bd_size_lock); bdev->bd_disk = disk; bdev->bd_partno = partno; bdev->bd_inode = inode; - bdev->bd_bdi = &noop_backing_dev_info; #ifdef CONFIG_SYSFS INIT_LIST_HEAD(&bdev->bd_holder_disks); #endif @@ -1056,7 +1066,6 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder) /** * bd_abort_claiming - abort claiming of a block device * @bdev: block device of interest - * @whole: whole block device * @holder: holder that has claimed @bdev * * Abort claiming of a block device when the exclusive open failed. This can be @@ -1829,6 +1838,7 @@ const struct file_operations def_blk_fops = { /** * lookup_bdev - lookup a struct block_device by name * @pathname: special file representing the block device + * @dev: return value of the block device's dev_t * * Get a reference to the blockdevice at @pathname in the current * namespace if possible and return it. Return ERR_PTR(error) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 02d7d7b2563b..9cadacf3ec27 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -3117,7 +3117,7 @@ void btrfs_backref_error_cleanup(struct btrfs_backref_cache *cache, list_del_init(&lower->list); if (lower == node) node = NULL; - btrfs_backref_free_node(cache, lower); + btrfs_backref_drop_node(cache, lower); } btrfs_backref_cleanup_node(cache, node); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 52f2198d44c9..48ebc106a606 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -673,7 +673,15 @@ static noinline void caching_thread(struct btrfs_work *work) wake_up(&caching_ctl->wait); } - if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) + /* + * If we are in the transaction that populated the free space tree we + * can't actually cache from the free space tree as our commit root and + * real root are the same, so we could change the contents of the blocks + * while caching. Instead do the slow caching in this case, and after + * the transaction has committed we will be safe. + */ + if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !(test_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags))) ret = load_free_space_tree(caching_ctl); else ret = load_extent_tree_free(caching_ctl); @@ -2669,7 +2677,8 @@ again: * Go through delayed refs for all the stuff we've just kicked off * and then loop back (just once) */ - ret = btrfs_run_delayed_refs(trans, 0); + if (!ret) + ret = btrfs_run_delayed_refs(trans, 0); if (!ret && loops == 0) { loops++; spin_lock(&cur_trans->dirty_bgs_lock); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 555cbcef6585..d9bf53d9ff90 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -42,6 +42,15 @@ enum { * to an inode. */ BTRFS_INODE_NO_XATTRS, + /* + * Set when we are in a context where we need to start a transaction and + * have dirty pages with the respective file range locked. This is to + * ensure that when reserving space for the transaction, if we are low + * on available space and need to flush delalloc, we will not flush + * delalloc for this inode, because that could result in a deadlock (on + * the file range, inode's io_tree). + */ + BTRFS_INODE_NO_DELALLOC_FLUSH, }; /* in memory btrfs inode */ diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 07810891e204..cc89b63d65a4 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2555,8 +2555,14 @@ out: * @p: Holds all btree nodes along the search path * @root: The root node of the tree * @key: The key we are looking for - * @ins_len: Indicates purpose of search, for inserts it is 1, for - * deletions it's -1. 0 for plain searches + * @ins_len: Indicates purpose of search: + * >0 for inserts it's size of item inserted (*) + * <0 for deletions + * 0 for plain searches, not modifying the tree + * + * (*) If size of item inserted doesn't include + * sizeof(struct btrfs_item), then p->search_for_extension must + * be set. * @cow: boolean should CoW operations be performed. Must always be 1 * when modifying the tree. * @@ -2717,6 +2723,20 @@ cow_done: if (level == 0) { p->slots[level] = slot; + /* + * Item key already exists. In this case, if we are + * allowed to insert the item (for example, in dir_item + * case, item key collision is allowed), it will be + * merged with the original item. Only the item size + * grows, no new btrfs item will be added. If + * search_for_extension is not set, ins_len already + * accounts the size btrfs_item, deduct it here so leaf + * space check will be correct. + */ + if (ret == 0 && ins_len > 0 && !p->search_for_extension) { + ASSERT(ins_len >= sizeof(struct btrfs_item)); + ins_len -= sizeof(struct btrfs_item); + } if (ins_len > 0 && btrfs_leaf_free_space(b) < ins_len) { if (write_lock_level < 1) { diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 1d3c1e479f3d..4debdbdde2ab 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -131,6 +131,8 @@ enum { * defrag */ BTRFS_FS_STATE_REMOUNTING, + /* Filesystem in RO mode */ + BTRFS_FS_STATE_RO, /* Track if a transaction abort has been reported on this filesystem */ BTRFS_FS_STATE_TRANS_ABORTED, /* @@ -367,6 +369,12 @@ struct btrfs_path { unsigned int search_commit_root:1; unsigned int need_commit_sem:1; unsigned int skip_release_on_error:1; + /* + * Indicate that new item (btrfs_search_slot) is extending already + * existing item and ins_len contains only the data size and not item + * header (ie. sizeof(struct btrfs_item) is not included). + */ + unsigned int search_for_extension:1; }; #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \ sizeof(struct btrfs_item)) @@ -555,6 +563,9 @@ enum { /* Indicate that we need to cleanup space cache v1 */ BTRFS_FS_CLEANUP_SPACE_CACHE_V1, + + /* Indicate that we can't trust the free space tree for caching yet */ + BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, }; /* @@ -2885,10 +2896,26 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info) * If we remount the fs to be R/O or umount the fs, the cleaner needn't do * anything except sleeping. This function is used to check the status of * the fs. + * We check for BTRFS_FS_STATE_RO to avoid races with a concurrent remount, + * since setting and checking for SB_RDONLY in the superblock's flags is not + * atomic. */ static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info) { - return fs_info->sb->s_flags & SB_RDONLY || btrfs_fs_closing(fs_info); + return test_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state) || + btrfs_fs_closing(fs_info); +} + +static inline void btrfs_set_sb_rdonly(struct super_block *sb) +{ + sb->s_flags |= SB_RDONLY; + set_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state); +} + +static inline void btrfs_clear_sb_rdonly(struct super_block *sb) +{ + sb->s_flags &= ~SB_RDONLY; + clear_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state); } /* tree mod log functions from ctree.c */ @@ -3073,7 +3100,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, u32 min_type); int btrfs_start_delalloc_snapshot(struct btrfs_root *root); -int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr); +int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr, + bool in_reclaim_context); int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index a98e33f232d5..324f646d6e5e 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -715,7 +715,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, * flush all outstanding I/O and inode extent mappings before the * copy operation is declared as being finished */ - ret = btrfs_start_delalloc_roots(fs_info, U64_MAX); + ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false); if (ret) { mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index 1db966bf85b2..2b8383d41144 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -199,16 +199,15 @@ static struct btrfs_block_group *find_next_block_group( static struct btrfs_block_group *peek_discard_list( struct btrfs_discard_ctl *discard_ctl, enum btrfs_discard_state *discard_state, - int *discard_index) + int *discard_index, u64 now) { struct btrfs_block_group *block_group; - const u64 now = ktime_get_ns(); spin_lock(&discard_ctl->lock); again: block_group = find_next_block_group(discard_ctl, now); - if (block_group && now > block_group->discard_eligible_time) { + if (block_group && now >= block_group->discard_eligible_time) { if (block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED && block_group->used != 0) { if (btrfs_is_block_group_data_only(block_group)) @@ -222,12 +221,11 @@ again: block_group->discard_state = BTRFS_DISCARD_EXTENTS; } discard_ctl->block_group = block_group; + } + if (block_group) { *discard_state = block_group->discard_state; *discard_index = block_group->discard_index; - } else { - block_group = NULL; } - spin_unlock(&discard_ctl->lock); return block_group; @@ -330,28 +328,15 @@ void btrfs_discard_queue_work(struct btrfs_discard_ctl *discard_ctl, btrfs_discard_schedule_work(discard_ctl, false); } -/** - * btrfs_discard_schedule_work - responsible for scheduling the discard work - * @discard_ctl: discard control - * @override: override the current timer - * - * Discards are issued by a delayed workqueue item. @override is used to - * update the current delay as the baseline delay interval is reevaluated on - * transaction commit. This is also maxed with any other rate limit. - */ -void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, - bool override) +static void __btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, + u64 now, bool override) { struct btrfs_block_group *block_group; - const u64 now = ktime_get_ns(); - - spin_lock(&discard_ctl->lock); if (!btrfs_run_discard_work(discard_ctl)) - goto out; - + return; if (!override && delayed_work_pending(&discard_ctl->work)) - goto out; + return; block_group = find_next_block_group(discard_ctl, now); if (block_group) { @@ -393,7 +378,24 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, mod_delayed_work(discard_ctl->discard_workers, &discard_ctl->work, nsecs_to_jiffies(delay)); } -out: +} + +/* + * btrfs_discard_schedule_work - responsible for scheduling the discard work + * @discard_ctl: discard control + * @override: override the current timer + * + * Discards are issued by a delayed workqueue item. @override is used to + * update the current delay as the baseline delay interval is reevaluated on + * transaction commit. This is also maxed with any other rate limit. + */ +void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, + bool override) +{ + const u64 now = ktime_get_ns(); + + spin_lock(&discard_ctl->lock); + __btrfs_discard_schedule_work(discard_ctl, now, override); spin_unlock(&discard_ctl->lock); } @@ -438,13 +440,18 @@ static void btrfs_discard_workfn(struct work_struct *work) int discard_index = 0; u64 trimmed = 0; u64 minlen = 0; + u64 now = ktime_get_ns(); discard_ctl = container_of(work, struct btrfs_discard_ctl, work.work); block_group = peek_discard_list(discard_ctl, &discard_state, - &discard_index); + &discard_index, now); if (!block_group || !btrfs_run_discard_work(discard_ctl)) return; + if (now < block_group->discard_eligible_time) { + btrfs_discard_schedule_work(discard_ctl, false); + return; + } /* Perform discarding */ minlen = discard_minlen[discard_index]; @@ -474,13 +481,6 @@ static void btrfs_discard_workfn(struct work_struct *work) discard_ctl->discard_extent_bytes += trimmed; } - /* - * Updated without locks as this is inside the workfn and nothing else - * is reading the values - */ - discard_ctl->prev_discard = trimmed; - discard_ctl->prev_discard_time = ktime_get_ns(); - /* Determine next steps for a block_group */ if (block_group->discard_cursor >= btrfs_block_group_end(block_group)) { if (discard_state == BTRFS_DISCARD_BITMAPS) { @@ -496,11 +496,13 @@ static void btrfs_discard_workfn(struct work_struct *work) } } + now = ktime_get_ns(); spin_lock(&discard_ctl->lock); + discard_ctl->prev_discard = trimmed; + discard_ctl->prev_discard_time = now; discard_ctl->block_group = NULL; + __btrfs_discard_schedule_work(discard_ctl, now, false); spin_unlock(&discard_ctl->lock); - - btrfs_discard_schedule_work(discard_ctl, false); } /** diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 765deefda92b..07a2b4f69b10 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1457,7 +1457,7 @@ void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info) root = list_first_entry(&fs_info->allocated_roots, struct btrfs_root, leak_list); btrfs_err(fs_info, "leaked root %s refcount %d", - btrfs_root_name(root->root_key.objectid, buf), + btrfs_root_name(&root->root_key, buf), refcount_read(&root->refs)); while (refcount_read(&root->refs) > 1) btrfs_put_root(root); @@ -1729,7 +1729,7 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(fs_info); sleep: - clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); + clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); if (kthread_should_park()) kthread_parkme(); if (kthread_should_stop()) @@ -2830,6 +2830,9 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block return -ENOMEM; btrfs_init_delayed_root(fs_info->delayed_root); + if (sb_rdonly(sb)) + set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state); + return btrfs_alloc_stripe_hash_table(fs_info); } @@ -2969,6 +2972,7 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) } } + ret = btrfs_find_orphan_roots(fs_info); out: return ret; } @@ -3040,6 +3044,8 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_alloc; } + fs_info->csum_size = btrfs_super_csum_size(disk_super); + ret = btrfs_init_csum_hash(fs_info, csum_type); if (ret) { err = ret; @@ -3157,7 +3163,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device fs_info->nodesize = nodesize; fs_info->sectorsize = sectorsize; fs_info->sectorsize_bits = ilog2(sectorsize); - fs_info->csum_size = btrfs_super_csum_size(disk_super); fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size; fs_info->stripesize = stripesize; @@ -3383,10 +3388,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device } } - ret = btrfs_find_orphan_roots(fs_info); - if (ret) - goto fail_qgroup; - fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true); if (IS_ERR(fs_info->fs_root)) { err = PTR_ERR(fs_info->fs_root); @@ -4181,6 +4182,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) invalidate_inode_pages2(fs_info->btree_inode->i_mapping); btrfs_stop_all_workers(fs_info); + /* We shouldn't have any transaction open at this point */ + ASSERT(list_empty(&fs_info->trans_list)); + clear_bit(BTRFS_FS_OPEN, &fs_info->flags); free_root_pointers(fs_info, true); btrfs_free_fs_roots(fs_info); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 56ea380f5a17..0c335dae5af7 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -844,6 +844,7 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans, want = extent_ref_type(parent, owner); if (insert) { extra_size = btrfs_extent_inline_ref_size(want); + path->search_for_extension = 1; path->keep_locks = 1; } else extra_size = -1; @@ -996,6 +997,7 @@ again: out: if (insert) { path->keep_locks = 0; + path->search_for_extension = 0; btrfs_unlock_up_safe(path, 1); } return err; @@ -2600,8 +2602,6 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, struct btrfs_block_group *cache; int ret; - btrfs_add_excluded_extent(trans->fs_info, bytenr, num_bytes); - cache = btrfs_lookup_block_group(trans->fs_info, bytenr); if (!cache) return -EINVAL; @@ -2613,11 +2613,19 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, * the pinned extents. */ 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); + if (ret) + goto out; pin_down_extent(trans, cache, bytenr, num_bytes, 0); /* remove us from the free space cache (if we're there at all) */ ret = btrfs_remove_free_space(cache, bytenr, num_bytes); +out: btrfs_put_block_group(cache); return ret; } @@ -2627,50 +2635,22 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info, { int ret; struct btrfs_block_group *block_group; - struct btrfs_caching_control *caching_ctl; block_group = btrfs_lookup_block_group(fs_info, start); if (!block_group) return -EINVAL; - btrfs_cache_block_group(block_group, 0); - caching_ctl = btrfs_get_caching_control(block_group); - - if (!caching_ctl) { - /* Logic error */ - BUG_ON(!btrfs_block_group_done(block_group)); - ret = btrfs_remove_free_space(block_group, start, num_bytes); - } else { - /* - * We must wait for v1 caching to finish, otherwise we may not - * remove our space. - */ - btrfs_wait_space_cache_v1_finished(block_group, caching_ctl); - mutex_lock(&caching_ctl->mutex); - - if (start >= caching_ctl->progress) { - ret = btrfs_add_excluded_extent(fs_info, start, - num_bytes); - } else if (start + num_bytes <= caching_ctl->progress) { - ret = btrfs_remove_free_space(block_group, - start, num_bytes); - } else { - num_bytes = caching_ctl->progress - start; - ret = btrfs_remove_free_space(block_group, - start, num_bytes); - if (ret) - goto out_lock; + 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); + if (ret) + goto out; - num_bytes = (start + num_bytes) - - caching_ctl->progress; - start = caching_ctl->progress; - ret = btrfs_add_excluded_extent(fs_info, start, - num_bytes); - } -out_lock: - mutex_unlock(&caching_ctl->mutex); - btrfs_put_caching_control(caching_ctl); - } + ret = btrfs_remove_free_space(block_group, start, num_bytes); +out: btrfs_put_block_group(block_group); return ret; } @@ -2861,9 +2841,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; } - if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) - clear_extent_bits(&fs_info->excluded_extents, start, - end, EXTENT_UPTODATE); if (btrfs_test_opt(fs_info, DISCARD_SYNC)) ret = btrfs_discard_extent(fs_info, start, @@ -5547,7 +5524,15 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) goto out_free; } - trans = btrfs_start_transaction(tree_root, 0); + /* + * Use join to avoid potential EINTR from transaction + * start. See wait_reserve_ticket and the whole + * reservation callchain. + */ + if (for_reloc) + trans = btrfs_join_transaction(tree_root); + else + trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); goto out_free; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 6e3b72e63e42..c9cee458e001 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -676,9 +676,7 @@ alloc_extent_state_atomic(struct extent_state *prealloc) static void extent_io_tree_panic(struct extent_io_tree *tree, int err) { - struct inode *inode = tree->private_data; - - btrfs_panic(btrfs_sb(inode->i_sb), err, + btrfs_panic(tree->fs_info, err, "locking error: extent tree was modified by another thread while locked"); } diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 1545c22ef280..6ccfc019ad90 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -1016,8 +1016,10 @@ again: } btrfs_release_path(path); + path->search_for_extension = 1; ret = btrfs_search_slot(trans, root, &file_key, path, csum_size, 1); + path->search_for_extension = 0; if (ret < 0) goto out; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index e33a65bd9a0c..a33bca94d133 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1150,6 +1150,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) return PTR_ERR(trans); set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); free_space_root = btrfs_create_tree(trans, BTRFS_FREE_SPACE_TREE_OBJECTID); if (IS_ERR(free_space_root)) { @@ -1171,11 +1172,18 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + ret = btrfs_commit_transaction(trans); - return btrfs_commit_transaction(trans); + /* + * Now that we've committed the transaction any reading of our commit + * root will be safe, so we can cache from the free space tree now. + */ + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); + return ret; abort: clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 8e23780acfae..a8e0a6b038d3 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9390,7 +9390,9 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode * some fairly slow code that needs optimization. This walks the list * of all the inodes with pending delalloc and forces them to disk. */ -static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot) +static int start_delalloc_inodes(struct btrfs_root *root, + struct writeback_control *wbc, bool snapshot, + bool in_reclaim_context) { struct btrfs_inode *binode; struct inode *inode; @@ -9398,6 +9400,7 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot struct list_head works; struct list_head splice; int ret = 0; + bool full_flush = wbc->nr_to_write == LONG_MAX; INIT_LIST_HEAD(&works); INIT_LIST_HEAD(&splice); @@ -9411,6 +9414,11 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot list_move_tail(&binode->delalloc_inodes, &root->delalloc_inodes); + + if (in_reclaim_context && + test_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &binode->runtime_flags)) + continue; + inode = igrab(&binode->vfs_inode); if (!inode) { cond_resched_lock(&root->delalloc_lock); @@ -9421,18 +9429,24 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot if (snapshot) set_bit(BTRFS_INODE_SNAPSHOT_FLUSH, &binode->runtime_flags); - work = btrfs_alloc_delalloc_work(inode); - if (!work) { - iput(inode); - ret = -ENOMEM; - goto out; - } - list_add_tail(&work->list, &works); - btrfs_queue_work(root->fs_info->flush_workers, - &work->work); - if (*nr != U64_MAX) { - (*nr)--; - if (*nr == 0) + if (full_flush) { + work = btrfs_alloc_delalloc_work(inode); + if (!work) { + iput(inode); + ret = -ENOMEM; + goto out; + } + list_add_tail(&work->list, &works); + btrfs_queue_work(root->fs_info->flush_workers, + &work->work); + } else { + ret = sync_inode(inode, wbc); + if (!ret && + test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, + &BTRFS_I(inode)->runtime_flags)) + ret = sync_inode(inode, wbc); + btrfs_add_delayed_iput(inode); + if (ret || wbc->nr_to_write <= 0) goto out; } cond_resched(); @@ -9458,17 +9472,29 @@ out: int btrfs_start_delalloc_snapshot(struct btrfs_root *root) { + struct writeback_control wbc = { + .nr_to_write = LONG_MAX, + .sync_mode = WB_SYNC_NONE, + .range_start = 0, + .range_end = LLONG_MAX, + }; struct btrfs_fs_info *fs_info = root->fs_info; - u64 nr = U64_MAX; if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) return -EROFS; - return start_delalloc_inodes(root, &nr, true); + return start_delalloc_inodes(root, &wbc, true, false); } -int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr) +int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr, + bool in_reclaim_context) { + struct writeback_control wbc = { + .nr_to_write = (nr == U64_MAX) ? LONG_MAX : (unsigned long)nr, + .sync_mode = WB_SYNC_NONE, + .range_start = 0, + .range_end = LLONG_MAX, + }; struct btrfs_root *root; struct list_head splice; int ret; @@ -9482,6 +9508,13 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr) spin_lock(&fs_info->delalloc_root_lock); list_splice_init(&fs_info->delalloc_roots, &splice); while (!list_empty(&splice) && nr) { + /* + * Reset nr_to_write here so we know that we're doing a full + * flush. + */ + if (nr == U64_MAX) + wbc.nr_to_write = LONG_MAX; + root = list_first_entry(&splice, struct btrfs_root, delalloc_root); root = btrfs_grab_root(root); @@ -9490,9 +9523,9 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr) &fs_info->delalloc_roots); spin_unlock(&fs_info->delalloc_root_lock); - ret = start_delalloc_inodes(root, &nr, false); + ret = start_delalloc_inodes(root, &wbc, false, in_reclaim_context); btrfs_put_root(root); - if (ret < 0) + if (ret < 0 || wbc.nr_to_write <= 0) goto out; spin_lock(&fs_info->delalloc_root_lock); } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 703212ff50a5..dde49a791f3e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4951,7 +4951,7 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_SYNC: { int ret; - ret = btrfs_start_delalloc_roots(fs_info, U64_MAX); + ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false); if (ret) return ret; ret = btrfs_sync_fs(inode->i_sb, 1); diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index fe5e0026129d..aae1027bd76a 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -26,22 +26,22 @@ static const struct root_name_map root_map[] = { { BTRFS_DATA_RELOC_TREE_OBJECTID, "DATA_RELOC_TREE" }, }; -const char *btrfs_root_name(u64 objectid, char *buf) +const char *btrfs_root_name(const struct btrfs_key *key, char *buf) { int i; - if (objectid == BTRFS_TREE_RELOC_OBJECTID) { + if (key->objectid == BTRFS_TREE_RELOC_OBJECTID) { snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, - "TREE_RELOC offset=%llu", objectid); + "TREE_RELOC offset=%llu", key->offset); return buf; } for (i = 0; i < ARRAY_SIZE(root_map); i++) { - if (root_map[i].id == objectid) + if (root_map[i].id == key->objectid) return root_map[i].name; } - snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", objectid); + snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", key->objectid); return buf; } diff --git a/fs/btrfs/print-tree.h b/fs/btrfs/print-tree.h index 78b99385a503..8c3e9319ec4e 100644 --- a/fs/btrfs/print-tree.h +++ b/fs/btrfs/print-tree.h @@ -11,6 +11,6 @@ void btrfs_print_leaf(struct extent_buffer *l); void btrfs_print_tree(struct extent_buffer *c, bool follow); -const char *btrfs_root_name(u64 objectid, char *buf); +const char *btrfs_root_name(const struct btrfs_key *key, char *buf); #endif diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index fe3046007f52..808370ada888 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3190,6 +3190,12 @@ out: return ret; } +static bool rescan_should_stop(struct btrfs_fs_info *fs_info) +{ + return btrfs_fs_closing(fs_info) || + test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); +} + static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) { struct btrfs_fs_info *fs_info = container_of(work, struct btrfs_fs_info, @@ -3198,6 +3204,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) struct btrfs_trans_handle *trans = NULL; int err = -ENOMEM; int ret = 0; + bool stopped = false; path = btrfs_alloc_path(); if (!path) @@ -3210,7 +3217,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) path->skip_locking = 1; err = 0; - while (!err && !btrfs_fs_closing(fs_info)) { + while (!err && !(stopped = rescan_should_stop(fs_info))) { trans = btrfs_start_transaction(fs_info->fs_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -3253,7 +3260,7 @@ out: } mutex_lock(&fs_info->qgroup_rescan_lock); - if (!btrfs_fs_closing(fs_info)) + if (!stopped) fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; if (trans) { ret = update_qgroup_status_item(trans); @@ -3272,7 +3279,7 @@ out: btrfs_end_transaction(trans); - if (btrfs_fs_closing(fs_info)) { + if (stopped) { btrfs_info(fs_info, "qgroup scan paused"); } else if (err >= 0) { btrfs_info(fs_info, "qgroup scan completed%s", @@ -3531,16 +3538,6 @@ static int try_flush_qgroup(struct btrfs_root *root) bool can_commit = true; /* - * We don't want to run flush again and again, so if there is a running - * one, we won't try to start a new flush, but exit directly. - */ - if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) { - wait_event(root->qgroup_flush_wait, - !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)); - return 0; - } - - /* * If current process holds a transaction, we shouldn't flush, as we * assume all space reservation happens before a transaction handle is * held. @@ -3554,6 +3551,26 @@ static int try_flush_qgroup(struct btrfs_root *root) current->journal_info != BTRFS_SEND_TRANS_STUB) can_commit = false; + /* + * We don't want to run flush again and again, so if there is a running + * one, we won't try to start a new flush, but exit directly. + */ + if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) { + /* + * We are already holding a transaction, thus we can block other + * threads from flushing. So exit right now. This increases + * the chance of EDQUOT for heavy load and near limit cases. + * But we can argue that if we're already near limit, EDQUOT is + * unavoidable anyway. + */ + if (!can_commit) + return 0; + + wait_event(root->qgroup_flush_wait, + !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)); + return 0; + } + ret = btrfs_start_delalloc_snapshot(root); if (ret < 0) goto out; diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index ab80896315be..b03e7891394e 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -89,6 +89,19 @@ static int copy_inline_to_page(struct btrfs_inode *inode, if (ret) goto out_unlock; + /* + * After dirtying the page our caller will need to start a transaction, + * and if we are low on metadata free space, that can cause flushing of + * delalloc for all inodes in order to get metadata space released. + * However we are holding the range locked for the whole duration of + * the clone/dedupe operation, so we may deadlock if that happens and no + * other task releases enough space. So mark this inode as not being + * possible to flush to avoid such deadlock. We will clear that flag + * when we finish cloning all extents, since a transaction is started + * after finding each extent to clone. + */ + set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags); + if (comp_type == BTRFS_COMPRESS_NONE) { char *map; @@ -549,6 +562,8 @@ process_slot: out: btrfs_free_path(path); kvfree(buf); + clear_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &BTRFS_I(inode)->runtime_flags); + return ret; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 19b7db8b2117..df63ef64c5c0 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2975,11 +2975,16 @@ static int delete_v1_space_cache(struct extent_buffer *leaf, return 0; for (i = 0; i < btrfs_header_nritems(leaf); i++) { + u8 type; + btrfs_item_key_to_cpu(leaf, &key, i); if (key.type != BTRFS_EXTENT_DATA_KEY) continue; ei = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item); - if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_REG && + type = btrfs_file_extent_type(leaf, ei); + + if ((type == BTRFS_FILE_EXTENT_REG || + type == BTRFS_FILE_EXTENT_PREALLOC) && btrfs_file_extent_disk_bytenr(leaf, ei) == data_bytenr) { found = true; space_cache_ino = key.objectid; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index d719a2755a40..78a35374d492 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -236,6 +236,7 @@ struct waiting_dir_move { * after this directory is moved, we can try to rmdir the ino rmdir_ino. */ u64 rmdir_ino; + u64 rmdir_gen; bool orphanized; }; @@ -316,7 +317,7 @@ static int is_waiting_for_move(struct send_ctx *sctx, u64 ino); static struct waiting_dir_move * get_waiting_dir_move(struct send_ctx *sctx, u64 ino); -static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino); +static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen); static int need_send_hole(struct send_ctx *sctx) { @@ -2299,7 +2300,7 @@ static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen, fs_path_reset(name); - if (is_waiting_for_rm(sctx, ino)) { + if (is_waiting_for_rm(sctx, ino, gen)) { ret = gen_unique_name(sctx, ino, gen, name); if (ret < 0) goto out; @@ -2858,8 +2859,8 @@ out: return ret; } -static struct orphan_dir_info * -add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) +static struct orphan_dir_info *add_orphan_dir_info(struct send_ctx *sctx, + u64 dir_ino, u64 dir_gen) { struct rb_node **p = &sctx->orphan_dirs.rb_node; struct rb_node *parent = NULL; @@ -2868,20 +2869,23 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) while (*p) { parent = *p; entry = rb_entry(parent, struct orphan_dir_info, node); - if (dir_ino < entry->ino) { + if (dir_ino < entry->ino) p = &(*p)->rb_left; - } else if (dir_ino > entry->ino) { + else if (dir_ino > entry->ino) p = &(*p)->rb_right; - } else { + else if (dir_gen < entry->gen) + p = &(*p)->rb_left; + else if (dir_gen > entry->gen) + p = &(*p)->rb_right; + else return entry; - } } odi = kmalloc(sizeof(*odi), GFP_KERNEL); if (!odi) return ERR_PTR(-ENOMEM); odi->ino = dir_ino; - odi->gen = 0; + odi->gen = dir_gen; odi->last_dir_index_offset = 0; rb_link_node(&odi->node, parent, p); @@ -2889,8 +2893,8 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) return odi; } -static struct orphan_dir_info * -get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) +static struct orphan_dir_info *get_orphan_dir_info(struct send_ctx *sctx, + u64 dir_ino, u64 gen) { struct rb_node *n = sctx->orphan_dirs.rb_node; struct orphan_dir_info *entry; @@ -2901,15 +2905,19 @@ get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) n = n->rb_left; else if (dir_ino > entry->ino) n = n->rb_right; + else if (gen < entry->gen) + n = n->rb_left; + else if (gen > entry->gen) + n = n->rb_right; else return entry; } return NULL; } -static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino) +static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen) { - struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino); + struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino, gen); return odi != NULL; } @@ -2954,7 +2962,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, key.type = BTRFS_DIR_INDEX_KEY; key.offset = 0; - odi = get_orphan_dir_info(sctx, dir); + odi = get_orphan_dir_info(sctx, dir, dir_gen); if (odi) key.offset = odi->last_dir_index_offset; @@ -2985,7 +2993,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, dm = get_waiting_dir_move(sctx, loc.objectid); if (dm) { - odi = add_orphan_dir_info(sctx, dir); + odi = add_orphan_dir_info(sctx, dir, dir_gen); if (IS_ERR(odi)) { ret = PTR_ERR(odi); goto out; @@ -2993,12 +3001,13 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, odi->gen = dir_gen; odi->last_dir_index_offset = found_key.offset; dm->rmdir_ino = dir; + dm->rmdir_gen = dir_gen; ret = 0; goto out; } if (loc.objectid > send_progress) { - odi = add_orphan_dir_info(sctx, dir); + odi = add_orphan_dir_info(sctx, dir, dir_gen); if (IS_ERR(odi)) { ret = PTR_ERR(odi); goto out; @@ -3038,6 +3047,7 @@ static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino, bool orphanized) return -ENOMEM; dm->ino = ino; dm->rmdir_ino = 0; + dm->rmdir_gen = 0; dm->orphanized = orphanized; while (*p) { @@ -3183,7 +3193,7 @@ static int path_loop(struct send_ctx *sctx, struct fs_path *name, while (ino != BTRFS_FIRST_FREE_OBJECTID) { fs_path_reset(name); - if (is_waiting_for_rm(sctx, ino)) + if (is_waiting_for_rm(sctx, ino, gen)) break; if (is_waiting_for_move(sctx, ino)) { if (*ancestor_ino == 0) @@ -3223,6 +3233,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) u64 parent_ino, parent_gen; struct waiting_dir_move *dm = NULL; u64 rmdir_ino = 0; + u64 rmdir_gen; u64 ancestor; bool is_orphan; int ret; @@ -3237,6 +3248,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) dm = get_waiting_dir_move(sctx, pm->ino); ASSERT(dm); rmdir_ino = dm->rmdir_ino; + rmdir_gen = dm->rmdir_gen; is_orphan = dm->orphanized; free_waiting_dir_move(sctx, dm); @@ -3273,6 +3285,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) dm = get_waiting_dir_move(sctx, pm->ino); ASSERT(dm); dm->rmdir_ino = rmdir_ino; + dm->rmdir_gen = rmdir_gen; } goto out; } @@ -3291,7 +3304,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) struct orphan_dir_info *odi; u64 gen; - odi = get_orphan_dir_info(sctx, rmdir_ino); + odi = get_orphan_dir_info(sctx, rmdir_ino, rmdir_gen); if (!odi) { /* already deleted */ goto finish; @@ -5499,6 +5512,21 @@ static int clone_range(struct send_ctx *sctx, break; offset += clone_len; clone_root->offset += clone_len; + + /* + * If we are cloning from the file we are currently processing, + * and using the send root as the clone root, we must stop once + * the current clone offset reaches the current eof of the file + * at the receiver, otherwise we would issue an invalid clone + * operation (source range going beyond eof) and cause the + * receiver to fail. So if we reach the current eof, bail out + * and fallback to a regular write. + */ + if (clone_root->root == sctx->send_root && + clone_root->ino == sctx->cur_ino && + clone_root->offset >= sctx->cur_inode_next_write_offset) + break; + data_offset += clone_len; next: path->slots[0]++; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 64099565ab8f..e8347461c8dd 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -532,7 +532,9 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, loops = 0; while ((delalloc_bytes || dio_bytes) && loops < 3) { - btrfs_start_delalloc_roots(fs_info, items); + u64 nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT; + + btrfs_start_delalloc_roots(fs_info, nr_pages, true); loops++; if (wait_ordered && !trans) { diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 022f20810089..12d7d3be7cd4 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -175,7 +175,7 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function btrfs_discard_stop(fs_info); /* btrfs handle error by forcing the filesystem readonly */ - sb->s_flags |= SB_RDONLY; + btrfs_set_sb_rdonly(sb); btrfs_info(fs_info, "forced readonly"); /* * Note that a running device replace operation is not canceled here @@ -1953,7 +1953,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) /* avoid complains from lockdep et al. */ up(&fs_info->uuid_tree_rescan_sem); - sb->s_flags |= SB_RDONLY; + btrfs_set_sb_rdonly(sb); /* * Setting SB_RDONLY will put the cleaner thread to @@ -1964,10 +1964,42 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) */ btrfs_delete_unused_bgs(fs_info); + /* + * The cleaner task could be already running before we set the + * flag BTRFS_FS_STATE_RO (and SB_RDONLY in the superblock). + * We must make sure that after we finish the remount, i.e. after + * we call btrfs_commit_super(), the cleaner can no longer start + * a transaction - either because it was dropping a dead root, + * running delayed iputs or deleting an unused block group (the + * cleaner picked a block group from the list of unused block + * groups before we were able to in the previous call to + * btrfs_delete_unused_bgs()). + */ + wait_on_bit(&fs_info->flags, BTRFS_FS_CLEANER_RUNNING, + TASK_UNINTERRUPTIBLE); + + /* + * We've set the superblock to RO mode, so we might have made + * the cleaner task sleep without running all pending delayed + * iputs. Go through all the delayed iputs here, so that if an + * unmount happens without remounting RW we don't end up at + * finishing close_ctree() with a non-empty list of delayed + * iputs. + */ + btrfs_run_delayed_iputs(fs_info); + btrfs_dev_replace_suspend_for_unmount(fs_info); btrfs_scrub_cancel(fs_info); btrfs_pause_balance(fs_info); + /* + * Pause the qgroup rescan worker if it is running. We don't want + * it to be still running after we are in RO mode, as after that, + * by the time we unmount, it might have left a transaction open, + * so we would leak the transaction and/or crash. + */ + btrfs_qgroup_wait_for_completion(fs_info, false); + ret = btrfs_commit_super(fs_info); if (ret) goto restore; @@ -2006,7 +2038,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; - sb->s_flags &= ~SB_RDONLY; + btrfs_clear_sb_rdonly(sb); set_bit(BTRFS_FS_OPEN, &fs_info->flags); } @@ -2028,6 +2060,8 @@ restore: /* We've hit an error - don't reset SB_RDONLY */ if (sb_rdonly(sb)) old_flags |= SB_RDONLY; + if (!(old_flags & SB_RDONLY)) + clear_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state); sb->s_flags = old_flags; fs_info->mount_opt = old_opts; fs_info->compress_type = old_compress_type; diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 8ca334d554af..6bd97bd4cb37 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -55,8 +55,14 @@ struct inode *btrfs_new_test_inode(void) struct inode *inode; inode = new_inode(test_mnt->mnt_sb); - if (inode) - inode_init_owner(inode, NULL, S_IFREG); + if (!inode) + return NULL; + + inode->i_mode = S_IFREG; + BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; + BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; + BTRFS_I(inode)->location.offset = 0; + inode_init_owner(inode, NULL, S_IFREG); return inode; } diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index 04022069761d..c9874b12d337 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -232,11 +232,6 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) return ret; } - inode->i_mode = S_IFREG; - BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; - BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; - BTRFS_I(inode)->location.offset = 0; - fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { test_std_err(TEST_ALLOC_FS_INFO); @@ -835,10 +830,6 @@ static int test_hole_first(u32 sectorsize, u32 nodesize) return ret; } - BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; - BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; - BTRFS_I(inode)->location.offset = 0; - fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { test_std_err(TEST_ALLOC_FS_INFO); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 8e0f7a1029c6..6af7f2bf92de 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2265,14 +2265,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) btrfs_free_log_root_tree(trans, fs_info); /* - * commit_fs_roots() can call btrfs_save_ino_cache(), which generates - * new delayed refs. Must handle them or qgroup can be wrong. - */ - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - goto unlock_tree_log; - - /* * Since fs roots are all committed, we can get a quite accurate * new_roots. So let's do quota accounting. */ diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 028e733e42f3..582061c7b547 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -760,6 +760,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, { struct btrfs_fs_info *fs_info = leaf->fs_info; u64 length; + u64 chunk_end; u64 stripe_len; u16 num_stripes; u16 sub_stripes; @@ -814,6 +815,12 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, "invalid chunk length, have %llu", length); return -EUCLEAN; } + if (unlikely(check_add_overflow(logical, length, &chunk_end))) { + chunk_err(leaf, chunk, logical, +"invalid chunk logical start and length, have logical start %llu length %llu", + logical, length); + return -EUCLEAN; + } if (unlikely(!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN)) { chunk_err(leaf, chunk, logical, "invalid chunk stripe length: %llu", diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ee086fc56c30..d6c24c8ad749 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -433,7 +433,7 @@ static struct btrfs_device *__alloc_device(struct btrfs_fs_info *fs_info) atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); - btrfs_device_data_ordered_init(dev, fs_info); + btrfs_device_data_ordered_init(dev); INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); extent_io_tree_init(fs_info, &dev->alloc_state, @@ -2592,7 +2592,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); if (seeding_dev) { - sb->s_flags &= ~SB_RDONLY; + btrfs_clear_sb_rdonly(sb); ret = btrfs_prepare_sprout(fs_info); if (ret) { btrfs_abort_transaction(trans, ret); @@ -2728,7 +2728,7 @@ error_sysfs: mutex_unlock(&fs_info->fs_devices->device_list_mutex); error_trans: if (seeding_dev) - sb->s_flags |= SB_RDONLY; + btrfs_set_sb_rdonly(sb); if (trans) btrfs_end_transaction(trans); error_free_zone: @@ -4317,6 +4317,8 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info) btrfs_warn(fs_info, "balance: cannot set exclusive op status, resume manually"); + btrfs_release_path(path); + mutex_lock(&fs_info->balance_mutex); BUG_ON(fs_info->balance_ctl); spin_lock(&fs_info->balance_lock); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 1997a4649a66..c43663d9c22e 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -39,10 +39,10 @@ struct btrfs_io_geometry { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __BTRFS_NEED_DEVICE_DATA_ORDERED -#define btrfs_device_data_ordered_init(device, info) \ - seqcount_mutex_init(&device->data_seqcount, &info->chunk_mutex) +#define btrfs_device_data_ordered_init(device) \ + seqcount_init(&device->data_seqcount) #else -#define btrfs_device_data_ordered_init(device, info) do { } while (0) +#define btrfs_device_data_ordered_init(device) do { } while (0) #endif #define BTRFS_DEV_STATE_WRITEABLE (0) @@ -76,8 +76,7 @@ struct btrfs_device { blk_status_t last_flush_error; #ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED - /* A seqcount_t with associated chunk_mutex (for lockdep) */ - seqcount_mutex_t data_seqcount; + seqcount_t data_seqcount; #endif /* the internal btrfs device id */ @@ -168,9 +167,11 @@ btrfs_device_get_##name(const struct btrfs_device *dev) \ static inline void \ btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \ { \ + preempt_disable(); \ write_seqcount_begin(&dev->data_seqcount); \ dev->name = size; \ write_seqcount_end(&dev->data_seqcount); \ + preempt_enable(); \ } #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) #define BTRFS_DEVICE_GETSET_FUNCS(name) \ diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 8bda092e60c5..e027c718ca01 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -413,7 +413,6 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, inode = d_backing_inode(object->backer); ASSERT(S_ISREG(inode->i_mode)); - ASSERT(inode->i_mapping->a_ops->readpages); /* calculate the shift required to use bmap */ shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; @@ -713,7 +712,6 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, inode = d_backing_inode(object->backer); ASSERT(S_ISREG(inode->i_mode)); - ASSERT(inode->i_mapping->a_ops->readpages); /* calculate the shift required to use bmap */ shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 98c15ff2e599..d87bd852ed96 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2475,6 +2475,22 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, return r; } +static void encode_timestamp_and_gids(void **p, + const struct ceph_mds_request *req) +{ + struct ceph_timespec ts; + int i; + + ceph_encode_timespec64(&ts, &req->r_stamp); + ceph_encode_copy(p, &ts, sizeof(ts)); + + /* gid_list */ + ceph_encode_32(p, req->r_cred->group_info->ngroups); + for (i = 0; i < req->r_cred->group_info->ngroups; i++) + ceph_encode_64(p, from_kgid(&init_user_ns, + req->r_cred->group_info->gid[i])); +} + /* * called under mdsc->mutex */ @@ -2491,7 +2507,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, u64 ino1 = 0, ino2 = 0; int pathlen1 = 0, pathlen2 = 0; bool freepath1 = false, freepath2 = false; - int len, i; + int len; u16 releases; void *p, *end; int ret; @@ -2517,17 +2533,10 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, goto out_free1; } - if (legacy) { - /* Old style */ - len = sizeof(*head); - } else { - /* New style: add gid_list and any later fields */ - len = sizeof(struct ceph_mds_request_head) + sizeof(u32) + - (sizeof(u64) * req->r_cred->group_info->ngroups); - } - + len = legacy ? sizeof(*head) : sizeof(struct ceph_mds_request_head); len += pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) + sizeof(struct ceph_timespec); + len += sizeof(u32) + (sizeof(u64) * req->r_cred->group_info->ngroups); /* calculate (max) length for cap releases */ len += sizeof(struct ceph_mds_request_release) * @@ -2548,7 +2557,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, msg->hdr.tid = cpu_to_le64(req->r_tid); /* - * The old ceph_mds_request_header didn't contain a version field, and + * The old ceph_mds_request_head didn't contain a version field, and * one was added when we moved the message version from 3->4. */ if (legacy) { @@ -2609,20 +2618,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, head->num_releases = cpu_to_le16(releases); - /* time stamp */ - { - struct ceph_timespec ts; - ceph_encode_timespec64(&ts, &req->r_stamp); - ceph_encode_copy(&p, &ts, sizeof(ts)); - } - - /* gid list */ - if (!legacy) { - ceph_encode_32(&p, req->r_cred->group_info->ngroups); - for (i = 0; i < req->r_cred->group_info->ngroups; i++) - ceph_encode_64(&p, from_kgid(&init_user_ns, - req->r_cred->group_info->gid[i])); - } + encode_timestamp_and_gids(&p, req); if (WARN_ON_ONCE(p > end)) { ceph_msg_put(msg); @@ -2730,13 +2726,8 @@ static int __prepare_send_request(struct ceph_mds_session *session, /* remove cap/dentry releases from message */ rhead->num_releases = 0; - /* time stamp */ p = msg->front.iov_base + req->r_request_release_offset; - { - struct ceph_timespec ts; - ceph_encode_timespec64(&ts, &req->r_stamp); - ceph_encode_copy(&p, &ts, sizeof(ts)); - } + encode_timestamp_and_gids(&p, req); msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); @@ -5047,7 +5038,7 @@ bad: return; } -static struct ceph_connection *con_get(struct ceph_connection *con) +static struct ceph_connection *mds_get_con(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; @@ -5056,7 +5047,7 @@ static struct ceph_connection *con_get(struct ceph_connection *con) return NULL; } -static void con_put(struct ceph_connection *con) +static void mds_put_con(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; @@ -5067,7 +5058,7 @@ static void con_put(struct ceph_connection *con) * if the client is unresponsive for long enough, the mds will kill * the session entirely. */ -static void peer_reset(struct ceph_connection *con) +static void mds_peer_reset(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5076,7 +5067,7 @@ static void peer_reset(struct ceph_connection *con) send_mds_reconnect(mdsc, s); } -static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) +static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5134,8 +5125,8 @@ out: * Note: returned pointer is the address of a structure that's * managed separately. Caller must *not* attempt to free it. */ -static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, - int *proto, int force_new) +static struct ceph_auth_handshake * +mds_get_authorizer(struct ceph_connection *con, int *proto, int force_new) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5151,7 +5142,7 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, return auth; } -static int add_authorizer_challenge(struct ceph_connection *con, +static int mds_add_authorizer_challenge(struct ceph_connection *con, void *challenge_buf, int challenge_buf_len) { struct ceph_mds_session *s = con->private; @@ -5162,7 +5153,7 @@ static int add_authorizer_challenge(struct ceph_connection *con, challenge_buf, challenge_buf_len); } -static int verify_authorizer_reply(struct ceph_connection *con) +static int mds_verify_authorizer_reply(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5174,7 +5165,7 @@ static int verify_authorizer_reply(struct ceph_connection *con) NULL, NULL, NULL, NULL); } -static int invalidate_authorizer(struct ceph_connection *con) +static int mds_invalidate_authorizer(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5297,15 +5288,15 @@ static int mds_check_message_signature(struct ceph_msg *msg) } static const struct ceph_connection_operations mds_con_ops = { - .get = con_get, - .put = con_put, - .dispatch = dispatch, - .get_authorizer = get_authorizer, - .add_authorizer_challenge = add_authorizer_challenge, - .verify_authorizer_reply = verify_authorizer_reply, - .invalidate_authorizer = invalidate_authorizer, - .peer_reset = peer_reset, + .get = mds_get_con, + .put = mds_put_con, .alloc_msg = mds_alloc_msg, + .dispatch = mds_dispatch, + .peer_reset = mds_peer_reset, + .get_authorizer = mds_get_authorizer, + .add_authorizer_challenge = mds_add_authorizer_challenge, + .verify_authorizer_reply = mds_verify_authorizer_reply, + .invalidate_authorizer = mds_invalidate_authorizer, .sign_message = mds_sign_message, .check_message_signature = mds_check_message_signature, .get_auth_request = mds_get_auth_request, diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index e4c6ae47a796..6b1ce4efb591 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -133,8 +133,9 @@ cifs_build_devname(char *nodename, const char *prepath) * Caller is responsible for freeing returned value if it is not error. */ char *cifs_compose_mount_options(const char *sb_mountdata, - const char *fullpath, - const struct dfs_info3_param *ref) + const char *fullpath, + const struct dfs_info3_param *ref, + char **devname) { int rc; char *name; @@ -231,7 +232,10 @@ char *cifs_compose_mount_options(const char *sb_mountdata, strcat(mountdata, "ip="); strcat(mountdata, srvIP); - kfree(name); + if (devname) + *devname = name; + else + kfree(name); /*cifs_dbg(FYI, "%s: parent mountdata: %s\n", __func__, sb_mountdata);*/ /*cifs_dbg(FYI, "%s: submount mountdata: %s\n", __func__, mountdata );*/ @@ -278,7 +282,7 @@ static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt, /* strip first '\' from fullpath */ mountdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - fullpath + 1, NULL); + fullpath + 1, NULL, NULL); if (IS_ERR(mountdata)) { kfree(devname); return (struct vfsmount *)mountdata; diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c index c594e588a8b5..d35f599aa00e 100644 --- a/fs/cifs/cifs_swn.c +++ b/fs/cifs/cifs_swn.c @@ -285,8 +285,6 @@ static struct cifs_swn_reg *cifs_find_swn_reg(struct cifs_tcon *tcon) continue; } - mutex_unlock(&cifs_swnreg_idr_mutex); - cifs_dbg(FYI, "Existing swn registration for %s:%s found\n", swnreg->net_name, swnreg->share_name); @@ -482,48 +480,51 @@ static int cifs_swn_store_swn_addr(const struct sockaddr_storage *new, static int cifs_swn_reconnect(struct cifs_tcon *tcon, struct sockaddr_storage *addr) { + int ret = 0; + /* Store the reconnect address */ mutex_lock(&tcon->ses->server->srv_mutex); - if (!cifs_sockaddr_equal(&tcon->ses->server->dstaddr, addr)) { - int ret; - - ret = cifs_swn_store_swn_addr(addr, &tcon->ses->server->dstaddr, - &tcon->ses->server->swn_dstaddr); - if (ret < 0) { - cifs_dbg(VFS, "%s: failed to store address: %d\n", __func__, ret); - return ret; - } - tcon->ses->server->use_swn_dstaddr = true; + if (cifs_sockaddr_equal(&tcon->ses->server->dstaddr, addr)) + goto unlock; - /* - * Unregister to stop receiving notifications for the old IP address. - */ - ret = cifs_swn_unregister(tcon); - if (ret < 0) { - cifs_dbg(VFS, "%s: Failed to unregister for witness notifications: %d\n", - __func__, ret); - return ret; - } + ret = cifs_swn_store_swn_addr(addr, &tcon->ses->server->dstaddr, + &tcon->ses->server->swn_dstaddr); + if (ret < 0) { + cifs_dbg(VFS, "%s: failed to store address: %d\n", __func__, ret); + goto unlock; + } + tcon->ses->server->use_swn_dstaddr = true; - /* - * And register to receive notifications for the new IP address now that we have - * stored the new address. - */ - ret = cifs_swn_register(tcon); - if (ret < 0) { - cifs_dbg(VFS, "%s: Failed to register for witness notifications: %d\n", - __func__, ret); - return ret; - } + /* + * Unregister to stop receiving notifications for the old IP address. + */ + ret = cifs_swn_unregister(tcon); + if (ret < 0) { + cifs_dbg(VFS, "%s: Failed to unregister for witness notifications: %d\n", + __func__, ret); + goto unlock; + } - spin_lock(&GlobalMid_Lock); - if (tcon->ses->server->tcpStatus != CifsExiting) - tcon->ses->server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); + /* + * And register to receive notifications for the new IP address now that we have + * stored the new address. + */ + ret = cifs_swn_register(tcon); + if (ret < 0) { + cifs_dbg(VFS, "%s: Failed to register for witness notifications: %d\n", + __func__, ret); + goto unlock; } + + spin_lock(&GlobalMid_Lock); + if (tcon->ses->server->tcpStatus != CifsExiting) + tcon->ses->server->tcpStatus = CifsNeedReconnect; + spin_unlock(&GlobalMid_Lock); + +unlock: mutex_unlock(&tcon->ses->server->srv_mutex); - return 0; + return ret; } static int cifs_swn_client_move(struct cifs_swn_reg *swnreg, struct sockaddr_storage *addr) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 2f21f89871cc..562913e2b3f2 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1195,7 +1195,8 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd, } struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, - const struct cifs_fid *cifsfid, u32 *pacllen) + const struct cifs_fid *cifsfid, u32 *pacllen, + u32 __maybe_unused unused) { struct cifs_ntsd *pntsd = NULL; unsigned int xid; @@ -1263,7 +1264,7 @@ static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, /* Retrieve an ACL from the server */ struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, struct inode *inode, const char *path, - u32 *pacllen) + u32 *pacllen, u32 info) { struct cifs_ntsd *pntsd = NULL; struct cifsFileInfo *open_file = NULL; @@ -1273,7 +1274,7 @@ struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, if (!open_file) return get_cifs_acl_by_path(cifs_sb, path, pacllen); - pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen); + pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen, info); cifsFileInfo_put(open_file); return pntsd; } @@ -1338,6 +1339,7 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, int rc = 0; struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); struct smb_version_operations *ops; + const u32 info = 0; cifs_dbg(NOISY, "converting ACL to mode for %s\n", path); @@ -1347,9 +1349,9 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, ops = tlink_tcon(tlink)->ses->server->ops; if (pfid && (ops->get_acl_by_fid)) - pntsd = ops->get_acl_by_fid(cifs_sb, pfid, &acllen); + pntsd = ops->get_acl_by_fid(cifs_sb, pfid, &acllen, info); else if (ops->get_acl) - pntsd = ops->get_acl(cifs_sb, inode, path, &acllen); + pntsd = ops->get_acl(cifs_sb, inode, path, &acllen, info); else { cifs_put_tlink(tlink); return -EOPNOTSUPP; @@ -1388,6 +1390,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); struct smb_version_operations *ops; bool mode_from_sid, id_from_sid; + const u32 info = 0; if (IS_ERR(tlink)) return PTR_ERR(tlink); @@ -1403,7 +1406,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, return -EOPNOTSUPP; } - pntsd = ops->get_acl(cifs_sb, inode, path, &secdesclen); + pntsd = ops->get_acl(cifs_sb, inode, path, &secdesclen, info); if (IS_ERR(pntsd)) { rc = PTR_ERR(pntsd); cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index ce0d0037fd0a..ab883e84e116 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -469,7 +469,7 @@ cifs_show_cache_flavor(struct seq_file *s, struct cifs_sb_info *cifs_sb) static int cifs_show_devname(struct seq_file *m, struct dentry *root) { struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb); - char *devname = kstrdup(cifs_sb->ctx->UNC, GFP_KERNEL); + char *devname = kstrdup(cifs_sb->ctx->source, GFP_KERNEL); if (devname == NULL) seq_puts(m, "none"); @@ -822,7 +822,7 @@ cifs_smb3_do_mount(struct file_system_type *fs_type, goto out; } - rc = cifs_setup_volume_info(cifs_sb->ctx); + rc = cifs_setup_volume_info(cifs_sb->ctx, NULL, old_ctx->UNC); if (rc) { root = ERR_PTR(rc); goto out; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 720d0f6a982d..50fcb65920e8 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -456,9 +456,9 @@ struct smb_version_operations { const char *, const void *, const __u16, const struct nls_table *, struct cifs_sb_info *); struct cifs_ntsd * (*get_acl)(struct cifs_sb_info *, struct inode *, - const char *, u32 *); + const char *, u32 *, u32); struct cifs_ntsd * (*get_acl_by_fid)(struct cifs_sb_info *, - const struct cifs_fid *, u32 *); + const struct cifs_fid *, u32 *, u32); int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *, int); /* writepages retry size */ diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index ce51183ecaf4..64fe5a47b5e8 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -240,6 +240,8 @@ #define SYNCHRONIZE 0x00100000 /* The file handle can waited on to */ /* synchronize with the completion */ /* of an input/output request */ +#define SYSTEM_SECURITY 0x01000000 /* The system access control list */ + /* can be read and changed */ #define GENERIC_ALL 0x10000000 #define GENERIC_EXECUTE 0x20000000 #define GENERIC_WRITE 0x40000000 diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index bd1c9b038568..32f7a013402e 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -78,7 +78,8 @@ extern char *cifs_build_path_to_root(struct smb3_fs_context *ctx, int add_treename); 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); + 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); @@ -89,6 +90,7 @@ 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); extern int smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx); +extern int smb3_parse_opt(const char *options, const char *key, char **val); extern bool cifs_match_ipaddr(struct sockaddr *srcaddr, struct sockaddr *rhs); extern int cifs_discard_remaining_data(struct TCP_Server_Info *server); extern int cifs_call_async(struct TCP_Server_Info *server, @@ -218,9 +220,9 @@ extern int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, extern int id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, kuid_t uid, kgid_t gid); extern struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *, struct inode *, - const char *, u32 *); + const char *, u32 *, u32); extern struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *, - const struct cifs_fid *, u32 *); + const struct cifs_fid *, u32 *, u32); extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *, const char *, int); extern unsigned int setup_authusers_ACE(struct cifs_ace *pace); @@ -549,7 +551,7 @@ extern int SMBencrypt(unsigned char *passwd, const unsigned char *c8, unsigned char *p24); extern int -cifs_setup_volume_info(struct smb3_fs_context *ctx); +cifs_setup_volume_info(struct smb3_fs_context *ctx, const char *mntopts, const char *devname); extern struct TCP_Server_Info * cifs_find_tcp_session(struct smb3_fs_context *ctx); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 509a41ff56b8..4bb9decbbf27 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -155,6 +155,7 @@ static void reconn_set_next_dfs_target(struct TCP_Server_Info *server, cifs_dbg(FYI, "%s: failed to extract hostname from target: %ld\n", __func__, PTR_ERR(server->hostname)); + return; } rc = reconn_set_ipaddr_from_hostname(server); @@ -2194,7 +2195,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) tcon->nohandlecache = ctx->nohandlecache; else - tcon->nohandlecache = 1; + tcon->nohandlecache = true; tcon->nodelete = ctx->nodelete; tcon->local_lease = ctx->local_lease; INIT_LIST_HEAD(&tcon->pending_opens); @@ -2627,7 +2628,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon, } else if (ctx) tcon->unix_ext = 1; /* Unix Extensions supported */ - if (tcon->unix_ext == 0) { + if (!tcon->unix_ext) { cifs_dbg(FYI, "Unix extensions disabled so not set on reconnect\n"); return; } @@ -2755,6 +2756,7 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb) cifs_sb->prepath = kstrdup(ctx->prepath, GFP_KERNEL); if (cifs_sb->prepath == NULL) return -ENOMEM; + cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; } return 0; @@ -2971,17 +2973,28 @@ expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses, rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), ref_path, &referral, NULL); if (!rc) { + char *fake_devname = NULL; + mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - full_path + 1, &referral); + full_path + 1, &referral, + &fake_devname); free_dfs_info_param(&referral); if (IS_ERR(mdata)) { rc = PTR_ERR(mdata); mdata = NULL; } else { - smb3_cleanup_fs_context_contents(ctx); - rc = cifs_setup_volume_info(ctx); + /* + * We can not clear out the whole structure since we + * no longer have an explicit function to parse + * a mount-string. Instead we need to clear out the + * individual fields that are no longer valid. + */ + kfree(ctx->prepath); + ctx->prepath = NULL; + rc = cifs_setup_volume_info(ctx, mdata, fake_devname); } + kfree(fake_devname); kfree(cifs_sb->ctx->mount_options); cifs_sb->ctx->mount_options = mdata; } @@ -3035,6 +3048,7 @@ static int setup_dfs_tgt_conn(const char *path, const char *full_path, struct dfs_info3_param ref = {0}; char *mdata = NULL; struct smb3_fs_context fake_ctx = {NULL}; + char *fake_devname = NULL; cifs_dbg(FYI, "%s: dfs path: %s\n", __func__, path); @@ -3043,16 +3057,18 @@ static int setup_dfs_tgt_conn(const char *path, const char *full_path, return rc; mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - full_path + 1, &ref); + full_path + 1, &ref, + &fake_devname); free_dfs_info_param(&ref); if (IS_ERR(mdata)) { rc = PTR_ERR(mdata); mdata = NULL; } else - rc = cifs_setup_volume_info(&fake_ctx); + rc = cifs_setup_volume_info(&fake_ctx, mdata, fake_devname); kfree(mdata); + kfree(fake_devname); if (!rc) { /* @@ -3121,10 +3137,24 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_ * we should pass a clone of the original context? */ int -cifs_setup_volume_info(struct smb3_fs_context *ctx) +cifs_setup_volume_info(struct smb3_fs_context *ctx, const char *mntopts, const char *devname) { int rc = 0; + smb3_parse_devname(devname, ctx); + + if (mntopts) { + char *ip; + + cifs_dbg(FYI, "%s: mntopts=%s\n", __func__, mntopts); + rc = smb3_parse_opt(mntopts, "ip", &ip); + if (!rc && !cifs_convert_address((struct sockaddr *)&ctx->dstaddr, ip, + strlen(ip))) { + cifs_dbg(VFS, "%s: failed to convert ip address\n", __func__); + return -EINVAL; + } + } + if (ctx->nullauth) { cifs_dbg(FYI, "Anonymous login\n"); kfree(ctx->username); @@ -3739,7 +3769,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, if (!ses->binding) { ses->capabilities = server->capabilities; - if (linuxExtEnabled == 0) + if (!linuxExtEnabled) ses->capabilities &= (~server->vals->cap_unix); if (ses->auth_key.response) { diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 6ad6ba5f6ebe..4950ab0486ae 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1260,7 +1260,8 @@ void dfs_cache_del_vol(const char *fullpath) vi = find_vol(fullpath); spin_unlock(&vol_list_lock); - kref_put(&vi->refcnt, vol_release); + if (!IS_ERR(vi)) + kref_put(&vi->refcnt, vol_release); } /** @@ -1416,7 +1417,7 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi, int rc; struct cache_entry *ce; struct dfs_info3_param ref = {0}; - char *mdata = NULL; + char *mdata = NULL, *devname = NULL; struct TCP_Server_Info *server; struct cifs_ses *ses; struct smb3_fs_context ctx = {NULL}; @@ -1443,7 +1444,8 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi, up_read(&htable_rw_lock); - mdata = cifs_compose_mount_options(vi->mntdata, rpath, &ref); + mdata = cifs_compose_mount_options(vi->mntdata, rpath, &ref, + &devname); free_dfs_info_param(&ref); if (IS_ERR(mdata)) { @@ -1452,7 +1454,7 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi, goto out; } - rc = cifs_setup_volume_info(&ctx); + rc = cifs_setup_volume_info(&ctx, NULL, devname); if (rc) { ses = ERR_PTR(rc); @@ -1471,6 +1473,7 @@ out: smb3_cleanup_fs_context_contents(&ctx); kfree(mdata); kfree(rpath); + kfree(devname); return ses; } diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 68900f1629bf..97ac363b5df1 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -737,6 +737,7 @@ static int cifs_d_revalidate(struct dentry *direntry, unsigned int flags) { struct inode *inode; + int rc; if (flags & LOOKUP_RCU) return -ECHILD; @@ -746,8 +747,25 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags) if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode))) CIFS_I(inode)->time = 0; /* force reval */ - if (cifs_revalidate_dentry(direntry)) - return 0; + rc = cifs_revalidate_dentry(direntry); + if (rc) { + cifs_dbg(FYI, "cifs_revalidate_dentry failed with rc=%d", rc); + switch (rc) { + case -ENOENT: + case -ESTALE: + /* + * Those errors mean the dentry is invalid + * (file was deleted or recreated) + */ + return 0; + default: + /* + * Otherwise some unexpected error happened + * report it as-is to VFS layer + */ + return rc; + } + } else { /* * If the inode wasn't known to be a dfs entry when diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 0afccbbed2e6..12a5da0230b5 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -148,7 +148,6 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { /* Mount options which take string value */ fsparam_string("source", Opt_source), - fsparam_string("unc", Opt_source), fsparam_string("user", Opt_user), fsparam_string("username", Opt_user), fsparam_string("pass", Opt_pass), @@ -175,8 +174,15 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_flag_no("exec", Opt_ignore), fsparam_flag_no("dev", Opt_ignore), fsparam_flag_no("mand", Opt_ignore), + fsparam_flag_no("auto", Opt_ignore), fsparam_string("cred", Opt_ignore), fsparam_string("credentials", Opt_ignore), + /* + * UNC and prefixpath is now extracted from Opt_source + * in the new mount API so we can just ignore them going forward. + */ + fsparam_string("unc", Opt_ignore), + fsparam_string("prefixpath", Opt_ignore), {} }; @@ -303,8 +309,6 @@ do { \ int smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx) { - int rc = 0; - memcpy(new_ctx, ctx, sizeof(*ctx)); new_ctx->prepath = NULL; new_ctx->mount_options = NULL; @@ -313,6 +317,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx new_ctx->password = NULL; new_ctx->domainname = NULL; new_ctx->UNC = NULL; + new_ctx->source = NULL; new_ctx->iocharset = NULL; /* @@ -323,11 +328,12 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx DUP_CTX_STR(username); DUP_CTX_STR(password); DUP_CTX_STR(UNC); + DUP_CTX_STR(source); DUP_CTX_STR(domainname); DUP_CTX_STR(nodename); DUP_CTX_STR(iocharset); - return rc; + return 0; } static int @@ -401,6 +407,37 @@ cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3) return 0; } +int smb3_parse_opt(const char *options, const char *key, char **val) +{ + int rc = -ENOENT; + char *opts, *orig, *p; + + orig = opts = kstrdup(options, GFP_KERNEL); + if (!opts) + return -ENOMEM; + + while ((p = strsep(&opts, ","))) { + char *nval; + + if (!*p) + continue; + if (strncasecmp(p, key, strlen(key))) + continue; + nval = strchr(p, '='); + if (nval) { + if (nval == p) + continue; + *nval++ = 0; + *val = kstrndup(nval, strlen(nval), GFP_KERNEL); + rc = !*val ? -ENOMEM : 0; + goto out; + } + } +out: + kfree(orig); + return rc; +} + /* * Parse a devname into substrings and populate the ctx->UNC and ctx->prepath * fields with the result. Returns 0 on success and an error otherwise @@ -533,7 +570,7 @@ static int smb3_fs_context_validate(struct fs_context *fc) if (ctx->rdma && ctx->vals->protocol_id < SMB30_PROT_ID) { cifs_dbg(VFS, "SMB Direct requires Version >=3.0\n"); - return -1; + return -EOPNOTSUPP; } #ifndef CONFIG_KEYS @@ -556,7 +593,7 @@ static int smb3_fs_context_validate(struct fs_context *fc) /* make sure UNC has a share name */ if (strlen(ctx->UNC) < 3 || !strchr(ctx->UNC + 3, '\\')) { cifs_dbg(VFS, "Malformed UNC. Unable to find share name.\n"); - return -1; + return -ENOENT; } if (!ctx->got_ip) { @@ -570,7 +607,7 @@ static int smb3_fs_context_validate(struct fs_context *fc) if (!cifs_convert_address((struct sockaddr *)&ctx->dstaddr, &ctx->UNC[2], len)) { pr_err("Unable to determine destination address\n"); - return -1; + return -EHOSTUNREACH; } } @@ -701,6 +738,7 @@ static int smb3_reconfigure(struct fs_context *fc) * just use what we already have in cifs_sb->ctx. */ STEAL_STRING(cifs_sb, ctx, UNC); + STEAL_STRING(cifs_sb, ctx, source); STEAL_STRING(cifs_sb, ctx, username); STEAL_STRING(cifs_sb, ctx, password); STEAL_STRING(cifs_sb, ctx, domainname); @@ -943,6 +981,11 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, cifs_dbg(VFS, "Unknown error parsing devname\n"); goto cifs_parse_mount_err; } + ctx->source = kstrdup(param->string, GFP_KERNEL); + if (ctx->source == NULL) { + cifs_dbg(VFS, "OOM when copying UNC string\n"); + goto cifs_parse_mount_err; + } fc->source = kstrdup(param->string, GFP_KERNEL); if (fc->source == NULL) { cifs_dbg(VFS, "OOM when copying UNC string\n"); @@ -1265,7 +1308,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, return 0; cifs_parse_mount_err: - return 1; + return -EINVAL; } int smb3_init_fs_context(struct fs_context *fc) @@ -1365,6 +1408,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx) ctx->password = NULL; kfree(ctx->UNC); ctx->UNC = NULL; + kfree(ctx->source); + ctx->source = NULL; kfree(ctx->domainname); ctx->domainname = NULL; kfree(ctx->nodename); @@ -1502,8 +1547,8 @@ void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb) cifs_sb->mnt_cifs_flags |= (CIFS_MOUNT_MULTIUSER | CIFS_MOUNT_NO_PERM); else - cifs_sb->mnt_cifs_flags &= ~(CIFS_MOUNT_MULTIUSER | - CIFS_MOUNT_NO_PERM); + cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MULTIUSER; + if (ctx->strict_io) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_STRICT_IO; diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h index 3358b33abcd0..1c44a460e2c0 100644 --- a/fs/cifs/fs_context.h +++ b/fs/cifs/fs_context.h @@ -159,6 +159,7 @@ struct smb3_fs_context { char *username; char *password; char *domainname; + char *source; char *UNC; char *nodename; char *iocharset; /* local code page for mapping to and from Unicode */ diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 949cd1177147..f19274857292 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3214,7 +3214,7 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon, static struct cifs_ntsd * get_smb2_acl_by_fid(struct cifs_sb_info *cifs_sb, - const struct cifs_fid *cifsfid, u32 *pacllen) + const struct cifs_fid *cifsfid, u32 *pacllen, u32 info) { struct cifs_ntsd *pntsd = NULL; unsigned int xid; @@ -3228,7 +3228,8 @@ get_smb2_acl_by_fid(struct cifs_sb_info *cifs_sb, cifs_dbg(FYI, "trying to get acl\n"); rc = SMB2_query_acl(xid, tlink_tcon(tlink), cifsfid->persistent_fid, - cifsfid->volatile_fid, (void **)&pntsd, pacllen); + cifsfid->volatile_fid, (void **)&pntsd, pacllen, + info); free_xid(xid); cifs_put_tlink(tlink); @@ -3242,7 +3243,7 @@ get_smb2_acl_by_fid(struct cifs_sb_info *cifs_sb, static struct cifs_ntsd * get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb, - const char *path, u32 *pacllen) + const char *path, u32 *pacllen, u32 info) { struct cifs_ntsd *pntsd = NULL; u8 oplock = SMB2_OPLOCK_LEVEL_NONE; @@ -3280,12 +3281,16 @@ get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb, oparms.fid = &fid; oparms.reconnect = false; + if (info & SACL_SECINFO) + oparms.desired_access |= SYSTEM_SECURITY; + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL, NULL); kfree(utf16_path); if (!rc) { rc = SMB2_query_acl(xid, tlink_tcon(tlink), fid.persistent_fid, - fid.volatile_fid, (void **)&pntsd, pacllen); + fid.volatile_fid, (void **)&pntsd, pacllen, + info); SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); } @@ -3319,10 +3324,12 @@ set_smb2_acl(struct cifs_ntsd *pnntsd, __u32 acllen, tcon = tlink_tcon(tlink); xid = get_xid(); - if (aclflag == CIFS_ACL_OWNER || aclflag == CIFS_ACL_GROUP) - access_flags = WRITE_OWNER; - else - access_flags = WRITE_DAC; + if (aclflag & CIFS_ACL_OWNER || aclflag & CIFS_ACL_GROUP) + access_flags |= WRITE_OWNER; + if (aclflag & CIFS_ACL_SACL) + access_flags |= SYSTEM_SECURITY; + if (aclflag & CIFS_ACL_DACL) + access_flags |= WRITE_DAC; utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); if (!utf16_path) { @@ -3356,18 +3363,18 @@ set_smb2_acl(struct cifs_ntsd *pnntsd, __u32 acllen, /* Retrieve an ACL from the server */ static struct cifs_ntsd * get_smb2_acl(struct cifs_sb_info *cifs_sb, - struct inode *inode, const char *path, - u32 *pacllen) + struct inode *inode, const char *path, + u32 *pacllen, u32 info) { struct cifs_ntsd *pntsd = NULL; struct cifsFileInfo *open_file = NULL; - if (inode) + if (inode && !(info & SACL_SECINFO)) open_file = find_readable_file(CIFS_I(inode), true); - if (!open_file) - return get_smb2_acl_by_path(cifs_sb, path, pacllen); + if (!open_file || (info & SACL_SECINFO)) + return get_smb2_acl_by_path(cifs_sb, path, pacllen, info); - pntsd = get_smb2_acl_by_fid(cifs_sb, &open_file->fid, pacllen); + pntsd = get_smb2_acl_by_fid(cifs_sb, &open_file->fid, pacllen, info); cifsFileInfo_put(open_file); return pntsd; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index fc06c762fbbf..794fc3b68b4f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3248,7 +3248,7 @@ close_exit: free_rsp_buf(resp_buftype, rsp); /* retry close in a worker thread if this one is interrupted */ - if (rc == -EINTR) { + if (is_interrupt_error(rc)) { int tmp_rc; tmp_rc = smb2_handle_cancelled_close(tcon, persistent_fid, @@ -3479,10 +3479,11 @@ SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon, int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon, - u64 persistent_fid, u64 volatile_fid, - void **data, u32 *plen) + u64 persistent_fid, u64 volatile_fid, + void **data, u32 *plen, u32 extra_info) { - __u32 additional_info = OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO; + __u32 additional_info = OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO | + extra_info; *plen = 0; return query_info(xid, tcon, persistent_fid, volatile_fid, diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 204a622b89ed..a5a9e33c0d73 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -286,7 +286,7 @@ struct smb2_negotiate_req { __le32 NegotiateContextOffset; /* SMB3.1.1 only. MBZ earlier */ __le16 NegotiateContextCount; /* SMB3.1.1 only. MBZ earlier */ __le16 Reserved2; - __le16 Dialects[1]; /* One dialect (vers=) at a time for now */ + __le16 Dialects[4]; /* BB expand this if autonegotiate > 4 dialects */ } __packed; /* Dialects */ @@ -424,7 +424,7 @@ struct smb2_rdma_transform_capabilities_context { __le16 TransformCount; __u16 Reserved1; __u32 Reserved2; - __le16 RDMATransformIds[1]; + __le16 RDMATransformIds[]; } __packed; /* Signing algorithms */ diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index d4110447ee3a..9565e27681a5 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -200,8 +200,8 @@ extern int SMB2_query_info_init(struct cifs_tcon *tcon, size_t input_len, void *input); extern void SMB2_query_info_free(struct smb_rqst *rqst); extern int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon, - u64 persistent_file_id, u64 volatile_file_id, - void **data, unsigned int *plen); + u64 persistent_file_id, u64 volatile_file_id, + void **data, unsigned int *plen, u32 info); extern int SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le64 *uniqueid); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index e9abb41aa89b..4a2b836eb017 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -338,7 +338,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, if (ssocket == NULL) return -EAGAIN; - if (signal_pending(current)) { + if (fatal_signal_pending(current)) { cifs_dbg(FYI, "signal pending before send request\n"); return -ERESTARTSYS; } @@ -429,7 +429,7 @@ unmask: if (signal_pending(current) && (total_len != send_length)) { cifs_dbg(FYI, "signal is pending after attempt to send\n"); - rc = -EINTR; + rc = -ERESTARTSYS; } /* uncork it */ @@ -666,10 +666,22 @@ wait_for_compound_request(struct TCP_Server_Info *server, int num, if (*credits < num) { /* - * Return immediately if not too many requests in flight since - * we will likely be stuck on waiting for credits. + * If the server is tight on resources or just gives us less + * credits for other reasons (e.g. requests are coming out of + * order and the server delays granting more credits until it + * processes a missing mid) and we exhausted most available + * credits there may be situations when we try to send + * a compound request but we don't have enough credits. At this + * point the client needs to decide if it should wait for + * additional credits or fail the request. If at least one + * request is in flight there is a high probability that the + * server will return enough credits to satisfy this compound + * request. + * + * Return immediately if no requests in flight since we will be + * stuck on waiting for credits. */ - if (server->in_flight < num - *credits) { + if (server->in_flight == 0) { spin_unlock(&server->req_lock); trace_smb3_insufficient_credits(server->CurrentMid, server->hostname, scredits, sin_flight); diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index b8299173ea7e..6b658a1172ef 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -34,6 +34,7 @@ #define MAX_EA_VALUE_SIZE CIFSMaxBufSize #define CIFS_XATTR_CIFS_ACL "system.cifs_acl" /* DACL only */ #define CIFS_XATTR_CIFS_NTSD "system.cifs_ntsd" /* owner plus DACL */ +#define CIFS_XATTR_CIFS_NTSD_FULL "system.cifs_ntsd_full" /* owner/DACL/SACL */ #define CIFS_XATTR_ATTRIB "cifs.dosattrib" /* full name: user.cifs.dosattrib */ #define CIFS_XATTR_CREATETIME "cifs.creationtime" /* user.cifs.creationtime */ /* @@ -43,12 +44,13 @@ */ #define SMB3_XATTR_CIFS_ACL "system.smb3_acl" /* DACL only */ #define SMB3_XATTR_CIFS_NTSD "system.smb3_ntsd" /* owner plus DACL */ +#define SMB3_XATTR_CIFS_NTSD_FULL "system.smb3_ntsd_full" /* owner/DACL/SACL */ #define SMB3_XATTR_ATTRIB "smb3.dosattrib" /* full name: user.smb3.dosattrib */ #define SMB3_XATTR_CREATETIME "smb3.creationtime" /* user.smb3.creationtime */ /* BB need to add server (Samba e.g) support for security and trusted prefix */ enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT, - XATTR_CIFS_NTSD }; + XATTR_CIFS_NTSD, XATTR_CIFS_NTSD_FULL }; static int cifs_attrib_set(unsigned int xid, struct cifs_tcon *pTcon, struct inode *inode, char *full_path, @@ -164,7 +166,8 @@ static int cifs_xattr_set(const struct xattr_handler *handler, break; case XATTR_CIFS_ACL: - case XATTR_CIFS_NTSD: { + case XATTR_CIFS_NTSD: + case XATTR_CIFS_NTSD_FULL: { struct cifs_ntsd *pacl; if (!value) @@ -174,23 +177,27 @@ static int cifs_xattr_set(const struct xattr_handler *handler, rc = -ENOMEM; } else { memcpy(pacl, value, size); - if (value && - pTcon->ses->server->ops->set_acl) { + if (pTcon->ses->server->ops->set_acl) { + int aclflags = 0; rc = 0; - if (handler->flags == XATTR_CIFS_NTSD) { - /* set owner and DACL */ - rc = pTcon->ses->server->ops->set_acl( - pacl, size, inode, - full_path, - CIFS_ACL_OWNER); - } - if (rc == 0) { - /* set DACL */ - rc = pTcon->ses->server->ops->set_acl( - pacl, size, inode, - full_path, - CIFS_ACL_DACL); + + switch (handler->flags) { + case XATTR_CIFS_NTSD_FULL: + aclflags = (CIFS_ACL_OWNER | + CIFS_ACL_DACL | + CIFS_ACL_SACL); + break; + case XATTR_CIFS_NTSD: + aclflags = (CIFS_ACL_OWNER | + CIFS_ACL_DACL); + break; + case XATTR_CIFS_ACL: + default: + aclflags = CIFS_ACL_DACL; } + + rc = pTcon->ses->server->ops->set_acl(pacl, + size, inode, full_path, aclflags); } else { rc = -EOPNOTSUPP; } @@ -327,16 +334,25 @@ static int cifs_xattr_get(const struct xattr_handler *handler, break; case XATTR_CIFS_ACL: - case XATTR_CIFS_NTSD: { - /* the whole ntsd is fetched regardless */ - u32 acllen; + case XATTR_CIFS_NTSD: + case XATTR_CIFS_NTSD_FULL: { + /* + * fetch owner, DACL, and SACL if asked for full descriptor, + * fetch owner and DACL otherwise + */ + u32 acllen, extra_info; struct cifs_ntsd *pacl; if (pTcon->ses->server->ops->get_acl == NULL) goto out; /* rc already EOPNOTSUPP */ + if (handler->flags == XATTR_CIFS_NTSD_FULL) { + extra_info = SACL_SECINFO; + } else { + extra_info = 0; + } pacl = pTcon->ses->server->ops->get_acl(cifs_sb, - inode, full_path, &acllen); + inode, full_path, &acllen, extra_info); if (IS_ERR(pacl)) { rc = PTR_ERR(pacl); cifs_dbg(VFS, "%s: error %zd getting sec desc\n", @@ -486,6 +502,27 @@ static const struct xattr_handler smb3_ntsd_xattr_handler = { .set = cifs_xattr_set, }; +static const struct xattr_handler cifs_cifs_ntsd_full_xattr_handler = { + .name = CIFS_XATTR_CIFS_NTSD_FULL, + .flags = XATTR_CIFS_NTSD_FULL, + .get = cifs_xattr_get, + .set = cifs_xattr_set, +}; + +/* + * Although this is just an alias for the above, need to move away from + * confusing users and using the 20 year old term 'cifs' when it is no + * longer secure and was replaced by SMB2/SMB3 a long time ago, and + * SMB3 and later are highly secure. + */ +static const struct xattr_handler smb3_ntsd_full_xattr_handler = { + .name = SMB3_XATTR_CIFS_NTSD_FULL, + .flags = XATTR_CIFS_NTSD_FULL, + .get = cifs_xattr_get, + .set = cifs_xattr_set, +}; + + static const struct xattr_handler cifs_posix_acl_access_xattr_handler = { .name = XATTR_NAME_POSIX_ACL_ACCESS, .flags = XATTR_ACL_ACCESS, @@ -507,6 +544,8 @@ const struct xattr_handler *cifs_xattr_handlers[] = { &smb3_acl_xattr_handler, /* alias for above since avoiding "cifs" */ &cifs_cifs_ntsd_xattr_handler, &smb3_ntsd_xattr_handler, /* alias for above since avoiding "cifs" */ + &cifs_cifs_ntsd_full_xattr_handler, + &smb3_ntsd_full_xattr_handler, /* alias for above since avoiding "cifs" */ &cifs_posix_acl_access_xattr_handler, &cifs_posix_acl_default_xattr_handler, NULL diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index 2c557229696a..95e72d271b95 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -50,6 +50,7 @@ * which requires asm/elf.h to define compat_elf_gregset_t et al. */ #define elf_prstatus compat_elf_prstatus +#define elf_prstatus_common compat_elf_prstatus_common #define elf_prpsinfo compat_elf_prpsinfo #undef ns_to_kernel_old_timeval @@ -61,7 +62,6 @@ * differ from the native ones, or omitted when they match. */ -#undef ELF_ARCH #undef elf_check_arch #define elf_check_arch compat_elf_check_arch @@ -90,11 +90,6 @@ #define ELF_ET_DYN_BASE COMPAT_ELF_ET_DYN_BASE #endif -#ifdef COMPAT_ELF_EXEC_PAGESIZE -#undef ELF_EXEC_PAGESIZE -#define ELF_EXEC_PAGESIZE COMPAT_ELF_EXEC_PAGESIZE -#endif - #ifdef COMPAT_ELF_PLAT_INIT #undef ELF_PLAT_INIT #define ELF_PLAT_INIT COMPAT_ELF_PLAT_INIT diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index b0983e2a4e2c..b839dd1b459f 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -267,6 +267,7 @@ static void configfs_remove_dirent(struct dentry *dentry) * configfs_create_dir - create a directory for an config_item. * @item: config_itemwe're creating directory for. * @dentry: config_item's dentry. + * @frag: config_item's fragment. * * Note: user-created entries won't be allowed under this new directory * until it is validated by configfs_dir_set_ready() diff --git a/fs/dcache.c b/fs/dcache.c index ea0485861d93..97e81a844a96 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -793,10 +793,17 @@ static inline bool fast_dput(struct dentry *dentry) * a reference to the dentry and change that, but * our work is done - we can leave the dentry * around with a zero refcount. + * + * Nevertheless, there are two cases that we should kill + * the dentry anyway. + * 1. free disconnected dentries as soon as their refcount + * reached zero. + * 2. free dentries if they should not be cached. */ smp_rmb(); d_flags = READ_ONCE(dentry->d_flags); - d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED; + d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | + DCACHE_DISCONNECTED | DCACHE_DONTCACHE; /* Nothing to do? Dropping the reference was all we needed? */ if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry)) diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index e23752d9a79f..58d0f7187997 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -1016,15 +1016,19 @@ ecryptfs_setxattr(struct dentry *dentry, struct inode *inode, { int rc; struct dentry *lower_dentry; + struct inode *lower_inode; lower_dentry = ecryptfs_dentry_to_lower(dentry); - if (!(d_inode(lower_dentry)->i_opflags & IOP_XATTR)) { + lower_inode = d_inode(lower_dentry); + if (!(lower_inode->i_opflags & IOP_XATTR)) { rc = -EOPNOTSUPP; goto out; } - rc = vfs_setxattr(lower_dentry, name, value, size, flags); + inode_lock(lower_inode); + rc = __vfs_setxattr_locked(lower_dentry, name, value, size, flags, NULL); + inode_unlock(lower_inode); if (!rc && inode) - fsstack_copy_attr_all(inode, d_inode(lower_dentry)); + fsstack_copy_attr_all(inode, lower_inode); out: return rc; } diff --git a/fs/eventfd.c b/fs/eventfd.c index df466ef81ddd..e265b6dd4f34 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -182,11 +182,14 @@ static __poll_t eventfd_poll(struct file *file, poll_table *wait) return events; } -static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) +void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) { + lockdep_assert_held(&ctx->wqh.lock); + *cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count; ctx->count -= *cnt; } +EXPORT_SYMBOL_GPL(eventfd_ctx_do_read); /** * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue. diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 10b81e69db74..a829af074eb5 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -389,19 +389,24 @@ static bool ep_busy_loop_end(void *p, unsigned long start_time) * * we must do our busy polling with irqs enabled */ -static void ep_busy_loop(struct eventpoll *ep, int nonblock) +static bool ep_busy_loop(struct eventpoll *ep, int nonblock) { unsigned int napi_id = READ_ONCE(ep->napi_id); - if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on()) + if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on()) { napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, false, BUSY_POLL_BUDGET); -} - -static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep) -{ - if (ep->napi_id) + if (ep_events_available(ep)) + return true; + /* + * Busy poll timed out. Drop NAPI ID for now, we can add + * it back in when we have moved a socket with a valid NAPI + * ID onto the ready list. + */ ep->napi_id = 0; + return false; + } + return false; } /* @@ -441,12 +446,9 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) #else -static inline void ep_busy_loop(struct eventpoll *ep, int nonblock) -{ -} - -static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep) +static inline bool ep_busy_loop(struct eventpoll *ep, int nonblock) { + return false; } static inline void ep_set_busy_poll_napi_id(struct epitem *epi) @@ -1625,6 +1627,14 @@ static int ep_send_events(struct eventpoll *ep, poll_table pt; int res = 0; + /* + * Always short-circuit for fatal signals to allow threads to make a + * timely exit without the chance of finding more events available and + * fetching repeatedly. + */ + if (fatal_signal_pending(current)) + return -EINTR; + init_poll_funcptr(&pt, NULL); mutex_lock(&ep->mtx); @@ -1702,15 +1712,25 @@ static int ep_send_events(struct eventpoll *ep, return res; } -static inline struct timespec64 ep_set_mstimeout(long ms) +static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms) { - struct timespec64 now, ts = { - .tv_sec = ms / MSEC_PER_SEC, - .tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC), - }; + struct timespec64 now; + + if (ms < 0) + return NULL; + + if (!ms) { + to->tv_sec = 0; + to->tv_nsec = 0; + return to; + } + + to->tv_sec = ms / MSEC_PER_SEC; + to->tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC); ktime_get_ts64(&now); - return timespec64_add_safe(now, ts); + *to = timespec64_add_safe(now, *to); + return to; } /** @@ -1722,8 +1742,8 @@ static inline struct timespec64 ep_set_mstimeout(long ms) * stored. * @maxevents: Size (in terms of number of events) of the caller event buffer. * @timeout: Maximum timeout for the ready events fetch operation, in - * milliseconds. If the @timeout is zero, the function will not block, - * while if the @timeout is less than zero, the function will block + * timespec. If the timeout is zero, the function will not block, + * while if the @timeout ptr is NULL, the function will block * until at least one event has been retrieved (or an error * occurred). * @@ -1731,55 +1751,59 @@ static inline struct timespec64 ep_set_mstimeout(long ms) * error code, in case of error. */ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, - int maxevents, long timeout) + int maxevents, struct timespec64 *timeout) { - int res = 0, eavail, timed_out = 0; + int res, eavail, timed_out = 0; u64 slack = 0; wait_queue_entry_t wait; ktime_t expires, *to = NULL; lockdep_assert_irqs_enabled(); - if (timeout > 0) { - struct timespec64 end_time = ep_set_mstimeout(timeout); - - slack = select_estimate_accuracy(&end_time); + if (timeout && (timeout->tv_sec | timeout->tv_nsec)) { + slack = select_estimate_accuracy(timeout); to = &expires; - *to = timespec64_to_ktime(end_time); - } else if (timeout == 0) { + *to = timespec64_to_ktime(*timeout); + } else if (timeout) { /* * Avoid the unnecessary trip to the wait queue loop, if the - * caller specified a non blocking operation. We still need - * lock because we could race and not see an epi being added - * to the ready list while in irq callback. Thus incorrectly - * returning 0 back to userspace. + * caller specified a non blocking operation. */ timed_out = 1; - - write_lock_irq(&ep->lock); - eavail = ep_events_available(ep); - write_unlock_irq(&ep->lock); - - goto send_events; } -fetch_events: + /* + * This call is racy: We may or may not see events that are being added + * to the ready list under the lock (e.g., in IRQ callbacks). For, cases + * with a non-zero timeout, this thread will check the ready list under + * lock and will added to the wait queue. For, cases with a zero + * timeout, the user by definition should not care and will have to + * recheck again. + */ + eavail = ep_events_available(ep); + + while (1) { + if (eavail) { + /* + * Try to transfer events to user space. In case we get + * 0 events and there's still timeout left over, we go + * trying again in search of more luck. + */ + res = ep_send_events(ep, events, maxevents); + if (res) + return res; + } - if (!ep_events_available(ep)) - ep_busy_loop(ep, timed_out); + if (timed_out) + return 0; - eavail = ep_events_available(ep); - if (eavail) - goto send_events; + eavail = ep_busy_loop(ep, timed_out); + if (eavail) + continue; - /* - * Busy poll timed out. Drop NAPI ID for now, we can add - * it back in when we have moved a socket with a valid NAPI - * ID onto the ready list. - */ - ep_reset_busy_poll_napi_id(ep); + if (signal_pending(current)) + return -EINTR; - do { /* * Internally init_wait() uses autoremove_wake_function(), * thus wait entry is removed from the wait queue on each @@ -1809,55 +1833,38 @@ fetch_events: * important. */ eavail = ep_events_available(ep); - if (!eavail) { - if (signal_pending(current)) - res = -EINTR; - else - __add_wait_queue_exclusive(&ep->wq, &wait); - } - write_unlock_irq(&ep->lock); - - if (eavail || res) - break; - - if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) { - timed_out = 1; - break; - } - - /* We were woken up, thus go and try to harvest some events */ - eavail = 1; - - } while (0); + if (!eavail) + __add_wait_queue_exclusive(&ep->wq, &wait); - __set_current_state(TASK_RUNNING); - - if (!list_empty_careful(&wait.entry)) { - write_lock_irq(&ep->lock); - __remove_wait_queue(&ep->wq, &wait); write_unlock_irq(&ep->lock); - } -send_events: - if (fatal_signal_pending(current)) { + if (!eavail) + timed_out = !schedule_hrtimeout_range(to, slack, + HRTIMER_MODE_ABS); + __set_current_state(TASK_RUNNING); + /* - * Always short-circuit for fatal signals to allow - * threads to make a timely exit without the chance of - * finding more events available and fetching - * repeatedly. + * We were woken up, thus go and try to harvest some events. + * If timed out and still on the wait queue, recheck eavail + * carefully under lock, below. */ - res = -EINTR; - } - /* - * Try to transfer events to user space. In case we get 0 events and - * there's still timeout left over, we go trying again in search of - * more luck. - */ - if (!res && eavail && - !(res = ep_send_events(ep, events, maxevents)) && !timed_out) - goto fetch_events; + eavail = 1; - return res; + if (!list_empty_careful(&wait.entry)) { + write_lock_irq(&ep->lock); + /* + * If the thread timed out and is not on the wait queue, + * it means that the thread was woken up after its + * timeout expired before it could reacquire the lock. + * Thus, when wait.entry is empty, it needs to harvest + * events. + */ + if (timed_out) + eavail = list_empty(&wait.entry); + __remove_wait_queue(&ep->wq, &wait); + write_unlock_irq(&ep->lock); + } + } } /** @@ -2176,7 +2183,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, * part of the user space epoll_wait(2). */ static int do_epoll_wait(int epfd, struct epoll_event __user *events, - int maxevents, int timeout) + int maxevents, struct timespec64 *to) { int error; struct fd f; @@ -2210,7 +2217,7 @@ static int do_epoll_wait(int epfd, struct epoll_event __user *events, ep = f.file->private_data; /* Time to fish for events ... */ - error = ep_poll(ep, events, maxevents, timeout); + error = ep_poll(ep, events, maxevents, to); error_fput: fdput(f); @@ -2220,16 +2227,19 @@ error_fput: SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout) { - return do_epoll_wait(epfd, events, maxevents, timeout); + struct timespec64 to; + + return do_epoll_wait(epfd, events, maxevents, + ep_timeout_to_timespec(&to, timeout)); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). */ -SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, - int, maxevents, int, timeout, const sigset_t __user *, sigmask, - size_t, sigsetsize) +static int do_epoll_pwait(int epfd, struct epoll_event __user *events, + int maxevents, struct timespec64 *to, + const sigset_t __user *sigmask, size_t sigsetsize) { int error; @@ -2241,18 +2251,47 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, if (error) return error; - error = do_epoll_wait(epfd, events, maxevents, timeout); + error = do_epoll_wait(epfd, events, maxevents, to); + restore_saved_sigmask_unless(error == -EINTR); return error; } +SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, + int, maxevents, int, timeout, const sigset_t __user *, sigmask, + size_t, sigsetsize) +{ + struct timespec64 to; + + return do_epoll_pwait(epfd, events, maxevents, + ep_timeout_to_timespec(&to, timeout), + sigmask, sigsetsize); +} + +SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, + int, maxevents, const struct __kernel_timespec __user *, timeout, + const sigset_t __user *, sigmask, size_t, sigsetsize) +{ + struct timespec64 ts, *to = NULL; + + if (timeout) { + if (get_timespec64(&ts, timeout)) + return -EFAULT; + to = &ts; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; + } + + return do_epoll_pwait(epfd, events, maxevents, to, + sigmask, sigsetsize); +} + #ifdef CONFIG_COMPAT -COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, - struct epoll_event __user *, events, - int, maxevents, int, timeout, - const compat_sigset_t __user *, sigmask, - compat_size_t, sigsetsize) +static int do_compat_epoll_pwait(int epfd, struct epoll_event __user *events, + int maxevents, struct timespec64 *timeout, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize) { long err; @@ -2265,10 +2304,46 @@ COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, return err; err = do_epoll_wait(epfd, events, maxevents, timeout); + restore_saved_sigmask_unless(err == -EINTR); return err; } + +COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, + struct epoll_event __user *, events, + int, maxevents, int, timeout, + const compat_sigset_t __user *, sigmask, + compat_size_t, sigsetsize) +{ + struct timespec64 to; + + return do_compat_epoll_pwait(epfd, events, maxevents, + ep_timeout_to_timespec(&to, timeout), + sigmask, sigsetsize); +} + +COMPAT_SYSCALL_DEFINE6(epoll_pwait2, int, epfd, + struct epoll_event __user *, events, + int, maxevents, + const struct __kernel_timespec __user *, timeout, + const compat_sigset_t __user *, sigmask, + compat_size_t, sigsetsize) +{ + struct timespec64 ts, *to = NULL; + + if (timeout) { + if (get_timespec64(&ts, timeout)) + return -EFAULT; + to = &ts; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; + } + + return do_compat_epoll_pwait(epfd, events, maxevents, to, + sigmask, sigsetsize); +} + #endif static int __init eventpoll_init(void) diff --git a/fs/exfat/nls.c b/fs/exfat/nls.c index 675d0e7058c5..314d5407a1be 100644 --- a/fs/exfat/nls.c +++ b/fs/exfat/nls.c @@ -659,7 +659,7 @@ static int exfat_load_upcase_table(struct super_block *sb, unsigned char skip = false; unsigned short *upcase_table; - upcase_table = kcalloc(UTBL_COUNT, sizeof(unsigned short), GFP_KERNEL); + upcase_table = kvcalloc(UTBL_COUNT, sizeof(unsigned short), GFP_KERNEL); if (!upcase_table) return -ENOMEM; @@ -715,7 +715,7 @@ static int exfat_load_default_upcase_table(struct super_block *sb) unsigned short uni = 0, *upcase_table; unsigned int index = 0; - upcase_table = kcalloc(UTBL_COUNT, sizeof(unsigned short), GFP_KERNEL); + upcase_table = kvcalloc(UTBL_COUNT, sizeof(unsigned short), GFP_KERNEL); if (!upcase_table) return -ENOMEM; @@ -803,5 +803,5 @@ load_default: void exfat_free_upcase_table(struct exfat_sb_info *sbi) { - kfree(sbi->vol_utbl); + kvfree(sbi->vol_utbl); } diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 1d640b145637..f45f9feebe59 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -185,7 +185,7 @@ static int ext4_init_block_bitmap(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t start, tmp; - J_ASSERT_BH(bh, buffer_locked(bh)); + ASSERT(buffer_locked(bh)); /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 8e6ca23ed172..4666b55b736e 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -176,12 +176,10 @@ static int ext4_protect_reserved_inode(struct super_block *sb, err = add_system_zone(system_blks, map.m_pblk, n, ino); if (err < 0) { if (err == -EFSCORRUPTED) { - __ext4_error(sb, __func__, __LINE__, - -err, map.m_pblk, - "blocks %llu-%llu from inode %u overlap system zone", - map.m_pblk, - map.m_pblk + map.m_len - 1, - ino); + EXT4_ERROR_INODE_ERR(inode, -err, + "blocks %llu-%llu from inode overlap system zone", + map.m_pblk, + map.m_pblk + map.m_len - 1); } break; } @@ -206,7 +204,7 @@ static void ext4_destroy_system_zone(struct rcu_head *rcu) * * The update of system_blks pointer in this function is protected by * sb->s_umount semaphore. However we have to be careful as we can be - * racing with ext4_data_block_valid() calls reading system_blks rbtree + * racing with ext4_inode_block_valid() calls reading system_blks rbtree * protected only by RCU. That's why we first build the rbtree and then * swap it in place. */ @@ -258,7 +256,7 @@ int ext4_setup_system_zone(struct super_block *sb) /* * System blks rbtree complete, announce it once to prevent racing - * with ext4_data_block_valid() accessing the rbtree at the same + * with ext4_inode_block_valid() accessing the rbtree at the same * time. */ rcu_assign_pointer(sbi->s_system_blks, system_blks); @@ -278,7 +276,7 @@ err: * * The update of system_blks pointer in this function is protected by * sb->s_umount semaphore. However we have to be careful as we can be - * racing with ext4_data_block_valid() calls reading system_blks rbtree + * racing with ext4_inode_block_valid() calls reading system_blks rbtree * protected only by RCU. So we first clear the system_blks pointer and * then free the rbtree only after RCU grace period expires. */ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c64ea8f59ea7..2866d249f3d2 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -98,6 +98,16 @@ #define ext_debug(ino, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif +#define ASSERT(assert) \ +do { \ + if (unlikely(!(assert))) { \ + printk(KERN_EMERG \ + "Assertion failure in %s() at %s:%d: '%s'\n", \ + __func__, __FILE__, __LINE__, #assert); \ + BUG(); \ + } \ +} while (0) + /* data type for block offset of block group */ typedef int ext4_grpblk_t; @@ -1619,6 +1629,27 @@ struct ext4_sb_info { errseq_t s_bdev_wb_err; spinlock_t s_bdev_wb_lock; + /* Information about errors that happened during this mount */ + spinlock_t s_error_lock; + int s_add_error_count; + int s_first_error_code; + __u32 s_first_error_line; + __u32 s_first_error_ino; + __u64 s_first_error_block; + const char *s_first_error_func; + time64_t s_first_error_time; + int s_last_error_code; + __u32 s_last_error_line; + __u32 s_last_error_ino; + __u64 s_last_error_block; + const char *s_last_error_func; + time64_t s_last_error_time; + /* + * If we are in a context where we cannot update error information in + * the on-disk superblock, we queue this work to do it. + */ + struct work_struct s_error_work; + /* Ext4 fast commit stuff */ atomic_t s_fc_subtid; atomic_t s_fc_ineligible_updates; @@ -1858,7 +1889,6 @@ static inline bool ext4_verity_in_progress(struct inode *inode) #define EXT4_GOOD_OLD_REV 0 /* The good old (original) format */ #define EXT4_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */ -#define EXT4_CURRENT_REV EXT4_GOOD_OLD_REV #define EXT4_MAX_SUPP_REV EXT4_DYNAMIC_REV #define EXT4_GOOD_OLD_INODE_SIZE 128 @@ -2952,9 +2982,9 @@ extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t block_group, unsigned int flags); -extern __printf(6, 7) -void __ext4_error(struct super_block *, const char *, unsigned int, int, __u64, - const char *, ...); +extern __printf(7, 8) +void __ext4_error(struct super_block *, const char *, unsigned int, bool, + int, __u64, const char *, ...); extern __printf(6, 7) void __ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t, int, const char *, ...); @@ -2963,9 +2993,6 @@ void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t, const char *, ...); extern void __ext4_std_error(struct super_block *, const char *, unsigned int, int); -extern __printf(5, 6) -void __ext4_abort(struct super_block *, const char *, unsigned int, int, - const char *, ...); extern __printf(4, 5) void __ext4_warning(struct super_block *, const char *, unsigned int, const char *, ...); @@ -2995,6 +3022,9 @@ void __ext4_grp_locked_error(const char *, unsigned int, #define EXT4_ERROR_FILE(file, block, fmt, a...) \ ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a) +#define ext4_abort(sb, err, fmt, a...) \ + __ext4_error((sb), __func__, __LINE__, true, (err), 0, (fmt), ## a) + #ifdef CONFIG_PRINTK #define ext4_error_inode(inode, func, line, block, fmt, ...) \ @@ -3005,11 +3035,11 @@ void __ext4_grp_locked_error(const char *, unsigned int, #define ext4_error_file(file, func, line, block, fmt, ...) \ __ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__) #define ext4_error(sb, fmt, ...) \ - __ext4_error((sb), __func__, __LINE__, 0, 0, (fmt), ##__VA_ARGS__) + __ext4_error((sb), __func__, __LINE__, false, 0, 0, (fmt), \ + ##__VA_ARGS__) #define ext4_error_err(sb, err, fmt, ...) \ - __ext4_error((sb), __func__, __LINE__, (err), 0, (fmt), ##__VA_ARGS__) -#define ext4_abort(sb, err, fmt, ...) \ - __ext4_abort((sb), __func__, __LINE__, (err), (fmt), ##__VA_ARGS__) + __ext4_error((sb), __func__, __LINE__, false, (err), 0, (fmt), \ + ##__VA_ARGS__) #define ext4_warning(sb, fmt, ...) \ __ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__) #define ext4_warning_inode(inode, fmt, ...) \ @@ -3042,17 +3072,12 @@ do { \ #define ext4_error(sb, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ - __ext4_error(sb, "", 0, 0, 0, " "); \ + __ext4_error(sb, "", 0, false, 0, 0, " "); \ } while (0) #define ext4_error_err(sb, err, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ - __ext4_error(sb, "", 0, err, 0, " "); \ -} while (0) -#define ext4_abort(sb, err, fmt, ...) \ -do { \ - no_printk(fmt, ##__VA_ARGS__); \ - __ext4_abort(sb, "", 0, err, " "); \ + __ext4_error(sb, "", 0, false, err, 0, " "); \ } while (0) #define ext4_warning(sb, fmt, ...) \ do { \ @@ -3361,6 +3386,21 @@ static inline void ext4_unlock_group(struct super_block *sb, spin_unlock(ext4_group_lock_ptr(sb, group)); } +#ifdef CONFIG_QUOTA +static inline bool ext4_quota_capable(struct super_block *sb) +{ + return (test_opt(sb, QUOTA) || ext4_has_feature_quota(sb)); +} + +static inline bool ext4_is_quota_journalled(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + return (ext4_has_feature_quota(sb) || + sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]); +} +#endif + /* * Block validity checking */ @@ -3609,7 +3649,6 @@ extern void ext4_io_submit(struct ext4_io_submit *io); extern int ext4_bio_write_page(struct ext4_io_submit *io, struct page *page, int len, - struct writeback_control *wbc, bool keep_towrite); extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end); extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end); diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 0fd0c42a4f7d..be799040a415 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -296,8 +296,8 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle, if (err) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); - __ext4_abort(inode->i_sb, where, line, -err, - "error %d when attempting revoke", err); + __ext4_error(inode->i_sb, where, line, true, -err, 0, + "error %d when attempting revoke", err); } BUFFER_TRACE(bh, "exit"); return err; @@ -372,20 +372,3 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, } return err; } - -int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb) -{ - struct buffer_head *bh = EXT4_SB(sb)->s_sbh; - int err = 0; - - ext4_superblock_csum_set(sb); - if (ext4_handle_valid(handle)) { - err = jbd2_journal_dirty_metadata(handle, bh); - if (err) - ext4_journal_abort_handle(where, line, __func__, - bh, handle, err); - } else - mark_buffer_dirty(bh); - return err; -} diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 00dc668e052b..0d2fa423b7ad 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -86,17 +86,14 @@ #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ -#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ - ext4_has_feature_quota(sb)) ? 1 : 0) +#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ -#define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ - ext4_has_feature_quota(sb)) ?\ +#define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_INIT_REWRITE) : 0) -#define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ - ext4_has_feature_quota(sb)) ?\ +#define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_DEL_REWRITE) : 0) #else @@ -247,9 +244,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh); -int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb); - #define ext4_journal_get_write_access(handle, bh) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh)) #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \ @@ -260,8 +254,6 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) -#define ext4_handle_dirty_super(handle, sb) \ - __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb)) handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 17d7096b3212..3960b7ec3ab7 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5815,8 +5815,8 @@ int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start, int ret; path = ext4_find_extent(inode, start, NULL, 0); - if (!path) - return -EINVAL; + if (IS_ERR(path)) + return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) { ret = -EFSCORRUPTED; @@ -5988,7 +5988,6 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) kfree(path); break; } - ex = path2[path2->p_depth].p_ext; for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) { cmp1 = cmp2 = 0; if (i <= path->p_depth) diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index f2033e13a273..0a14a7c87bf8 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -103,8 +103,69 @@ * * Replay code should thus check for all the valid tails in the FC area. * + * Fast Commit Replay Idempotence + * ------------------------------ + * + * Fast commits tags are idempotent in nature provided the recovery code follows + * certain rules. The guiding principle that the commit path follows while + * committing is that it stores the result of a particular operation instead of + * storing the procedure. + * + * Let's consider this rename operation: 'mv /a /b'. Let's assume dirent '/a' + * was associated with inode 10. During fast commit, instead of storing this + * operation as a procedure "rename a to b", we store the resulting file system + * state as a "series" of outcomes: + * + * - Link dirent b to inode 10 + * - Unlink dirent a + * - Inode <10> with valid refcount + * + * Now when recovery code runs, it needs "enforce" this state on the file + * system. This is what guarantees idempotence of fast commit replay. + * + * Let's take an example of a procedure that is not idempotent and see how fast + * commits make it idempotent. Consider following sequence of operations: + * + * rm A; mv B A; read A + * (x) (y) (z) + * + * (x), (y) and (z) are the points at which we can crash. If we store this + * sequence of operations as is then the replay is not idempotent. Let's say + * while in replay, we crash at (z). During the second replay, file A (which was + * actually created as a result of "mv B A" operation) would get deleted. Thus, + * file named A would be absent when we try to read A. So, this sequence of + * operations is not idempotent. However, as mentioned above, instead of storing + * the procedure fast commits store the outcome of each procedure. Thus the fast + * commit log for above procedure would be as follows: + * + * (Let's assume dirent A was linked to inode 10 and dirent B was linked to + * inode 11 before the replay) + * + * [Unlink A] [Link A to inode 11] [Unlink B] [Inode 11] + * (w) (x) (y) (z) + * + * If we crash at (z), we will have file A linked to inode 11. During the second + * replay, we will remove file A (inode 11). But we will create it back and make + * it point to inode 11. We won't find B, so we'll just skip that step. At this + * point, the refcount for inode 11 is not reliable, but that gets fixed by the + * replay of last inode 11 tag. Crashes at points (w), (x) and (y) get handled + * similarly. Thus, by converting a non-idempotent procedure into a series of + * idempotent outcomes, fast commits ensured idempotence during the replay. + * * TODOs * ----- + * + * 0) Fast commit replay path hardening: Fast commit replay code should use + * journal handles to make sure all the updates it does during the replay + * path are atomic. With that if we crash during fast commit replay, after + * trying to do recovery again, we will find a file system where fast commit + * area is invalid (because new full commit would be found). In order to deal + * with that, fast commit replay code should ensure that the "FC_REPLAY" + * superblock state is persisted before starting the replay, so that after + * the crash, fast commit recovery code can look at that flag and perform + * fast commit recovery even if that area is invalidated by later full + * commits. + * * 1) Make fast commit atomic updates more fine grained. Today, a fast commit * eligible update must be protected within ext4_fc_start_update() and * ext4_fc_stop_update(). These routines are called at much higher @@ -543,13 +604,13 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star trace_ext4_fc_track_range(inode, start, end, ret); } -static void ext4_fc_submit_bh(struct super_block *sb) +static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail) { int write_flags = REQ_SYNC; struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh; - /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */ - if (test_opt(sb, BARRIER)) + /* Add REQ_FUA | REQ_PREFLUSH only its tail */ + if (test_opt(sb, BARRIER) && is_tail) write_flags |= REQ_FUA | REQ_PREFLUSH; lock_buffer(bh); set_buffer_dirty(bh); @@ -623,7 +684,7 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc) *crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl)); if (pad_len > 0) ext4_fc_memzero(sb, tl + 1, pad_len, crc); - ext4_fc_submit_bh(sb); + ext4_fc_submit_bh(sb, false); ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh); if (ret) @@ -680,7 +741,7 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc) tail.fc_crc = cpu_to_le32(crc); ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL); - ext4_fc_submit_bh(sb); + ext4_fc_submit_bh(sb, true); return 0; } @@ -1207,7 +1268,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full) list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING], &sbi->s_fc_dentry_q[FC_Q_MAIN]); list_splice_init(&sbi->s_fc_q[FC_Q_STAGING], - &sbi->s_fc_q[FC_Q_STAGING]); + &sbi->s_fc_q[FC_Q_MAIN]); ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); @@ -1220,18 +1281,6 @@ static void ext4_fc_cleanup(journal_t *journal, int full) /* Ext4 Replay Path Routines */ -/* Get length of a particular tlv */ -static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl) -{ - return le16_to_cpu(tl->fc_len); -} - -/* Get a pointer to "value" of a tlv */ -static inline u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl) -{ - return (u8 *)tl + sizeof(*tl); -} - /* Helper struct for dentry replay routines */ struct dentry_info_args { int parent_ino, dname_len, ino, inode_len; @@ -1269,14 +1318,14 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl) entry.len = darg.dname_len; inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode %d not found", darg.ino); return 0; } old_parent = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(old_parent)) { + if (IS_ERR(old_parent)) { jbd_debug(1, "Dir with inode %d not found", darg.parent_ino); iput(inode); return 0; @@ -1361,7 +1410,7 @@ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl) darg.parent_ino, darg.dname_len); inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode not found."); return 0; } @@ -1417,10 +1466,11 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl) trace_ext4_fc_replay(sb, tag, ino, 0, 0); inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); - if (!IS_ERR_OR_NULL(inode)) { + if (!IS_ERR(inode)) { ext4_ext_clear_bb(inode); iput(inode); } + inode = NULL; ext4_fc_record_modified_inode(sb, ino); @@ -1463,7 +1513,7 @@ 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_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode not found."); return -EFSCORRUPTED; } @@ -1515,7 +1565,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl) goto out; inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "inode %d not found.", darg.ino); inode = NULL; ret = -EINVAL; @@ -1528,7 +1578,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl) * dot and dot dot dirents are setup properly. */ dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(dir)) { + if (IS_ERR(dir)) { jbd_debug(1, "Dir %d not found.", darg.ino); goto out; } @@ -1604,7 +1654,7 @@ 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_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode not found."); return 0; } @@ -1728,7 +1778,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl) le32_to_cpu(lrange->fc_ino), cur, remaining); inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino)); return 0; } @@ -1770,32 +1820,6 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl) return 0; } -static inline const char *tag2str(u16 tag) -{ - switch (tag) { - case EXT4_FC_TAG_LINK: - return "TAG_ADD_ENTRY"; - case EXT4_FC_TAG_UNLINK: - return "TAG_DEL_ENTRY"; - case EXT4_FC_TAG_ADD_RANGE: - return "TAG_ADD_RANGE"; - case EXT4_FC_TAG_CREAT: - return "TAG_CREAT_DENTRY"; - case EXT4_FC_TAG_DEL_RANGE: - return "TAG_DEL_RANGE"; - case EXT4_FC_TAG_INODE: - return "TAG_INODE"; - case EXT4_FC_TAG_PAD: - return "TAG_PAD"; - case EXT4_FC_TAG_TAIL: - return "TAG_TAIL"; - case EXT4_FC_TAG_HEAD: - return "TAG_HEAD"; - default: - return "TAG_ERROR"; - } -} - static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) { struct ext4_fc_replay_state *state; @@ -1809,7 +1833,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) for (i = 0; i < state->fc_modified_inodes_used; i++) { inode = ext4_iget(sb, state->fc_modified_inodes[i], EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode %d not found.", state->fc_modified_inodes[i]); continue; @@ -1826,7 +1850,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) if (ret > 0) { path = ext4_find_extent(inode, map.m_lblk, NULL, 0); - if (!IS_ERR_OR_NULL(path)) { + if (!IS_ERR(path)) { for (j = 0; j < path->p_depth; j++) ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, 1); diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h index 3a6e5a1fa1b8..b77f70f55a62 100644 --- a/fs/ext4/fast_commit.h +++ b/fs/ext4/fast_commit.h @@ -3,6 +3,11 @@ #ifndef __FAST_COMMIT_H__ #define __FAST_COMMIT_H__ +/* + * Note this file is present in e2fsprogs/lib/ext2fs/fast_commit.h and + * linux/fs/ext4/fast_commit.h. These file should always be byte identical. + */ + /* Fast commit tags */ #define EXT4_FC_TAG_ADD_RANGE 0x0001 #define EXT4_FC_TAG_DEL_RANGE 0x0002 @@ -50,7 +55,7 @@ struct ext4_fc_del_range { struct ext4_fc_dentry_info { __le32 fc_parent_ino; __le32 fc_ino; - u8 fc_dname[0]; + __u8 fc_dname[0]; }; /* Value structure for EXT4_FC_TAG_INODE and EXT4_FC_TAG_INODE_PARTIAL. */ @@ -66,19 +71,6 @@ struct ext4_fc_tail { }; /* - * In memory list of dentry updates that are performed on the file - * system used by fast commit code. - */ -struct ext4_fc_dentry_update { - int fcd_op; /* Type of update create / unlink / link */ - int fcd_parent; /* Parent inode number */ - int fcd_ino; /* Inode number */ - struct qstr fcd_name; /* Dirent name */ - unsigned char fcd_iname[DNAME_INLINE_LEN]; /* Dirent name string */ - struct list_head fcd_list; -}; - -/* * Fast commit reason codes */ enum { @@ -107,6 +99,20 @@ enum { EXT4_FC_REASON_MAX }; +#ifdef __KERNEL__ +/* + * In memory list of dentry updates that are performed on the file + * system used by fast commit code. + */ +struct ext4_fc_dentry_update { + int fcd_op; /* Type of update create / unlink / link */ + int fcd_parent; /* Parent inode number */ + int fcd_ino; /* Inode number */ + struct qstr fcd_name; /* Dirent name */ + unsigned char fcd_iname[DNAME_INLINE_LEN]; /* Dirent name string */ + struct list_head fcd_list; +}; + struct ext4_fc_stats { unsigned int fc_ineligible_reason_count[EXT4_FC_REASON_MAX]; unsigned long fc_num_commits; @@ -145,13 +151,51 @@ struct ext4_fc_replay_state { }; #define region_last(__region) (((__region)->lblk) + ((__region)->len) - 1) +#endif #define fc_for_each_tl(__start, __end, __tl) \ - for (tl = (struct ext4_fc_tl *)start; \ - (u8 *)tl < (u8 *)end; \ - tl = (struct ext4_fc_tl *)((u8 *)tl + \ + for (tl = (struct ext4_fc_tl *)(__start); \ + (__u8 *)tl < (__u8 *)(__end); \ + tl = (struct ext4_fc_tl *)((__u8 *)tl + \ sizeof(struct ext4_fc_tl) + \ + le16_to_cpu(tl->fc_len))) +static inline const char *tag2str(__u16 tag) +{ + switch (tag) { + case EXT4_FC_TAG_LINK: + return "ADD_ENTRY"; + case EXT4_FC_TAG_UNLINK: + return "DEL_ENTRY"; + case EXT4_FC_TAG_ADD_RANGE: + return "ADD_RANGE"; + case EXT4_FC_TAG_CREAT: + return "CREAT_DENTRY"; + case EXT4_FC_TAG_DEL_RANGE: + return "DEL_RANGE"; + case EXT4_FC_TAG_INODE: + return "INODE"; + case EXT4_FC_TAG_PAD: + return "PAD"; + case EXT4_FC_TAG_TAIL: + return "TAIL"; + case EXT4_FC_TAG_HEAD: + return "HEAD"; + default: + return "ERROR"; + } +} + +/* Get length of a particular tlv */ +static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl) +{ + return le16_to_cpu(tl->fc_len); +} + +/* Get a pointer to "value" of a tlv */ +static inline __u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl) +{ + return (__u8 *)tl + sizeof(*tl); +} #endif /* __FAST_COMMIT_H__ */ diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 3ed8c048fb12..349b27f0dda0 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -809,9 +809,12 @@ static int ext4_sample_last_mounted(struct super_block *sb, err = ext4_journal_get_write_access(handle, sbi->s_sbh); if (err) goto out_journal; - strlcpy(sbi->s_es->s_last_mounted, cp, + lock_buffer(sbi->s_sbh); + strncpy(sbi->s_es->s_last_mounted, cp, sizeof(sbi->s_es->s_last_mounted)); - ext4_handle_dirty_super(handle, sb); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); + ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); out_journal: ext4_journal_stop(handle); out: diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index a42ca95840f2..113bfb023a4a 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -136,7 +136,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (unlikely(ext4_forced_shutdown(sbi))) return -EIO; - J_ASSERT(ext4_journal_current_handle() == NULL); + ASSERT(ext4_journal_current_handle() == NULL); trace_ext4_sync_file_enter(file, datasync); diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 05efa682bc2f..1223a18c3ff9 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -534,8 +534,8 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, ext4_fsblk_t first_block = 0; trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); - J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))); - J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); + ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))); + ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); depth = ext4_block_to_path(inode, map->m_lblk, offsets, &blocks_to_boundary); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0d8385aea898..c173c8405856 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -175,6 +175,7 @@ void ext4_evict_inode(struct inode *inode) */ int extra_credits = 6; struct ext4_xattr_inode_array *ea_inode_array = NULL; + bool freeze_protected = false; trace_ext4_evict_inode(inode); @@ -232,9 +233,14 @@ void ext4_evict_inode(struct inode *inode) /* * Protect us against freezing - iput() caller didn't have to have any - * protection against it + * protection against it. When we are in a running transaction though, + * we are already protected against freezing and we cannot grab further + * protection due to lock ordering constraints. */ - sb_start_intwrite(inode->i_sb); + if (!ext4_journal_current_handle()) { + sb_start_intwrite(inode->i_sb); + freeze_protected = true; + } if (!IS_NOQUOTA(inode)) extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb); @@ -253,7 +259,8 @@ void ext4_evict_inode(struct inode *inode) * cleaned up. */ ext4_orphan_del(NULL, inode); - sb_end_intwrite(inode->i_sb); + if (freeze_protected) + sb_end_intwrite(inode->i_sb); goto no_delete; } @@ -294,7 +301,8 @@ void ext4_evict_inode(struct inode *inode) stop_handle: ext4_journal_stop(handle); ext4_orphan_del(NULL, inode); - sb_end_intwrite(inode->i_sb); + if (freeze_protected) + sb_end_intwrite(inode->i_sb); ext4_xattr_inode_array_free(ea_inode_array); goto no_delete; } @@ -323,7 +331,8 @@ stop_handle: else ext4_free_inode(handle, inode); ext4_journal_stop(handle); - sb_end_intwrite(inode->i_sb); + if (freeze_protected) + sb_end_intwrite(inode->i_sb); ext4_xattr_inode_array_free(ea_inode_array); return; no_delete: @@ -830,8 +839,8 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, int create = map_flags & EXT4_GET_BLOCKS_CREATE; int err; - J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) - || handle != NULL || create == 0); + ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) + || handle != NULL || create == 0); map.m_lblk = block; map.m_len = 1; @@ -846,9 +855,9 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, if (unlikely(!bh)) return ERR_PTR(-ENOMEM); if (map.m_flags & EXT4_MAP_NEW) { - J_ASSERT(create != 0); - J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) - || (handle != NULL)); + ASSERT(create != 0); + ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) + || (handle != NULL)); /* * Now that we do not always journal data, we should @@ -2055,7 +2064,7 @@ static int ext4_writepage(struct page *page, unlock_page(page); return -ENOMEM; } - ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite); + ret = ext4_bio_write_page(&io_submit, page, len, keep_towrite); ext4_io_submit(&io_submit); /* Drop io_end reference we got from init */ ext4_put_io_end_defer(io_submit.io_end); @@ -2089,7 +2098,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) len = size & ~PAGE_MASK; else len = PAGE_SIZE; - err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false); + err = ext4_bio_write_page(&mpd->io_submit, page, len, false); if (!err) mpd->wbc->nr_to_write--; mpd->first_page++; @@ -4610,7 +4619,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))) { if (flags & EXT4_IGET_HANDLE) return ERR_PTR(-ESTALE); - __ext4_error(sb, function, line, EFSCORRUPTED, 0, + __ext4_error(sb, function, line, false, EFSCORRUPTED, 0, "inode #%lu: comm %s: iget: illegal inode #", ino, current->comm); return ERR_PTR(-EFSCORRUPTED); @@ -5141,9 +5150,13 @@ static int ext4_do_update_inode(handle_t *handle, err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh); if (err) goto out_brelse; + lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_large_file(sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_handle_sync(handle); - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, + EXT4_SB(sb)->s_sbh); } ext4_update_inode_fsync_trans(handle, inode, need_datasync); out_brelse: diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 524e13432447..d9665d2f82db 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1157,7 +1157,10 @@ resizefs_out: err = ext4_journal_get_write_access(handle, sbi->s_sbh); if (err) goto pwsalt_err_journal; + lock_buffer(sbi->s_sbh); generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); pwsalt_err_journal: diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 24af9ed5c3e5..99bf091fee10 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -822,24 +822,6 @@ void ext4_mb_generate_buddy(struct super_block *sb, spin_unlock(&sbi->s_bal_lock); } -static void mb_regenerate_buddy(struct ext4_buddy *e4b) -{ - int count; - int order = 1; - void *buddy; - - while ((buddy = mb_find_buddy(e4b, order++, &count))) { - ext4_set_bits(buddy, 0, count); - } - e4b->bd_info->bb_fragments = 0; - memset(e4b->bd_info->bb_counters, 0, - sizeof(*e4b->bd_info->bb_counters) * - (e4b->bd_sb->s_blocksize_bits + 2)); - - ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, - e4b->bd_bitmap, e4b->bd_group); -} - /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -1307,22 +1289,18 @@ static void ext4_mb_unload_buddy(struct ext4_buddy *e4b) static int mb_find_order_for_block(struct ext4_buddy *e4b, int block) { - int order = 1; - int bb_incr = 1 << (e4b->bd_blkbits - 1); + int order = 1, max; void *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); BUG_ON(block >= (1 << (e4b->bd_blkbits + 3))); - bb = e4b->bd_buddy; while (order <= e4b->bd_blkbits + 1) { - block = block >> 1; - if (!mb_test_bit(block, bb)) { + bb = mb_find_buddy(e4b, order, &max); + if (!mb_test_bit(block >> order, bb)) { /* this block is part of buddy of order 'order' */ return order; } - bb += bb_incr; - bb_incr >>= 1; order++; } return 0; @@ -1512,7 +1490,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } - mb_regenerate_buddy(e4b); goto done; } @@ -2395,9 +2372,9 @@ repeat: nr = sbi->s_mb_prefetch; if (ext4_has_feature_flex_bg(sb)) { - nr = (group / sbi->s_mb_prefetch) * - sbi->s_mb_prefetch; - nr = nr + sbi->s_mb_prefetch - group; + nr = 1 << sbi->s_log_groups_per_flex; + nr -= group & (nr - 1); + nr = min(nr, sbi->s_mb_prefetch); } prefetch_grp = ext4_mb_prefetch(sb, group, nr, &prefetch_ios); @@ -2733,7 +2710,8 @@ static int ext4_mb_init_backend(struct super_block *sb) if (ext4_has_feature_flex_bg(sb)) { /* a single flex group is supposed to be read by a single IO */ - sbi->s_mb_prefetch = 1 << sbi->s_es->s_log_groups_per_flex; + sbi->s_mb_prefetch = min(1 << sbi->s_es->s_log_groups_per_flex, + BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9)); sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ } else { sbi->s_mb_prefetch = 32; @@ -5126,6 +5104,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, cluster), "Block already on to-be-freed list"); + kmem_cache_free(ext4_free_data_cachep, new_entry); return 0; } } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 326fe402e495..cf652ba3e74d 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -182,10 +182,6 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, return bh; } -#ifndef assert -#define assert(test) J_ASSERT(test) -#endif - #ifdef DX_DEBUG #define dxtrace(command) command #else @@ -843,7 +839,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, break; } } - assert (at == p - 1); + ASSERT(at == p - 1); } at = p - 1; @@ -1259,8 +1255,8 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) struct dx_entry *old = frame->at, *new = old + 1; int count = dx_get_count(entries); - assert(count < dx_get_limit(entries)); - assert(old < entries + count); + ASSERT(count < dx_get_limit(entries)); + ASSERT(old < entries + count); memmove(new + 1, new, (char *)(entries + count) - (char *)(new)); dx_set_hash(new, hash); dx_set_block(new, block); @@ -2959,7 +2955,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) * hold i_mutex, or the inode can not be referenced from outside, * so i_nlink should not be bumped due to race */ - J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) || inode->i_nlink == 0); BUFFER_TRACE(sbi->s_sbh, "get_write_access"); @@ -2980,14 +2976,17 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) (le32_to_cpu(sbi->s_es->s_inodes_count))) { /* Insert this inode at the head of the on-disk orphan list */ NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan); + lock_buffer(sbi->s_sbh); sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); dirty = true; } list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan); mutex_unlock(&sbi->s_orphan_lock); if (dirty) { - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) err = rc; @@ -3063,9 +3062,12 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) mutex_unlock(&sbi->s_orphan_lock); goto out_brelse; } + lock_buffer(sbi->s_sbh); sbi->s_es->s_last_orphan = cpu_to_le32(ino_next); + ext4_superblock_csum_set(inode->i_sb); + unlock_buffer(sbi->s_sbh); mutex_unlock(&sbi->s_orphan_lock); - err = ext4_handle_dirty_super(handle, inode->i_sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); } else { struct ext4_iloc iloc2; struct inode *i_prev = @@ -3597,9 +3599,6 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, return retval2; } } - brelse(ent->bh); - ent->bh = NULL; - return retval; } @@ -3798,6 +3797,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, } } + old_file_type = old.de->file_type; if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir)) ext4_handle_sync(handle); @@ -3825,7 +3825,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, force_reread = (new.dir->i_ino == old.dir->i_ino && ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA)); - old_file_type = old.de->file_type; if (whiteout) { /* * Do this before adding a new entry, so the old entry is sure @@ -3923,15 +3922,19 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, retval = 0; end_rename: - brelse(old.dir_bh); - brelse(old.bh); - brelse(new.bh); if (whiteout) { - if (retval) + if (retval) { + ext4_setent(handle, &old, + old.inode->i_ino, old_file_type); drop_nlink(whiteout); + } unlock_new_inode(whiteout); iput(whiteout); + } + brelse(old.dir_bh); + brelse(old.bh); + brelse(new.bh); if (handle) ext4_journal_stop(handle); return retval; diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index defd2e10dfd1..03a44a0de86a 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -111,9 +111,6 @@ static void ext4_finish_bio(struct bio *bio) unsigned under_io = 0; unsigned long flags; - if (!page) - continue; - if (fscrypt_is_bounce_page(page)) { bounce_page = page; page = fscrypt_pagecache_page(bounce_page); @@ -438,7 +435,6 @@ submit_and_retry: int ext4_bio_write_page(struct ext4_io_submit *io, struct page *page, int len, - struct writeback_control *wbc, bool keep_towrite) { struct page *bounce_page = NULL; @@ -448,6 +444,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, int ret = 0; int nr_submitted = 0; int nr_to_submit = 0; + struct writeback_control *wbc = io->io_wbc; BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 928700d57eb6..bd0d185654f3 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -899,8 +899,11 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, EXT4_SB(sb)->s_gdb_count++; ext4_kvfree_array_rcu(o_group_desc); + lock_buffer(EXT4_SB(sb)->s_sbh); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); - err = ext4_handle_dirty_super(handle, sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); + err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); if (err) ext4_std_error(sb, err); return err; @@ -1384,6 +1387,7 @@ static void ext4_update_super(struct super_block *sb, reserved_blocks *= blocks_count; do_div(reserved_blocks, 100); + lock_buffer(sbi->s_sbh); ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count); ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks); le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) * @@ -1421,6 +1425,8 @@ static void ext4_update_super(struct super_block *sb, * active. */ ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) + reserved_blocks); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); /* Update the free space counts */ percpu_counter_add(&sbi->s_freeclusters_counter, @@ -1515,7 +1521,7 @@ static int ext4_flex_group_add(struct super_block *sb, ext4_update_super(sb, flex_gd); - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); exit_journal: err2 = ext4_journal_stop(handle); @@ -1717,15 +1723,18 @@ static int ext4_group_extend_no_check(struct super_block *sb, goto errout; } + lock_buffer(EXT4_SB(sb)->s_sbh); ext4_blocks_count_set(es, o_blocks_count + add); ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count, o_blocks_count + add); /* We add the blocks to the bitmap and set the group need init bit */ err = ext4_group_add_blocks(handle, sb, o_blocks_count, add); if (err) goto errout; - ext4_handle_dirty_super(handle, sb); + ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); ext4_debug("freed blocks %llu through %llu\n", o_blocks_count, o_blocks_count + add); errout: @@ -1874,12 +1883,15 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) if (err) goto errout; + lock_buffer(sbi->s_sbh); ext4_clear_feature_resize_inode(sb); ext4_set_feature_meta_bg(sb); sbi->s_es->s_first_meta_bg = cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count)); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); if (err) { ext4_std_error(sb, err); goto errout; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 830c196ec069..9a6f9875aa34 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -65,7 +65,8 @@ static struct ratelimit_state ext4_mount_msg_ratelimit; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); -static int ext4_commit_super(struct super_block *sb, int sync); +static void ext4_update_super(struct super_block *sb); +static int ext4_commit_super(struct super_block *sb); static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); static int ext4_clear_journal_err(struct super_block *sb, @@ -404,10 +405,8 @@ void ext4_itable_unused_set(struct super_block *sb, bg->bg_itable_unused_hi = cpu_to_le16(count >> 16); } -static void __ext4_update_tstamp(__le32 *lo, __u8 *hi) +static void __ext4_update_tstamp(__le32 *lo, __u8 *hi, time64_t now) { - time64_t now = ktime_get_real_seconds(); - now = clamp_val(now, 0, (1ull << 40) - 1); *lo = cpu_to_le32(lower_32_bits(now)); @@ -419,108 +418,11 @@ static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi) return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo); } #define ext4_update_tstamp(es, tstamp) \ - __ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi) + __ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi, \ + ktime_get_real_seconds()) #define ext4_get_tstamp(es, tstamp) \ __ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi) -static void __save_error_info(struct super_block *sb, int error, - __u32 ino, __u64 block, - const char *func, unsigned int line) -{ - struct ext4_super_block *es = EXT4_SB(sb)->s_es; - int err; - - EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; - if (bdev_read_only(sb->s_bdev)) - return; - es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_update_tstamp(es, s_last_error_time); - strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func)); - es->s_last_error_line = cpu_to_le32(line); - es->s_last_error_ino = cpu_to_le32(ino); - es->s_last_error_block = cpu_to_le64(block); - switch (error) { - case EIO: - err = EXT4_ERR_EIO; - break; - case ENOMEM: - err = EXT4_ERR_ENOMEM; - break; - case EFSBADCRC: - err = EXT4_ERR_EFSBADCRC; - break; - case 0: - case EFSCORRUPTED: - err = EXT4_ERR_EFSCORRUPTED; - break; - case ENOSPC: - err = EXT4_ERR_ENOSPC; - break; - case ENOKEY: - err = EXT4_ERR_ENOKEY; - break; - case EROFS: - err = EXT4_ERR_EROFS; - break; - case EFBIG: - err = EXT4_ERR_EFBIG; - break; - case EEXIST: - err = EXT4_ERR_EEXIST; - break; - case ERANGE: - err = EXT4_ERR_ERANGE; - break; - case EOVERFLOW: - err = EXT4_ERR_EOVERFLOW; - break; - case EBUSY: - err = EXT4_ERR_EBUSY; - break; - case ENOTDIR: - err = EXT4_ERR_ENOTDIR; - break; - case ENOTEMPTY: - err = EXT4_ERR_ENOTEMPTY; - break; - case ESHUTDOWN: - err = EXT4_ERR_ESHUTDOWN; - break; - case EFAULT: - err = EXT4_ERR_EFAULT; - break; - default: - err = EXT4_ERR_UNKNOWN; - } - es->s_last_error_errcode = err; - if (!es->s_first_error_time) { - es->s_first_error_time = es->s_last_error_time; - es->s_first_error_time_hi = es->s_last_error_time_hi; - strncpy(es->s_first_error_func, func, - sizeof(es->s_first_error_func)); - es->s_first_error_line = cpu_to_le32(line); - es->s_first_error_ino = es->s_last_error_ino; - es->s_first_error_block = es->s_last_error_block; - es->s_first_error_errcode = es->s_last_error_errcode; - } - /* - * Start the daily error reporting function if it hasn't been - * started already - */ - if (!es->s_error_count) - mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ); - le32_add_cpu(&es->s_error_count, 1); -} - -static void save_error_info(struct super_block *sb, int error, - __u32 ino, __u64 block, - const char *func, unsigned int line) -{ - __save_error_info(sb, error, ino, block, func, line); - if (!bdev_read_only(sb->s_bdev)) - ext4_commit_super(sb, 1); -} - /* * The del_gendisk() function uninitializes the disk-specific data * structures, including the bdi structure, without telling anyone @@ -649,6 +551,71 @@ static bool system_going_down(void) || system_state == SYSTEM_RESTART; } +struct ext4_err_translation { + int code; + int errno; +}; + +#define EXT4_ERR_TRANSLATE(err) { .code = EXT4_ERR_##err, .errno = err } + +static struct ext4_err_translation err_translation[] = { + EXT4_ERR_TRANSLATE(EIO), + EXT4_ERR_TRANSLATE(ENOMEM), + EXT4_ERR_TRANSLATE(EFSBADCRC), + EXT4_ERR_TRANSLATE(EFSCORRUPTED), + EXT4_ERR_TRANSLATE(ENOSPC), + EXT4_ERR_TRANSLATE(ENOKEY), + EXT4_ERR_TRANSLATE(EROFS), + EXT4_ERR_TRANSLATE(EFBIG), + EXT4_ERR_TRANSLATE(EEXIST), + EXT4_ERR_TRANSLATE(ERANGE), + EXT4_ERR_TRANSLATE(EOVERFLOW), + EXT4_ERR_TRANSLATE(EBUSY), + EXT4_ERR_TRANSLATE(ENOTDIR), + EXT4_ERR_TRANSLATE(ENOTEMPTY), + EXT4_ERR_TRANSLATE(ESHUTDOWN), + EXT4_ERR_TRANSLATE(EFAULT), +}; + +static int ext4_errno_to_code(int errno) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(err_translation); i++) + if (err_translation[i].errno == errno) + return err_translation[i].code; + return EXT4_ERR_UNKNOWN; +} + +static void save_error_info(struct super_block *sb, int error, + __u32 ino, __u64 block, + const char *func, unsigned int line) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + /* We default to EFSCORRUPTED error... */ + if (error == 0) + error = EFSCORRUPTED; + + spin_lock(&sbi->s_error_lock); + sbi->s_add_error_count++; + sbi->s_last_error_code = error; + sbi->s_last_error_line = line; + sbi->s_last_error_ino = ino; + sbi->s_last_error_block = block; + sbi->s_last_error_func = func; + sbi->s_last_error_time = ktime_get_real_seconds(); + if (!sbi->s_first_error_time) { + sbi->s_first_error_code = error; + sbi->s_first_error_line = line; + sbi->s_first_error_ino = ino; + sbi->s_first_error_block = block; + sbi->s_first_error_func = func; + sbi->s_first_error_time = sbi->s_last_error_time; + } + spin_unlock(&sbi->s_error_lock); +} + /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * @@ -662,40 +629,102 @@ static bool system_going_down(void) * We'll just use the jbd2_journal_abort() error code to record an error in * the journal instead. On recovery, the journal will complain about * that error until we've noted it down and cleared it. + * + * If force_ro is set, we unconditionally force the filesystem into an + * ABORT|READONLY state, unless the error response on the fs has been set to + * panic in which case we take the easy way out and panic immediately. This is + * used to deal with unrecoverable failures such as journal IO errors or ENOMEM + * at a critical moment in log management. */ - -static void ext4_handle_error(struct super_block *sb) +static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, + __u32 ino, __u64 block, + const char *func, unsigned int line) { + journal_t *journal = EXT4_SB(sb)->s_journal; + bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT); + + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); - if (sb_rdonly(sb)) - return; - - if (!test_opt(sb, ERRORS_CONT)) { - journal_t *journal = EXT4_SB(sb)->s_journal; - + if (!continue_fs && !sb_rdonly(sb)) { ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); if (journal) jbd2_journal_abort(journal, -EIO); } + + if (!bdev_read_only(sb->s_bdev)) { + save_error_info(sb, error, ino, block, func, line); + /* + * In case the fs should keep running, we need to writeout + * superblock through the journal. Due to lock ordering + * constraints, it may not be safe to do it right here so we + * defer superblock flushing to a workqueue. + */ + if (continue_fs) + schedule_work(&EXT4_SB(sb)->s_error_work); + else + ext4_commit_super(sb); + } + + if (sb_rdonly(sb) || continue_fs) + return; + /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already * disabled. */ - if (test_opt(sb, ERRORS_RO) || system_going_down()) { - ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); - /* - * Make sure updated value of ->s_mount_flags will be visible - * before ->s_flags update - */ - smp_wmb(); - sb->s_flags |= SB_RDONLY; - } else if (test_opt(sb, ERRORS_PANIC)) { + if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) { panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); } + ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); + /* + * Make sure updated value of ->s_mount_flags will be visible before + * ->s_flags update + */ + smp_wmb(); + sb->s_flags |= SB_RDONLY; +} + +static void flush_stashed_error_work(struct work_struct *work) +{ + struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, + s_error_work); + journal_t *journal = sbi->s_journal; + handle_t *handle; + + /* + * If the journal is still running, we have to write out superblock + * through the journal to avoid collisions of other journalled sb + * updates. + * + * We use directly jbd2 functions here to avoid recursing back into + * ext4 error handling code during handling of previous errors. + */ + if (!sb_rdonly(sbi->s_sb) && journal) { + handle = jbd2_journal_start(journal, 1); + if (IS_ERR(handle)) + goto write_directly; + if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) { + jbd2_journal_stop(handle); + goto write_directly; + } + ext4_update_super(sbi->s_sb); + if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) { + jbd2_journal_stop(handle); + goto write_directly; + } + jbd2_journal_stop(handle); + return; + } +write_directly: + /* + * Write through journal failed. Write sb directly to get error info + * out and hope for the best. + */ + ext4_commit_super(sbi->s_sb); } #define ext4_error_ratelimit(sb) \ @@ -703,7 +732,7 @@ static void ext4_handle_error(struct super_block *sb) "EXT4-fs error") void __ext4_error(struct super_block *sb, const char *function, - unsigned int line, int error, __u64 block, + unsigned int line, bool force_ro, int error, __u64 block, const char *fmt, ...) { struct va_format vaf; @@ -722,8 +751,7 @@ void __ext4_error(struct super_block *sb, const char *function, sb->s_id, function, line, current->comm, &vaf); va_end(args); } - save_error_info(sb, error, 0, block, function, line); - ext4_handle_error(sb); + ext4_handle_error(sb, force_ro, error, 0, block, function, line); } void __ext4_error_inode(struct inode *inode, const char *function, @@ -753,9 +781,8 @@ void __ext4_error_inode(struct inode *inode, const char *function, current->comm, &vaf); va_end(args); } - save_error_info(inode->i_sb, error, inode->i_ino, block, - function, line); - ext4_handle_error(inode->i_sb); + ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block, + function, line); } void __ext4_error_file(struct file *file, const char *function, @@ -792,9 +819,8 @@ void __ext4_error_file(struct file *file, const char *function, current->comm, path, &vaf); va_end(args); } - save_error_info(inode->i_sb, EFSCORRUPTED, inode->i_ino, block, - function, line); - ext4_handle_error(inode->i_sb); + ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block, + function, line); } const char *ext4_decode_error(struct super_block *sb, int errno, @@ -861,52 +887,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, sb->s_id, function, line, errstr); } - save_error_info(sb, -errno, 0, 0, function, line); - ext4_handle_error(sb); -} - -/* - * ext4_abort is a much stronger failure handler than ext4_error. The - * abort function may be used to deal with unrecoverable failures such - * as journal IO errors or ENOMEM at a critical moment in log management. - * - * We unconditionally force the filesystem into an ABORT|READONLY state, - * unless the error response on the fs has been set to panic in which - * case we take the easy way out and panic immediately. - */ - -void __ext4_abort(struct super_block *sb, const char *function, - unsigned int line, int error, const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) - return; - - save_error_info(sb, error, 0, 0, function, line); - va_start(args, fmt); - vaf.fmt = fmt; - vaf.va = &args; - printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: %pV\n", - sb->s_id, function, line, &vaf); - va_end(args); - - if (sb_rdonly(sb) == 0) { - ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); - if (EXT4_SB(sb)->s_journal) - jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); - - ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); - /* - * Make sure updated value of ->s_mount_flags will be visible - * before ->s_flags update - */ - smp_wmb(); - sb->s_flags |= SB_RDONLY; - } - if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) - panic("EXT4-fs panic from previous error\n"); + ext4_handle_error(sb, false, -errno, 0, 0, function, line); } void __ext4_msg(struct super_block *sb, @@ -982,8 +963,6 @@ __acquires(bitlock) return; trace_ext4_error(sb, function, line); - __save_error_info(sb, EFSCORRUPTED, ino, block, function, line); - if (ext4_error_ratelimit(sb)) { va_start(args, fmt); vaf.fmt = fmt; @@ -999,17 +978,19 @@ __acquires(bitlock) va_end(args); } - if (test_opt(sb, WARN_ON_ERROR)) - WARN_ON_ONCE(1); - if (test_opt(sb, ERRORS_CONT)) { - ext4_commit_super(sb, 0); + if (test_opt(sb, WARN_ON_ERROR)) + WARN_ON_ONCE(1); + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + if (!bdev_read_only(sb->s_bdev)) { + save_error_info(sb, EFSCORRUPTED, ino, block, function, + line); + schedule_work(&EXT4_SB(sb)->s_error_work); + } return; } - ext4_unlock_group(sb, grp); - ext4_commit_super(sb, 1); - ext4_handle_error(sb); + ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line); /* * We only get here in the ERRORS_RO case; relocking the group * may be dangerous, but nothing bad will happen since the @@ -1181,6 +1162,7 @@ static void ext4_put_super(struct super_block *sb) ext4_unregister_li_request(sb); ext4_quota_off_umount(sb); + flush_work(&sbi->s_error_work); destroy_workqueue(sbi->rsv_conversion_wq); /* @@ -1210,7 +1192,7 @@ static void ext4_put_super(struct super_block *sb) es->s_state = cpu_to_le16(sbi->s_mount_state); } if (!sb_rdonly(sb)) - ext4_commit_super(sb, 1); + ext4_commit_super(sb); rcu_read_lock(); group_desc = rcu_dereference(sbi->s_group_desc); @@ -1240,7 +1222,7 @@ static void ext4_put_super(struct super_block *sb) * in-memory list had better be clean by this point. */ if (!list_empty(&sbi->s_orphan)) dump_orphan_list(sb, sbi); - J_ASSERT(list_empty(&sbi->s_orphan)); + ASSERT(list_empty(&sbi->s_orphan)); sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); @@ -2700,7 +2682,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, if (sbi->s_journal) ext4_set_feature_journal_needs_recovery(sb); - err = ext4_commit_super(sb, 1); + err = ext4_commit_super(sb); done: if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " @@ -4005,6 +3987,21 @@ static void ext4_set_resv_clusters(struct super_block *sb) atomic64_set(&sbi->s_resv_clusters, resv_clusters); } +static const char *ext4_quota_mode(struct super_block *sb) +{ +#ifdef CONFIG_QUOTA + if (!ext4_quota_capable(sb)) + return "none"; + + if (EXT4_SB(sb)->s_journal && ext4_is_quota_journalled(sb)) + return "journalled"; + else + return "writeback"; +#else + return "disabled"; +#endif +} + static int ext4_fill_super(struct super_block *sb, void *data, int silent) { struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev); @@ -4073,7 +4070,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "unable to read superblock"); ret = PTR_ERR(bh); - bh = NULL; goto out_fail; } /* @@ -4187,19 +4183,26 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; - blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); - - if (blocksize == PAGE_SIZE) - set_opt(sb, DIOREAD_NOLOCK); - - if (blocksize < EXT4_MIN_BLOCK_SIZE || - blocksize > EXT4_MAX_BLOCK_SIZE) { + if (le32_to_cpu(es->s_log_block_size) > + (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, - "Unsupported filesystem blocksize %d (%d log_block_size)", - blocksize, le32_to_cpu(es->s_log_block_size)); + "Invalid log block size: %u", + le32_to_cpu(es->s_log_block_size)); + goto failed_mount; + } + if (le32_to_cpu(es->s_log_cluster_size) > + (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log cluster size: %u", + le32_to_cpu(es->s_log_cluster_size)); goto failed_mount; } + blocksize = EXT4_MIN_BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); + + if (blocksize == PAGE_SIZE) + set_opt(sb, DIOREAD_NOLOCK); + if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; @@ -4417,21 +4420,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (!ext4_feature_set_ok(sb, (sb_rdonly(sb)))) goto failed_mount; - if (le32_to_cpu(es->s_log_block_size) > - (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { - ext4_msg(sb, KERN_ERR, - "Invalid log block size: %u", - le32_to_cpu(es->s_log_block_size)); - goto failed_mount; - } - if (le32_to_cpu(es->s_log_cluster_size) > - (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { - ext4_msg(sb, KERN_ERR, - "Invalid log cluster size: %u", - le32_to_cpu(es->s_log_cluster_size)); - goto failed_mount; - } - if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) { ext4_msg(sb, KERN_ERR, "Number of reserved GDT blocks insanely large: %d", @@ -4702,7 +4690,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "can't read group descriptor %d", i); db_count = i; ret = PTR_ERR(bh); - bh = NULL; goto failed_mount2; } rcu_read_lock(); @@ -4717,6 +4704,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } timer_setup(&sbi->s_err_report, print_daily_error_info, 0); + spin_lock_init(&sbi->s_error_lock); + INIT_WORK(&sbi->s_error_work, flush_stashed_error_work); /* Register extent status tree shrinker */ if (ext4_es_register_shrinker(sbi)) @@ -4872,6 +4861,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "requested data journaling mode"); goto failed_mount_wq; } + break; default: break; } @@ -4918,7 +4908,7 @@ no_journal: if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) && !ext4_has_feature_encrypt(sb)) { ext4_set_feature_encrypt(sb); - ext4_commit_super(sb, 1); + ext4_commit_super(sb); } /* @@ -5000,13 +4990,11 @@ no_journal: block = ext4_count_free_clusters(sb); ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block)); - ext4_superblock_csum_set(sb); err = percpu_counter_init(&sbi->s_freeclusters_counter, block, GFP_KERNEL); if (!err) { unsigned long freei = ext4_count_free_inodes(sb); sbi->s_es->s_free_inodes_count = cpu_to_le32(freei); - ext4_superblock_csum_set(sb); err = percpu_counter_init(&sbi->s_freeinodes_counter, freei, GFP_KERNEL); } @@ -5086,10 +5074,11 @@ no_journal: if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount")) ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. " - "Opts: %.*s%s%s", descr, + "Opts: %.*s%s%s. Quota mode: %s.", descr, (int) sizeof(sbi->s_es->s_mount_opts), sbi->s_es->s_mount_opts, - *sbi->s_es->s_mount_opts ? "; " : "", orig_data); + *sbi->s_es->s_mount_opts ? "; " : "", orig_data, + ext4_quota_mode(sb)); if (es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */ @@ -5154,6 +5143,7 @@ failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: del_timer_sync(&sbi->s_err_report); + flush_work(&sbi->s_error_work); if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); failed_mount2: @@ -5468,7 +5458,7 @@ static int ext4_load_journal(struct super_block *sb, es->s_journal_dev = cpu_to_le32(journal_devnum); /* Make sure we flush the recovery flag to disk. */ - ext4_commit_super(sb, 1); + ext4_commit_super(sb); } return 0; @@ -5478,15 +5468,14 @@ err_out: return err; } -static int ext4_commit_super(struct super_block *sb, int sync) +/* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */ +static void ext4_update_super(struct super_block *sb) { - struct ext4_super_block *es = EXT4_SB(sb)->s_es; - struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; - int error = 0; - - if (!sbh || block_device_ejected(sb)) - return error; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + struct buffer_head *sbh = sbi->s_sbh; + lock_buffer(sbh); /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock @@ -5500,21 +5489,71 @@ static int ext4_commit_super(struct super_block *sb, int sync) if (!(sb->s_flags & SB_RDONLY)) ext4_update_tstamp(es, s_wtime); es->s_kbytes_written = - cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + + cpu_to_le64(sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - - EXT4_SB(sb)->s_sectors_written_start) >> 1)); - if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter)) + sbi->s_sectors_written_start) >> 1)); + if (percpu_counter_initialized(&sbi->s_freeclusters_counter)) ext4_free_blocks_count_set(es, - EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeclusters_counter))); - if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter)) + EXT4_C2B(sbi, percpu_counter_sum_positive( + &sbi->s_freeclusters_counter))); + if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeinodes_counter)); - BUFFER_TRACE(sbh, "marking dirty"); + &sbi->s_freeinodes_counter)); + /* Copy error information to the on-disk superblock */ + spin_lock(&sbi->s_error_lock); + if (sbi->s_add_error_count > 0) { + es->s_state |= cpu_to_le16(EXT4_ERROR_FS); + if (!es->s_first_error_time && !es->s_first_error_time_hi) { + __ext4_update_tstamp(&es->s_first_error_time, + &es->s_first_error_time_hi, + sbi->s_first_error_time); + strncpy(es->s_first_error_func, sbi->s_first_error_func, + sizeof(es->s_first_error_func)); + es->s_first_error_line = + cpu_to_le32(sbi->s_first_error_line); + es->s_first_error_ino = + cpu_to_le32(sbi->s_first_error_ino); + es->s_first_error_block = + cpu_to_le64(sbi->s_first_error_block); + es->s_first_error_errcode = + ext4_errno_to_code(sbi->s_first_error_code); + } + __ext4_update_tstamp(&es->s_last_error_time, + &es->s_last_error_time_hi, + sbi->s_last_error_time); + strncpy(es->s_last_error_func, sbi->s_last_error_func, + sizeof(es->s_last_error_func)); + es->s_last_error_line = cpu_to_le32(sbi->s_last_error_line); + es->s_last_error_ino = cpu_to_le32(sbi->s_last_error_ino); + es->s_last_error_block = cpu_to_le64(sbi->s_last_error_block); + es->s_last_error_errcode = + ext4_errno_to_code(sbi->s_last_error_code); + /* + * Start the daily error reporting function if it hasn't been + * started already + */ + if (!es->s_error_count) + mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); + le32_add_cpu(&es->s_error_count, sbi->s_add_error_count); + sbi->s_add_error_count = 0; + } + spin_unlock(&sbi->s_error_lock); + ext4_superblock_csum_set(sb); - if (sync) - lock_buffer(sbh); + unlock_buffer(sbh); +} + +static int ext4_commit_super(struct super_block *sb) +{ + struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; + int error = 0; + + if (!sbh || block_device_ejected(sb)) + return error; + + ext4_update_super(sb); + if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the @@ -5529,17 +5568,15 @@ static int ext4_commit_super(struct super_block *sb, int sync) clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } + BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); - if (sync) { - unlock_buffer(sbh); - error = __sync_dirty_buffer(sbh, - REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0)); - if (buffer_write_io_error(sbh)) { - ext4_msg(sb, KERN_ERR, "I/O error while writing " - "superblock"); - clear_buffer_write_io_error(sbh); - set_buffer_uptodate(sbh); - } + error = __sync_dirty_buffer(sbh, + REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0)); + if (buffer_write_io_error(sbh)) { + ext4_msg(sb, KERN_ERR, "I/O error while writing " + "superblock"); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); } return error; } @@ -5570,7 +5607,7 @@ static int ext4_mark_recovery_complete(struct super_block *sb, if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) { ext4_clear_feature_journal_needs_recovery(sb); - ext4_commit_super(sb, 1); + ext4_commit_super(sb); } out: jbd2_journal_unlock_updates(journal); @@ -5612,7 +5649,7 @@ static int ext4_clear_journal_err(struct super_block *sb, EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_commit_super(sb, 1); + ext4_commit_super(sb); jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); @@ -5714,7 +5751,7 @@ static int ext4_freeze(struct super_block *sb) ext4_clear_feature_journal_needs_recovery(sb); } - error = ext4_commit_super(sb, 1); + error = ext4_commit_super(sb); out: if (journal) /* we rely on upper layer to stop further updates */ @@ -5736,7 +5773,7 @@ static int ext4_unfreeze(struct super_block *sb) ext4_set_feature_journal_needs_recovery(sb); } - ext4_commit_super(sb, 1); + ext4_commit_super(sb); return 0; } @@ -5864,6 +5901,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); } + /* Flush outstanding errors before changing fs state */ + flush_work(&sbi->s_error_work); + if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) { err = -EROFS; @@ -5993,7 +6033,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { - err = ext4_commit_super(sb, 1); + err = ext4_commit_super(sb); if (err) goto restore_opts; } @@ -6022,7 +6062,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) */ *flags = (*flags & ~vfs_flags) | (sb->s_flags & vfs_flags); - ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data); + ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s. Quota mode: %s.", + orig_data, ext4_quota_mode(sb)); kfree(orig_data); return 0; @@ -6201,11 +6242,8 @@ static int ext4_release_dquot(struct dquot *dquot) static int ext4_mark_dquot_dirty(struct dquot *dquot) { struct super_block *sb = dquot->dq_sb; - struct ext4_sb_info *sbi = EXT4_SB(sb); - /* Are we journaling quotas? */ - if (ext4_has_feature_quota(sb) || - sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { + if (ext4_is_quota_journalled(sb)) { dquot_mark_dquot_dirty(dquot); return ext4_write_dquot(dquot); } else { diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 6127e94ea4f5..372208500f4e 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -792,8 +792,11 @@ static void ext4_xattr_update_super_block(handle_t *handle, BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access"); if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) { + lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_xattr(sb); - ext4_handle_dirty_super(handle, sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); + ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); } } @@ -1927,7 +1930,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, } else { /* Allocate a buffer where we construct the new block. */ s->base = kzalloc(sb->s_blocksize, GFP_NOFS); - /* assert(header == s->base) */ error = -ENOMEM; if (s->base == NULL) goto cleanup; diff --git a/fs/fcntl.c b/fs/fcntl.c index 05b36b28f2e8..483ef8861376 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -148,11 +148,15 @@ void f_delown(struct file *filp) pid_t f_getown(struct file *filp) { - pid_t pid; + pid_t pid = 0; read_lock(&filp->f_owner.lock); - pid = pid_vnr(filp->f_owner.pid); - if (filp->f_owner.pid_type == PIDTYPE_PGID) - pid = -pid; + rcu_read_lock(); + if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { + pid = pid_vnr(filp->f_owner.pid); + if (filp->f_owner.pid_type == PIDTYPE_PGID) + pid = -pid; + } + rcu_read_unlock(); read_unlock(&filp->f_owner.lock); return pid; } @@ -200,11 +204,14 @@ static int f_setown_ex(struct file *filp, unsigned long arg) static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; - struct f_owner_ex owner; + struct f_owner_ex owner = {}; int ret = 0; read_lock(&filp->f_owner.lock); - owner.pid = pid_vnr(filp->f_owner.pid); + rcu_read_lock(); + if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) + owner.pid = pid_vnr(filp->f_owner.pid); + rcu_read_unlock(); switch (filp->f_owner.pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; diff --git a/fs/file.c b/fs/file.c index 8434e0afecc7..dab120b71e44 100644 --- a/fs/file.c +++ b/fs/file.c @@ -21,7 +21,6 @@ #include <linux/rcupdate.h> #include <linux/close_range.h> #include <net/sock.h> -#include <linux/io_uring.h> unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; @@ -428,7 +427,6 @@ void exit_files(struct task_struct *tsk) struct files_struct * files = tsk->files; if (files) { - io_uring_files_cancel(files); task_lock(tsk); tsk->files = NULL; task_unlock(tsk); @@ -694,8 +692,10 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) * If the requested range is greater than the current maximum, * we're closing everything so only copy all file descriptors * beneath the lowest file descriptor. + * If the caller requested all fds to be made cloexec copy all + * of the file descriptors since they still want to use them. */ - if (max_fd >= cur_max) + if (!(flags & CLOSE_RANGE_CLOEXEC) && (max_fd >= cur_max)) max_unshare_fds = fd; ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index acfb55834af2..c41cb887eb7d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1474,21 +1474,25 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) } /* - * Some filesystems may redirty the inode during the writeback - * due to delalloc, clear dirty metadata flags right before - * write_inode() + * If the inode has dirty timestamps and we need to write them, call + * mark_inode_dirty_sync() to notify the filesystem about it and to + * change I_DIRTY_TIME into I_DIRTY_SYNC. */ - spin_lock(&inode->i_lock); - - dirty = inode->i_state & I_DIRTY; if ((inode->i_state & I_DIRTY_TIME) && - ((dirty & I_DIRTY_INODE) || - wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || + (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { - dirty |= I_DIRTY_TIME; trace_writeback_lazytime(inode); + mark_inode_dirty_sync(inode); } + + /* + * Some filesystems may redirty the inode during the writeback + * due to delalloc, clear dirty metadata flags right before + * write_inode() + */ + spin_lock(&inode->i_lock); + dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* @@ -1509,8 +1513,6 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_unlock(&inode->i_lock); - if (dirty & I_DIRTY_TIME) - mark_inode_dirty_sync(inode); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 35a6fd103761..d87a5bc3607b 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -857,12 +857,6 @@ static void delete_work_func(struct work_struct *work) clear_bit(GLF_PENDING_DELETE, &gl->gl_flags); spin_unlock(&gl->gl_lockref.lock); - /* If someone's using this glock to create a new dinode, the block must - have been freed by another node, then re-used, in which case our - iopen callback is too late after the fact. Ignore it. */ - if (test_bit(GLF_INODE_CREATING, &gl->gl_flags)) - goto out; - if (test_bit(GLF_DEMOTE, &gl->gl_flags)) { /* * If we can evict the inode, give the remote node trying to @@ -2112,8 +2106,6 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl) *p++ = 'o'; if (test_bit(GLF_BLOCKING, gflags)) *p++ = 'b'; - if (test_bit(GLF_INODE_CREATING, gflags)) - *p++ = 'c'; if (test_bit(GLF_PENDING_DELETE, gflags)) *p++ = 'P'; if (test_bit(GLF_FREEING, gflags)) diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index f8858d995b24..8e1ab8ed4abc 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -348,7 +348,6 @@ enum { GLF_LRU = 13, GLF_OBJECT = 14, /* Used only for tracing */ GLF_BLOCKING = 15, - GLF_INODE_CREATING = 16, /* Inode creation occurring */ GLF_PENDING_DELETE = 17, GLF_FREEING = 18, /* Wait for glock to be freed */ }; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 65ae4fc28ede..c1b77e8d6b1c 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -36,6 +36,10 @@ #include "super.h" #include "glops.h" +static const struct inode_operations gfs2_file_iops; +static const struct inode_operations gfs2_dir_iops; +static const struct inode_operations gfs2_symlink_iops; + static int iget_test(struct inode *inode, void *opaque) { u64 no_addr = *(u64 *)opaque; @@ -605,7 +609,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, struct inode *inode = NULL; struct gfs2_inode *dip = GFS2_I(dir), *ip; struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); - struct gfs2_glock *io_gl = NULL; + struct gfs2_glock *io_gl; int error, free_vfs_inode = 1; u32 aflags = 0; unsigned blocks = 1; @@ -746,8 +750,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, init_dinode(dip, ip, symname); gfs2_trans_end(sdp); - BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags)); - error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (error) goto fail_gunlock2; @@ -793,7 +795,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, gfs2_glock_dq_uninit(ghs); gfs2_qa_put(ip); gfs2_glock_dq_uninit(ghs + 1); - clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); gfs2_glock_put(io_gl); gfs2_qa_put(dip); return error; @@ -802,7 +803,6 @@ fail_gunlock3: glock_clear_object(io_gl, ip); gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_gunlock2: - clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); glock_clear_object(io_gl, ip); gfs2_glock_put(io_gl); fail_free_inode: @@ -2136,7 +2136,7 @@ static int gfs2_update_time(struct inode *inode, struct timespec64 *time, return generic_update_time(inode, time, flags); } -const struct inode_operations gfs2_file_iops = { +static const struct inode_operations gfs2_file_iops = { .permission = gfs2_permission, .setattr = gfs2_setattr, .getattr = gfs2_getattr, @@ -2147,7 +2147,7 @@ const struct inode_operations gfs2_file_iops = { .update_time = gfs2_update_time, }; -const struct inode_operations gfs2_dir_iops = { +static const struct inode_operations gfs2_dir_iops = { .create = gfs2_create, .lookup = gfs2_lookup, .link = gfs2_link, @@ -2168,7 +2168,7 @@ const struct inode_operations gfs2_dir_iops = { .atomic_open = gfs2_atomic_open, }; -const struct inode_operations gfs2_symlink_iops = { +static const struct inode_operations gfs2_symlink_iops = { .get_link = gfs2_get_link, .permission = gfs2_permission, .setattr = gfs2_setattr, diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index b52ecf4ffe63..8073b8d2c7fa 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -107,9 +107,6 @@ extern int gfs2_open_common(struct inode *inode, struct file *file); extern loff_t gfs2_seek_data(struct file *file, loff_t offset); extern loff_t gfs2_seek_hole(struct file *file, loff_t offset); -extern const struct inode_operations gfs2_file_iops; -extern const struct inode_operations gfs2_dir_iops; -extern const struct inode_operations gfs2_symlink_iops; extern const struct file_operations gfs2_file_fops_nolock; extern const struct file_operations gfs2_dir_fops_nolock; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index b3d951ab8068..2f56acc41c04 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -353,7 +353,6 @@ int gfs2_statfs_sync(struct super_block *sb, int type) struct buffer_head *m_bh, *l_bh; int error; - sb_start_write(sb); error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, GL_NOCACHE, &gh); if (error) @@ -392,7 +391,6 @@ out_bh: out_unlock: gfs2_glock_dq_uninit(&gh); out: - sb_end_write(sb); return error; } diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 0fba3bf64189..a374397f4273 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -137,7 +137,7 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) gfs2_glock_dq(&sdp->sd_jinode_gh); if (test_bit(SDF_FS_FROZEN, &sdp->sd_flags)) { /* Make sure gfs2_unfreeze works if partially-frozen */ - flush_workqueue(gfs2_freeze_wq); + flush_work(&sdp->sd_freeze_work); atomic_set(&sdp->sd_freeze_state, SFS_FROZEN); thaw_super(sdp->sd_vfs); } else { diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h index d7562981b3a0..a4443dd8a94b 100644 --- a/fs/gfs2/util.h +++ b/fs/gfs2/util.h @@ -151,7 +151,7 @@ extern int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, bool verbose); #define gfs2_io_error(sdp) \ -gfs2_io_error_i((sdp), __func__, __FILE__, __LINE__); +gfs2_io_error_i((sdp), __func__, __FILE__, __LINE__) void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh, @@ -159,10 +159,10 @@ void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh, bool withdraw); #define gfs2_io_error_bh_wd(sdp, bh) \ -gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__, true); +gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__, true) #define gfs2_io_error_bh(sdp, bh) \ -gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__, false); +gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__, false) extern struct kmem_cache *gfs2_glock_cachep; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index c070c0d8e3e9..aea35459d390 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -315,7 +315,7 @@ retry: if (mode & FMODE_WRITE) r = w = 1; - name = dentry_name(file->f_path.dentry); + name = dentry_name(d_real(file->f_path.dentry, file->f_inode)); if (name == NULL) return -ENOMEM; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index b5c109703daa..21c20fd5f9ee 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -735,9 +735,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, mutex_unlock(&hugetlb_fault_mutex_table[hash]); + set_page_huge_active(page); /* * unlock_page because locked by add_to_page_cache() - * page_put due to reference from alloc_huge_page() + * put_page() due to reference from alloc_huge_page() */ unlock_page(page); put_page(page); diff --git a/fs/inode.c b/fs/inode.c index cb008acf0efd..6442d97d9a4a 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1624,7 +1624,9 @@ static void iput_final(struct inode *inode) else drop = generic_drop_inode(inode); - if (!drop && (sb->s_flags & SB_ACTIVE)) { + if (!drop && + !(inode->i_state & I_DONTCACHE) && + (sb->s_flags & SB_ACTIVE)) { inode_add_lru(inode); spin_unlock(&inode->i_lock); return; diff --git a/fs/internal.h b/fs/internal.h index 77c50befbfbe..cff1f30cfefb 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -15,6 +15,7 @@ struct mount; struct shrink_control; struct fs_context; struct user_namespace; +struct pipe_inode_info; /* * block_dev.c @@ -193,3 +194,11 @@ int sb_init_dio_done_wq(struct super_block *sb); */ int do_statx(int dfd, const char __user *filename, unsigned flags, unsigned int mask, struct statx __user *buffer); + +/* + * fs/splice.c: + */ +long splice_file_to_pipe(struct file *in, + struct pipe_inode_info *opipe, + loff_t *offset, + size_t len, unsigned int flags); diff --git a/fs/io-wq.c b/fs/io-wq.c index f72d53848dcb..a564f36e260c 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -36,8 +36,7 @@ enum { enum { IO_WQ_BIT_EXIT = 0, /* wq exiting */ - IO_WQ_BIT_CANCEL = 1, /* cancel work on list */ - IO_WQ_BIT_ERROR = 2, /* error on setup */ + IO_WQ_BIT_ERROR = 1, /* error on setup */ }; enum { @@ -561,12 +560,6 @@ get_next: next_hashed = wq_next_work(work); io_impersonate_work(worker, work); - /* - * OK to set IO_WQ_WORK_CANCEL even for uncancellable - * work, the worker function will do the right thing. - */ - if (test_bit(IO_WQ_BIT_CANCEL, &wq->state)) - work->flags |= IO_WQ_WORK_CANCEL; old_work = work; linked = wq->do_work(work); @@ -732,12 +725,6 @@ static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index) return acct->nr_workers < acct->max_workers; } -static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data) -{ - send_sig(SIGINT, worker->task, 1); - return false; -} - /* * Iterate the passed in list and call the specific function for each * worker that isn't exiting @@ -938,21 +925,6 @@ void io_wq_hash_work(struct io_wq_work *work, void *val) work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT)); } -void io_wq_cancel_all(struct io_wq *wq) -{ - int node; - - set_bit(IO_WQ_BIT_CANCEL, &wq->state); - - rcu_read_lock(); - for_each_node(node) { - struct io_wqe *wqe = wq->wqes[node]; - - io_wq_for_each_worker(wqe, io_wqe_worker_send_sig, NULL); - } - rcu_read_unlock(); -} - struct io_cb_cancel_data { work_cancel_fn *fn; void *data; diff --git a/fs/io-wq.h b/fs/io-wq.h index 069496c6d4f9..b158f8addcf3 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -59,6 +59,7 @@ static inline void wq_list_add_tail(struct io_wq_work_node *node, list->last->next = node; list->last = node; } + node->next = NULL; } static inline void wq_list_cut(struct io_wq_work_list *list, @@ -128,8 +129,6 @@ static inline bool io_wq_is_hashed(struct io_wq_work *work) return work->flags & IO_WQ_WORK_HASHED; } -void io_wq_cancel_all(struct io_wq *wq); - typedef bool (work_cancel_fn)(struct io_wq_work *, void *); enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, diff --git a/fs/io_uring.c b/fs/io_uring.c index 6f9392c35eef..931671082e61 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -262,6 +262,7 @@ struct io_ring_ctx { unsigned int drain_next: 1; unsigned int eventfd_async: 1; unsigned int restricted: 1; + unsigned int sqo_dead: 1; /* * Ring buffer of indices into array of io_uring_sqe, which is @@ -353,6 +354,7 @@ struct io_ring_ctx { unsigned cq_entries; unsigned cq_mask; atomic_t cq_timeouts; + unsigned cq_last_tm_flush; unsigned long cq_check_overflow; struct wait_queue_head cq_wait; struct fasync_struct *cq_fasync; @@ -855,7 +857,8 @@ static const struct io_op_def io_op_defs[] = { .pollout = 1, .needs_async_data = 1, .async_size = sizeof(struct io_async_msghdr), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG, + .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | + IO_WQ_WORK_FS, }, [IORING_OP_RECVMSG] = { .needs_file = 1, @@ -864,7 +867,8 @@ static const struct io_op_def io_op_defs[] = { .buffer_select = 1, .needs_async_data = 1, .async_size = sizeof(struct io_async_msghdr), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG, + .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | + IO_WQ_WORK_FS, }, [IORING_OP_TIMEOUT] = { .needs_async_data = 1, @@ -992,6 +996,13 @@ enum io_mem_account { ACCT_PINNED, }; +static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx, + struct task_struct *task); + +static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node); +static struct fixed_file_ref_node *alloc_fixed_file_ref_node( + struct io_ring_ctx *ctx); + static void __io_complete_rw(struct io_kiocb *req, long res, long res2, struct io_comp_state *cs); static void io_cqring_fill_event(struct io_kiocb *req, long res); @@ -1016,6 +1027,8 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, const struct iovec *fast_iov, struct iov_iter *iter, bool force); +static void io_req_drop_files(struct io_kiocb *req); +static void io_req_task_queue(struct io_kiocb *req); static struct kmem_cache *req_cachep; @@ -1039,8 +1052,7 @@ EXPORT_SYMBOL(io_uring_get_socket); static inline void io_clean_op(struct io_kiocb *req) { - if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED | - REQ_F_INFLIGHT)) + if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED)) __io_clean_op(req); } @@ -1060,14 +1072,21 @@ static bool io_match_task(struct io_kiocb *head, { struct io_kiocb *req; - if (task && head->task != task) + if (task && head->task != task) { + /* in terms of cancelation, always match if req task is dead */ + if (head->task->flags & PF_EXITING) + return true; return false; + } if (!files) return true; io_for_each_link(req, head) { - if ((req->flags & REQ_F_WORK_INITIALIZED) && - (req->work.flags & IO_WQ_WORK_FILES) && + if (!(req->flags & REQ_F_WORK_INITIALIZED)) + continue; + if (req->file && req->file->f_op == &io_uring_fops) + return true; + if ((req->work.flags & IO_WQ_WORK_FILES) && req->work.identity->files == files) return true; } @@ -1098,6 +1117,9 @@ static void io_sq_thread_drop_mm_files(void) static int __io_sq_thread_acquire_files(struct io_ring_ctx *ctx) { + if (current->flags & PF_EXITING) + return -EFAULT; + if (!current->files) { struct files_struct *files; struct nsproxy *nsproxy; @@ -1125,6 +1147,8 @@ static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx) { struct mm_struct *mm; + if (current->flags & PF_EXITING) + return -EFAULT; if (current->mm) return 0; @@ -1338,11 +1362,6 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx) /* order cqe stores with ring update */ smp_store_release(&rings->cq.tail, ctx->cached_cq_tail); - - if (wq_has_sleeper(&ctx->cq_wait)) { - wake_up_interruptible(&ctx->cq_wait); - kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); - } } static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req) @@ -1385,6 +1404,8 @@ static void io_req_clean_work(struct io_kiocb *req) free_fs_struct(fs); req->work.flags &= ~IO_WQ_WORK_FS; } + if (req->flags & REQ_F_INFLIGHT) + io_req_drop_files(req); io_put_identity(req->task->io_uring, req); } @@ -1494,13 +1515,23 @@ static bool io_grab_identity(struct io_kiocb *req) return false; atomic_inc(&id->files->count); get_nsproxy(id->nsproxy); - req->flags |= REQ_F_INFLIGHT; - spin_lock_irq(&ctx->inflight_lock); - list_add(&req->inflight_entry, &ctx->inflight_list); - spin_unlock_irq(&ctx->inflight_lock); + if (!(req->flags & REQ_F_INFLIGHT)) { + req->flags |= REQ_F_INFLIGHT; + + spin_lock_irq(&ctx->inflight_lock); + list_add(&req->inflight_entry, &ctx->inflight_list); + spin_unlock_irq(&ctx->inflight_lock); + } req->work.flags |= IO_WQ_WORK_FILES; } + if (!(req->work.flags & IO_WQ_WORK_MM) && + (def->work_flags & IO_WQ_WORK_MM)) { + if (id->mm != current->mm) + return false; + mmgrab(id->mm); + req->work.flags |= IO_WQ_WORK_MM; + } return true; } @@ -1509,10 +1540,8 @@ static void io_prep_async_work(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; struct io_ring_ctx *ctx = req->ctx; - struct io_identity *id; io_req_init_async(req); - id = req->work.identity; if (req->flags & REQ_F_FORCE_ASYNC) req->work.flags |= IO_WQ_WORK_CONCURRENT; @@ -1525,13 +1554,6 @@ static void io_prep_async_work(struct io_kiocb *req) req->work.flags |= IO_WQ_WORK_UNBOUND; } - /* ->mm can never change on us */ - if (!(req->work.flags & IO_WQ_WORK_MM) && - (def->work_flags & IO_WQ_WORK_MM)) { - mmgrab(id->mm); - req->work.flags |= IO_WQ_WORK_MM; - } - /* if we fail grabbing identity, we must COW, regrab, and retry */ if (io_grab_identity(req)) return; @@ -1615,37 +1637,49 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx) do { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); - struct io_kiocb *link; if (req_need_defer(de->req, de->seq)) break; list_del_init(&de->list); - /* punt-init is done before queueing for defer */ - link = __io_queue_async_work(de->req); - if (link) { - __io_queue_linked_timeout(link); - /* drop submission reference */ - io_put_req_deferred(link, 1); - } + io_req_task_queue(de->req); kfree(de); } while (!list_empty(&ctx->defer_list)); } static void io_flush_timeouts(struct io_ring_ctx *ctx) { - while (!list_empty(&ctx->timeout_list)) { + u32 seq; + + if (list_empty(&ctx->timeout_list)) + return; + + seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + + do { + u32 events_needed, events_got; struct io_kiocb *req = list_first_entry(&ctx->timeout_list, struct io_kiocb, timeout.list); if (io_is_timeout_noseq(req)) break; - if (req->timeout.target_seq != ctx->cached_cq_tail - - atomic_read(&ctx->cq_timeouts)) + + /* + * Since seq can easily wrap around over time, subtract + * the last seq at which timeouts were flushed before comparing. + * Assuming not more than 2^31-1 events have happened since, + * these subtractions won't have wrapped, so we can check if + * target is in [last_seq, current_seq] by comparing the two. + */ + events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush; + events_got = seq - ctx->cq_last_tm_flush; + if (events_got < events_needed) break; list_del_init(&req->timeout.list); io_kill_timeout(req); - } + } while (!list_empty(&ctx->timeout_list)); + + ctx->cq_last_tm_flush = seq; } static void io_commit_cqring(struct io_ring_ctx *ctx) @@ -1693,51 +1727,62 @@ static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx) return io_wq_current_is_worker(); } +static inline unsigned __io_cqring_events(struct io_ring_ctx *ctx) +{ + return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); +} + static void io_cqring_ev_posted(struct io_ring_ctx *ctx) { + /* see waitqueue_active() comment */ + smp_mb(); + if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); + if (waitqueue_active(&ctx->cq_wait)) { + wake_up_interruptible(&ctx->cq_wait); + kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); + } } -static void io_cqring_mark_overflow(struct io_ring_ctx *ctx) +static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) { - if (list_empty(&ctx->cq_overflow_list)) { - clear_bit(0, &ctx->sq_check_overflow); - clear_bit(0, &ctx->cq_check_overflow); - ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; + /* see waitqueue_active() comment */ + smp_mb(); + + if (ctx->flags & IORING_SETUP_SQPOLL) { + if (waitqueue_active(&ctx->wait)) + wake_up(&ctx->wait); + } + if (io_should_trigger_evfd(ctx)) + eventfd_signal(ctx->cq_ev_fd, 1); + if (waitqueue_active(&ctx->cq_wait)) { + wake_up_interruptible(&ctx->cq_wait); + kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); } } /* Returns true if there are no backlogged entries after the flush */ -static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, - struct task_struct *tsk, - struct files_struct *files) +static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, + struct task_struct *tsk, + struct files_struct *files) { struct io_rings *rings = ctx->rings; struct io_kiocb *req, *tmp; struct io_uring_cqe *cqe; unsigned long flags; + bool all_flushed, posted; LIST_HEAD(list); - if (!force) { - if (list_empty_careful(&ctx->cq_overflow_list)) - return true; - if ((ctx->cached_cq_tail - READ_ONCE(rings->cq.head) == - rings->cq_ring_entries)) - return false; - } + if (!force && __io_cqring_events(ctx) == rings->cq_ring_entries) + return false; + posted = false; spin_lock_irqsave(&ctx->completion_lock, flags); - - /* if force is set, the ring is going away. always drop after that */ - if (force) - ctx->cq_overflow_flushed = 1; - - cqe = NULL; list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) { if (!io_match_task(req, tsk, files)) continue; @@ -1756,13 +1801,21 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, WRITE_ONCE(ctx->rings->cq_overflow, ctx->cached_cq_overflow); } + posted = true; } - io_commit_cqring(ctx); - io_cqring_mark_overflow(ctx); + all_flushed = list_empty(&ctx->cq_overflow_list); + if (all_flushed) { + clear_bit(0, &ctx->sq_check_overflow); + clear_bit(0, &ctx->cq_check_overflow); + ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; + } + if (posted) + io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); - io_cqring_ev_posted(ctx); + if (posted) + io_cqring_ev_posted(ctx); while (!list_empty(&list)) { req = list_first_entry(&list, struct io_kiocb, compl.list); @@ -1770,7 +1823,21 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, io_put_req(req); } - return cqe != NULL; + return all_flushed; +} + +static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, + struct task_struct *tsk, + struct files_struct *files) +{ + if (test_bit(0, &ctx->cq_check_overflow)) { + /* iopoll syncs against uring_lock, not completion_lock */ + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_lock(&ctx->uring_lock); + __io_cqring_overflow_flush(ctx, force, tsk, files); + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_unlock(&ctx->uring_lock); + } } static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags) @@ -2132,14 +2199,17 @@ static void __io_req_task_submit(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - if (!__io_sq_thread_acquire_mm(ctx) && - !__io_sq_thread_acquire_files(ctx)) { - mutex_lock(&ctx->uring_lock); + mutex_lock(&ctx->uring_lock); + if (!ctx->sqo_dead && + !__io_sq_thread_acquire_mm(ctx) && + !__io_sq_thread_acquire_files(ctx)) __io_queue_sqe(req, NULL); - mutex_unlock(&ctx->uring_lock); - } else { + else __io_req_task_cancel(req, -EFAULT); - } + mutex_unlock(&ctx->uring_lock); + + if (ctx->flags & IORING_SETUP_SQPOLL) + io_sq_thread_drop_mm_files(); } static void io_req_task_submit(struct callback_head *cb) @@ -2215,6 +2285,8 @@ static void io_req_free_batch_finish(struct io_ring_ctx *ctx, struct io_uring_task *tctx = rb->task->io_uring; percpu_counter_sub(&tctx->inflight, rb->task_refs); + if (atomic_read(&tctx->in_idle)) + wake_up(&tctx->wait); put_task_struct_many(rb->task, rb->task_refs); rb->task = NULL; } @@ -2233,6 +2305,8 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req) struct io_uring_task *tctx = rb->task->io_uring; percpu_counter_sub(&tctx->inflight, rb->task_refs); + if (atomic_read(&tctx->in_idle)) + wake_up(&tctx->wait); put_task_struct_many(rb->task, rb->task_refs); } rb->task = req->task; @@ -2318,25 +2392,11 @@ static void io_double_put_req(struct io_kiocb *req) io_free_req(req); } -static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush) +static unsigned io_cqring_events(struct io_ring_ctx *ctx) { - struct io_rings *rings = ctx->rings; - - if (test_bit(0, &ctx->cq_check_overflow)) { - /* - * noflush == true is from the waitqueue handler, just ensure - * we wake up the task, and the next invocation will flush the - * entries. We cannot safely to it from here. - */ - if (noflush) - return -1U; - - io_cqring_overflow_flush(ctx, false, NULL, NULL); - } - /* See comment at the top of this file */ smp_rmb(); - return ctx->cached_cq_tail - READ_ONCE(rings->cq.head); + return __io_cqring_events(ctx); } static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) @@ -2431,8 +2491,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, } io_commit_cqring(ctx); - if (ctx->flags & IORING_SETUP_SQPOLL) - io_cqring_ev_posted(ctx); + io_cqring_ev_posted_iopoll(ctx); io_req_free_batch_finish(ctx, &rb); if (!list_empty(&again)) @@ -2558,7 +2617,9 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) * If we do, we can potentially be spinning for commands that * already triggered a CQE (eg in error). */ - if (io_cqring_events(ctx, false)) + if (test_bit(0, &ctx->cq_check_overflow)) + __io_cqring_overflow_flush(ctx, false, NULL, NULL); + if (io_cqring_events(ctx)) break; /* @@ -2675,6 +2736,8 @@ static bool io_rw_reissue(struct io_kiocb *req, long res) if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker()) return false; + lockdep_assert_held(&req->ctx->uring_lock); + ret = io_sq_thread_acquire_mm_files(req->ctx, req); if (io_resubmit_prep(req, ret)) { @@ -3136,9 +3199,7 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, iov[0].iov_len = kbuf->len; return 0; } - if (!req->rw.len) - return 0; - else if (req->rw.len > 1) + if (req->rw.len != 1) return -EINVAL; #ifdef CONFIG_COMPAT @@ -3506,7 +3567,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, /* read it all, or we did blocking attempt. no retry. */ if (!iov_iter_count(iter) || !force_nonblock || - (req->file->f_flags & O_NONBLOCK)) + (req->file->f_flags & O_NONBLOCK) || !(req->flags & REQ_F_ISREG)) goto done; io_size -= ret; @@ -3784,6 +3845,8 @@ static int io_shutdown(struct io_kiocb *req, bool force_nonblock) return -ENOTSOCK; ret = __sys_shutdown_sock(sock, req->shutdown.how); + if (ret < 0) + req_set_fail_links(req); io_req_complete(req, ret); return 0; #else @@ -4424,7 +4487,6 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) * io_wq_work.flags, so initialize io_wq_work firstly. */ io_req_init_async(req); - req->work.flags |= IO_WQ_WORK_NO_CANCEL; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; @@ -4457,6 +4519,8 @@ static int io_close(struct io_kiocb *req, bool force_nonblock, /* if the file has a flush method, be safe and punt to async */ if (close->put_file->f_op->flush && force_nonblock) { + /* not safe to cancel at this point */ + req->work.flags |= IO_WQ_WORK_NO_CANCEL; /* was never set, but play safe */ req->flags &= ~REQ_F_NOWAIT; /* avoid grabbing files - we don't need the files */ @@ -5813,6 +5877,12 @@ static int io_timeout(struct io_kiocb *req) tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); req->timeout.target_seq = tail + off; + /* Update the last seq here in case io_flush_timeouts() hasn't. + * This is safe because ->completion_lock is held, and submissions + * and completions are never mixed in the same ->completion_lock section. + */ + ctx->cq_last_tm_flush = tail; + /* * Insertion sort, ensuring the first entry in the list is always * the one we need first. @@ -6107,15 +6177,17 @@ static void io_req_drop_files(struct io_kiocb *req) struct io_uring_task *tctx = req->task->io_uring; unsigned long flags; + if (req->work.flags & IO_WQ_WORK_FILES) { + put_files_struct(req->work.identity->files); + put_nsproxy(req->work.identity->nsproxy); + } spin_lock_irqsave(&ctx->inflight_lock, flags); list_del(&req->inflight_entry); - if (atomic_read(&tctx->in_idle)) - wake_up(&tctx->wait); spin_unlock_irqrestore(&ctx->inflight_lock, flags); req->flags &= ~REQ_F_INFLIGHT; - put_files_struct(req->work.identity->files); - put_nsproxy(req->work.identity->nsproxy); req->work.flags &= ~IO_WQ_WORK_FILES; + if (atomic_read(&tctx->in_idle)) + wake_up(&tctx->wait); } static void __io_clean_op(struct io_kiocb *req) @@ -6175,9 +6247,6 @@ static void __io_clean_op(struct io_kiocb *req) } req->flags &= ~REQ_F_NEED_CLEANUP; } - - if (req->flags & REQ_F_INFLIGHT) - io_req_drop_files(req); } static int io_issue_sqe(struct io_kiocb *req, bool force_nonblock, @@ -6343,19 +6412,28 @@ static struct io_wq_work *io_wq_submit_work(struct io_wq_work *work) } if (ret) { + struct io_ring_ctx *lock_ctx = NULL; + + if (req->ctx->flags & IORING_SETUP_IOPOLL) + lock_ctx = req->ctx; + /* - * io_iopoll_complete() does not hold completion_lock to complete - * polled io, so here for polled io, just mark it done and still let - * io_iopoll_complete() complete it. + * io_iopoll_complete() does not hold completion_lock to + * complete polled io, so here for polled io, we can not call + * io_req_complete() directly, otherwise there maybe concurrent + * access to cqring, defer_list, etc, which is not safe. Given + * that io_iopoll_complete() is always called under uring_lock, + * so here for polled io, we also get uring_lock to complete + * it. */ - if (req->ctx->flags & IORING_SETUP_IOPOLL) { - struct kiocb *kiocb = &req->rw.kiocb; + if (lock_ctx) + mutex_lock(&lock_ctx->uring_lock); - kiocb_done(kiocb, ret, NULL); - } else { - req_set_fail_links(req); - io_req_complete(req, ret); - } + req_set_fail_links(req); + io_req_complete(req, ret); + + if (lock_ctx) + mutex_unlock(&lock_ctx->uring_lock); } return io_steal_work(req); @@ -6387,6 +6465,16 @@ static struct file *io_file_get(struct io_submit_state *state, file = __io_file_get(state, fd); } + if (file && file->f_op == &io_uring_fops && + !(req->flags & REQ_F_INFLIGHT)) { + io_req_init_async(req); + req->flags |= REQ_F_INFLIGHT; + + spin_lock_irq(&ctx->inflight_lock); + list_add(&req->inflight_entry, &ctx->inflight_list); + spin_unlock_irq(&ctx->inflight_lock); + } + return file; } @@ -6824,8 +6912,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) /* if we have a backlog and couldn't flush it all, return BUSY */ if (test_bit(0, &ctx->sq_check_overflow)) { - if (!list_empty(&ctx->cq_overflow_list) && - !io_cqring_overflow_flush(ctx, false, NULL, NULL)) + if (!__io_cqring_overflow_flush(ctx, false, NULL, NULL)) return -EBUSY; } @@ -6927,7 +7014,8 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) if (!list_empty(&ctx->iopoll_list)) io_do_iopoll(ctx, &nr_events, 0); - if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs))) + if (to_submit && !ctx->sqo_dead && + likely(!percpu_ref_is_dying(&ctx->refs))) ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); } @@ -7028,6 +7116,7 @@ static int io_sq_thread(void *data) if (sqt_spin || !time_after(jiffies, timeout)) { io_run_task_work(); + io_sq_thread_drop_mm_files(); cond_resched(); if (sqt_spin) timeout = jiffies + sqd->sq_thread_idle; @@ -7065,6 +7154,7 @@ static int io_sq_thread(void *data) } io_run_task_work(); + io_sq_thread_drop_mm_files(); if (cur_css) io_sq_thread_unassociate_blkcg(); @@ -7088,7 +7178,7 @@ struct io_wait_queue { unsigned nr_timeouts; }; -static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush) +static inline bool io_should_wake(struct io_wait_queue *iowq) { struct io_ring_ctx *ctx = iowq->ctx; @@ -7097,7 +7187,7 @@ static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush) * started waiting. For timeouts, we always want to return to userspace, * regardless of event count. */ - return io_cqring_events(ctx, noflush) >= iowq->to_wait || + return io_cqring_events(ctx) >= iowq->to_wait || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; } @@ -7107,11 +7197,13 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue, wq); - /* use noflush == true, as we can't safely rely on locking context */ - if (!io_should_wake(iowq, true)) - return -1; - - return autoremove_wake_function(curr, mode, wake_flags, key); + /* + * Cannot safely flush overflowed CQEs from here, ensure we wake up + * the task, and the next invocation will do it. + */ + if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->cq_check_overflow)) + return autoremove_wake_function(curr, mode, wake_flags, key); + return -1; } static int io_run_task_work_sig(void) @@ -7148,7 +7240,8 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, int ret = 0; do { - if (io_cqring_events(ctx, false) >= min_events) + io_cqring_overflow_flush(ctx, false, NULL, NULL); + if (io_cqring_events(ctx) >= min_events) return 0; if (!io_run_task_work()) break; @@ -7176,16 +7269,23 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); trace_io_uring_cqring_wait(ctx, min_events); do { + io_cqring_overflow_flush(ctx, false, NULL, NULL); prepare_to_wait_exclusive(&ctx->wait, &iowq.wq, TASK_INTERRUPTIBLE); /* make sure we run task_work before checking for signals */ ret = io_run_task_work_sig(); - if (ret > 0) + if (ret > 0) { + finish_wait(&ctx->wait, &iowq.wq); continue; + } else if (ret < 0) break; - if (io_should_wake(&iowq, false)) + if (io_should_wake(&iowq)) break; + if (test_bit(0, &ctx->cq_check_overflow)) { + finish_wait(&ctx->wait, &iowq.wq); + continue; + } if (uts) { timeout = schedule_timeout(timeout); if (timeout == 0) { @@ -7234,14 +7334,28 @@ static void io_file_ref_kill(struct percpu_ref *ref) complete(&data->done); } +static void io_sqe_files_set_node(struct fixed_file_data *file_data, + struct fixed_file_ref_node *ref_node) +{ + spin_lock_bh(&file_data->lock); + file_data->node = ref_node; + list_add_tail(&ref_node->node, &file_data->ref_list); + spin_unlock_bh(&file_data->lock); + percpu_ref_get(&file_data->refs); +} + static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { struct fixed_file_data *data = ctx->file_data; - struct fixed_file_ref_node *ref_node = NULL; + struct fixed_file_ref_node *backup_node, *ref_node = NULL; unsigned nr_tables, i; + int ret; if (!data) return -ENXIO; + backup_node = alloc_fixed_file_ref_node(ctx); + if (!backup_node) + return -ENOMEM; spin_lock_bh(&data->lock); ref_node = data->node; @@ -7253,7 +7367,18 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) /* wait for all refs nodes to complete */ flush_delayed_work(&ctx->file_put_work); - wait_for_completion(&data->done); + do { + ret = wait_for_completion_interruptible(&data->done); + if (!ret) + break; + ret = io_run_task_work_sig(); + if (ret < 0) { + percpu_ref_resurrect(&data->refs); + reinit_completion(&data->done); + io_sqe_files_set_node(data, backup_node); + return ret; + } + } while (1); __io_sqe_files_unregister(ctx); nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE); @@ -7264,6 +7389,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) kfree(data); ctx->file_data = NULL; ctx->nr_user_files = 0; + destroy_fixed_file_ref_node(backup_node); return 0; } @@ -7657,12 +7783,12 @@ static struct fixed_file_ref_node *alloc_fixed_file_ref_node( ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); if (!ref_node) - return ERR_PTR(-ENOMEM); + return NULL; if (percpu_ref_init(&ref_node->refs, io_file_data_ref_zero, 0, GFP_KERNEL)) { kfree(ref_node); - return ERR_PTR(-ENOMEM); + return NULL; } INIT_LIST_HEAD(&ref_node->node); INIT_LIST_HEAD(&ref_node->file_list); @@ -7756,16 +7882,12 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, } ref_node = alloc_fixed_file_ref_node(ctx); - if (IS_ERR(ref_node)) { + if (!ref_node) { io_sqe_files_unregister(ctx); - return PTR_ERR(ref_node); + return -ENOMEM; } - file_data->node = ref_node; - spin_lock_bh(&file_data->lock); - list_add_tail(&ref_node->node, &file_data->ref_list); - spin_unlock_bh(&file_data->lock); - percpu_ref_get(&file_data->refs); + io_sqe_files_set_node(file_data, ref_node); return ret; out_fput: for (i = 0; i < ctx->nr_user_files; i++) { @@ -7862,8 +7984,8 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, return -EINVAL; ref_node = alloc_fixed_file_ref_node(ctx); - if (IS_ERR(ref_node)) - return PTR_ERR(ref_node); + if (!ref_node) + return -ENOMEM; done = 0; fds = u64_to_user_ptr(up->fds); @@ -7921,11 +8043,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (needs_switch) { percpu_ref_kill(&data->node->refs); - spin_lock_bh(&data->lock); - list_add_tail(&ref_node->node, &data->ref_list); - data->node = ref_node; - spin_unlock_bh(&data->lock); - percpu_ref_get(&ctx->file_data->refs); + io_sqe_files_set_node(data, ref_node); } else destroy_fixed_file_ref_node(ref_node); @@ -8155,10 +8273,13 @@ static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages, __io_unaccount_mem(ctx->user, nr_pages); if (ctx->mm_account) { - if (acct == ACCT_LOCKED) + if (acct == ACCT_LOCKED) { + mmap_write_lock(ctx->mm_account); ctx->mm_account->locked_vm -= nr_pages; - else if (acct == ACCT_PINNED) + mmap_write_unlock(ctx->mm_account); + }else if (acct == ACCT_PINNED) { atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm); + } } } @@ -8174,10 +8295,13 @@ static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages, } if (ctx->mm_account) { - if (acct == ACCT_LOCKED) + if (acct == ACCT_LOCKED) { + mmap_write_lock(ctx->mm_account); ctx->mm_account->locked_vm += nr_pages; - else if (acct == ACCT_PINNED) + mmap_write_unlock(ctx->mm_account); + } else if (acct == ACCT_PINNED) { atomic64_add(nr_pages, &ctx->mm_account->pinned_vm); + } } return 0; @@ -8599,7 +8723,8 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) smp_rmb(); if (!io_sqring_full(ctx)) mask |= EPOLLOUT | EPOLLWRNORM; - if (io_cqring_events(ctx, false)) + io_cqring_overflow_flush(ctx, false, NULL, NULL); + if (io_cqring_events(ctx)) mask |= EPOLLIN | EPOLLRDNORM; return mask; @@ -8638,24 +8763,37 @@ static void io_ring_exit_work(struct work_struct *work) * as nobody else will be looking for them. */ do { - io_iopoll_try_reap_events(ctx); + __io_uring_cancel_task_requests(ctx, NULL); } while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20)); io_ring_ctx_free(ctx); } +static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + return req->ctx == data; +} + static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { mutex_lock(&ctx->uring_lock); percpu_ref_kill(&ctx->refs); + + if (WARN_ON_ONCE((ctx->flags & IORING_SETUP_SQPOLL) && !ctx->sqo_dead)) + ctx->sqo_dead = 1; + + /* if force is set, the ring is going away. always drop after that */ + ctx->cq_overflow_flushed = 1; if (ctx->rings) - io_cqring_overflow_flush(ctx, true, NULL, NULL); + __io_cqring_overflow_flush(ctx, true, NULL, NULL); mutex_unlock(&ctx->uring_lock); io_kill_timeouts(ctx, NULL, NULL); io_poll_remove_all(ctx, NULL, NULL); if (ctx->io_wq) - io_wq_cancel_all(ctx->io_wq); + io_wq_cancel_cb(ctx->io_wq, io_cancel_ctx_cb, ctx, true); /* if we failed setting up the ctx, we might not have any rings */ io_iopoll_try_reap_events(ctx); @@ -8739,39 +8877,44 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx, } } +static int io_uring_count_inflight(struct io_ring_ctx *ctx, + struct task_struct *task, + struct files_struct *files) +{ + struct io_kiocb *req; + int cnt = 0; + + spin_lock_irq(&ctx->inflight_lock); + list_for_each_entry(req, &ctx->inflight_list, inflight_entry) + cnt += io_match_task(req, task, files); + spin_unlock_irq(&ctx->inflight_lock); + return cnt; +} + static void io_uring_cancel_files(struct io_ring_ctx *ctx, struct task_struct *task, struct files_struct *files) { while (!list_empty_careful(&ctx->inflight_list)) { struct io_task_cancel cancel = { .task = task, .files = files }; - struct io_kiocb *req; DEFINE_WAIT(wait); - bool found = false; - - spin_lock_irq(&ctx->inflight_lock); - list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { - if (req->task != task || - req->work.identity->files != files) - continue; - found = true; - break; - } - if (found) - prepare_to_wait(&task->io_uring->wait, &wait, - TASK_UNINTERRUPTIBLE); - spin_unlock_irq(&ctx->inflight_lock); + int inflight; - /* We need to keep going until we don't find a matching req */ - if (!found) + inflight = io_uring_count_inflight(ctx, task, files); + if (!inflight) break; io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); io_poll_remove_all(ctx, task, files); io_kill_timeouts(ctx, task, files); + io_cqring_overflow_flush(ctx, true, task, files); /* cancellations _may_ trigger task work */ io_run_task_work(); - schedule(); + + prepare_to_wait(&task->io_uring->wait, &wait, + TASK_UNINTERRUPTIBLE); + if (inflight == io_uring_count_inflight(ctx, task, files)) + schedule(); finish_wait(&task->io_uring->wait, &wait); } } @@ -8784,9 +8927,11 @@ static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx, enum io_wq_cancel cret; bool ret = false; - cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); - if (cret != IO_WQ_CANCEL_NOTFOUND) - ret = true; + if (ctx->io_wq) { + cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, + &cancel, true); + ret |= (cret != IO_WQ_CANCEL_NOTFOUND); + } /* SQPOLL thread does its own polling */ if (!(ctx->flags & IORING_SETUP_SQPOLL)) { @@ -8798,13 +8943,24 @@ static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx, ret |= io_poll_remove_all(ctx, task, NULL); ret |= io_kill_timeouts(ctx, task, NULL); + ret |= io_run_task_work(); if (!ret) break; - io_run_task_work(); cond_resched(); } } +static void io_disable_sqo_submit(struct io_ring_ctx *ctx) +{ + mutex_lock(&ctx->uring_lock); + ctx->sqo_dead = 1; + mutex_unlock(&ctx->uring_lock); + + /* make sure callers enter the ring to get error */ + if (ctx->rings) + io_ring_set_wakeup_flag(ctx); +} + /* * We need to iteratively cancel requests, in case a request has dependent * hard links. These persist even for failure of cancelations, hence keep @@ -8816,29 +8972,21 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, struct task_struct *task = current; if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { + io_disable_sqo_submit(ctx); task = ctx->sq_data->thread; atomic_inc(&task->io_uring->in_idle); io_sq_thread_park(ctx->sq_data); } io_cancel_defer_files(ctx, task, files); - io_ring_submit_lock(ctx, (ctx->flags & IORING_SETUP_IOPOLL)); io_cqring_overflow_flush(ctx, true, task, files); - io_ring_submit_unlock(ctx, (ctx->flags & IORING_SETUP_IOPOLL)); + io_uring_cancel_files(ctx, task, files); if (!files) __io_uring_cancel_task_requests(ctx, task); - else - io_uring_cancel_files(ctx, task, files); if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { atomic_dec(&task->io_uring->in_idle); - /* - * If the files that are going away are the ones in the thread - * identity, clear them out. - */ - if (task->io_uring->identity->files == files) - task->io_uring->identity->files = NULL; io_sq_thread_unpark(ctx->sq_data); } } @@ -8849,10 +8997,9 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file) { struct io_uring_task *tctx = current->io_uring; + int ret; if (unlikely(!tctx)) { - int ret; - ret = io_uring_alloc_task_context(current); if (unlikely(ret)) return ret; @@ -8863,7 +9010,12 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file) if (!old) { get_file(file); - xa_store(&tctx->xa, (unsigned long)file, file, GFP_KERNEL); + ret = xa_err(xa_store(&tctx->xa, (unsigned long)file, + file, GFP_KERNEL)); + if (ret) { + fput(file); + return ret; + } } tctx->last = file; } @@ -8893,20 +9045,12 @@ static void io_uring_del_task_file(struct file *file) fput(file); } -/* - * Drop task note for this file if we're the only ones that hold it after - * pending fput() - */ -static void io_uring_attempt_task_drop(struct file *file) +static void io_uring_remove_task_files(struct io_uring_task *tctx) { - if (!current->io_uring) - return; - /* - * fput() is pending, will be 2 if the only other ref is our potential - * task file note. If the task is exiting, drop regardless of count. - */ - if (fatal_signal_pending(current) || (current->flags & PF_EXITING) || - atomic_long_read(&file->f_count) == 2) + struct file *file; + unsigned long index; + + xa_for_each(&tctx->xa, index, file) io_uring_del_task_file(file); } @@ -8918,16 +9062,12 @@ void __io_uring_files_cancel(struct files_struct *files) /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); - - xa_for_each(&tctx->xa, index, file) { - struct io_ring_ctx *ctx = file->private_data; - - io_uring_cancel_task_requests(ctx, files); - if (files) - io_uring_del_task_file(file); - } - + xa_for_each(&tctx->xa, index, file) + io_uring_cancel_task_requests(file->private_data, files); atomic_dec(&tctx->in_idle); + + if (files) + io_uring_remove_task_files(tctx); } static s64 tctx_inflight(struct io_uring_task *tctx) @@ -8970,6 +9110,10 @@ void __io_uring_task_cancel(void) /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); + /* trigger io_disable_sqo_submit() */ + if (tctx->sqpoll) + __io_uring_files_cancel(NULL); + do { /* read completions before cancelations */ inflight = tctx_inflight(tctx); @@ -8980,21 +9124,55 @@ void __io_uring_task_cancel(void) prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); /* - * If we've seen completions, retry. This avoids a race where - * a completion comes in before we did prepare_to_wait(). + * If we've seen completions, retry without waiting. This + * avoids a race where a completion comes in before we did + * prepare_to_wait(). */ - if (inflight != tctx_inflight(tctx)) - continue; - schedule(); + if (inflight == tctx_inflight(tctx)) + schedule(); + finish_wait(&tctx->wait, &wait); } while (1); - finish_wait(&tctx->wait, &wait); atomic_dec(&tctx->in_idle); + + io_uring_remove_task_files(tctx); } static int io_uring_flush(struct file *file, void *data) { - io_uring_attempt_task_drop(file); + struct io_uring_task *tctx = current->io_uring; + struct io_ring_ctx *ctx = file->private_data; + + if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) + io_uring_cancel_task_requests(ctx, NULL); + + if (!tctx) + return 0; + + /* we should have cancelled and erased it before PF_EXITING */ + WARN_ON_ONCE((current->flags & PF_EXITING) && + xa_load(&tctx->xa, (unsigned long)file)); + + /* + * fput() is pending, will be 2 if the only other ref is our potential + * task file note. If the task is exiting, drop regardless of count. + */ + if (atomic_long_read(&file->f_count) != 2) + return 0; + + if (ctx->flags & IORING_SETUP_SQPOLL) { + /* there is only one file note, which is owned by sqo_task */ + WARN_ON_ONCE(ctx->sqo_task != current && + xa_load(&tctx->xa, (unsigned long)file)); + /* sqo_dead check is for when this happens after cancellation */ + WARN_ON_ONCE(ctx->sqo_task == current && !ctx->sqo_dead && + !xa_load(&tctx->xa, (unsigned long)file)); + + io_disable_sqo_submit(ctx); + } + + if (!(ctx->flags & IORING_SETUP_SQPOLL) || ctx->sqo_task == current) + io_uring_del_task_file(file); return 0; } @@ -9068,8 +9246,9 @@ static unsigned long io_uring_nommu_get_unmapped_area(struct file *file, #endif /* !CONFIG_MMU */ -static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx) +static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx) { + int ret = 0; DEFINE_WAIT(wait); do { @@ -9078,6 +9257,11 @@ static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx) prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE); + if (unlikely(ctx->sqo_dead)) { + ret = -EOWNERDEAD; + goto out; + } + if (!io_sqring_full(ctx)) break; @@ -9085,6 +9269,8 @@ static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx) } while (!signal_pending(current)); finish_wait(&ctx->sqo_sq_wait, &wait); +out: + return ret; } static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz, @@ -9156,14 +9342,18 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, */ ret = 0; if (ctx->flags & IORING_SETUP_SQPOLL) { - io_ring_submit_lock(ctx, (ctx->flags & IORING_SETUP_IOPOLL)); - if (!list_empty_careful(&ctx->cq_overflow_list)) - io_cqring_overflow_flush(ctx, false, NULL, NULL); - io_ring_submit_unlock(ctx, (ctx->flags & IORING_SETUP_IOPOLL)); + io_cqring_overflow_flush(ctx, false, NULL, NULL); + + ret = -EOWNERDEAD; + if (unlikely(ctx->sqo_dead)) + goto out; if (flags & IORING_ENTER_SQ_WAKEUP) wake_up(&ctx->sq_data->wait); - if (flags & IORING_ENTER_SQ_WAIT) - io_sqpoll_wait_sq(ctx); + if (flags & IORING_ENTER_SQ_WAIT) { + ret = io_sqpoll_wait_sq(ctx); + if (ret) + goto out; + } submitted = to_submit; } else if (to_submit) { ret = io_uring_add_task_file(ctx, f.file); @@ -9369,55 +9559,52 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, return 0; } +static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) +{ + int ret, fd; + + fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); + if (fd < 0) + return fd; + + ret = io_uring_add_task_file(ctx, file); + if (ret) { + put_unused_fd(fd); + return ret; + } + fd_install(fd, file); + return fd; +} + /* * Allocate an anonymous fd, this is what constitutes the application * visible backing of an io_uring instance. The application mmaps this * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled, * we have to tie this fd to a socket for file garbage collection purposes. */ -static int io_uring_get_fd(struct io_ring_ctx *ctx) +static struct file *io_uring_get_file(struct io_ring_ctx *ctx) { struct file *file; +#if defined(CONFIG_UNIX) int ret; - int fd; -#if defined(CONFIG_UNIX) ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP, &ctx->ring_sock); if (ret) - return ret; + return ERR_PTR(ret); #endif - ret = get_unused_fd_flags(O_RDWR | O_CLOEXEC); - if (ret < 0) - goto err; - fd = ret; - file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx, O_RDWR | O_CLOEXEC); - if (IS_ERR(file)) { - put_unused_fd(fd); - ret = PTR_ERR(file); - goto err; - } - #if defined(CONFIG_UNIX) - ctx->ring_sock->file = file; -#endif - ret = io_uring_add_task_file(ctx, file); - if (ret) { - fput(file); - put_unused_fd(fd); - goto err; + if (IS_ERR(file)) { + sock_release(ctx->ring_sock); + ctx->ring_sock = NULL; + } else { + ctx->ring_sock->file = file; } - fd_install(fd, file); - return fd; -err: -#if defined(CONFIG_UNIX) - sock_release(ctx->ring_sock); - ctx->ring_sock = NULL; #endif - return ret; + return file; } static int io_uring_create(unsigned entries, struct io_uring_params *p, @@ -9425,6 +9612,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, { struct user_struct *user = NULL; struct io_ring_ctx *ctx; + struct file *file; bool limit_mem; int ret; @@ -9572,17 +9760,28 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, goto err; } + file = io_uring_get_file(ctx); + if (IS_ERR(file)) { + ret = PTR_ERR(file); + goto err; + } + /* * Install ring fd as the very last thing, so we don't risk someone * having closed it before we finish setup */ - ret = io_uring_get_fd(ctx); - if (ret < 0) - goto err; + ret = io_uring_install_fd(ctx, file); + if (ret < 0) { + io_disable_sqo_submit(ctx); + /* fput will clean it up */ + fput(file); + return ret; + } trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: + io_disable_sqo_submit(ctx); io_ring_ctx_wait_and_kill(ctx); return ret; } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 188f79d76988..2dc944442802 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1869,9 +1869,7 @@ static int load_superblock(journal_t *journal) if (jbd2_has_feature_fast_commit(journal)) { journal->j_fc_last = be32_to_cpu(sb->s_maxlen); - num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks); - if (!num_fc_blocks) - num_fc_blocks = JBD2_MIN_FC_BLOCKS; + num_fc_blocks = jbd2_journal_get_num_fc_blks(sb); if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS) journal->j_last = journal->j_fc_last - num_fc_blocks; journal->j_fc_first = journal->j_last + 1; @@ -2102,9 +2100,7 @@ jbd2_journal_initialize_fast_commit(journal_t *journal) journal_superblock_t *sb = journal->j_superblock; unsigned long long num_fc_blks; - num_fc_blks = be32_to_cpu(sb->s_num_fc_blks); - if (num_fc_blks == 0) - num_fc_blks = JBD2_MIN_FC_BLOCKS; + num_fc_blks = jbd2_journal_get_num_fc_blks(sb); if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS) return -ENOSPC; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index f277d023ebcd..c75719312147 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -14,6 +14,7 @@ #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> +#include <linux/uio.h> #include "kernfs-internal.h" @@ -180,11 +181,10 @@ static const struct seq_operations kernfs_seq_ops = { * it difficult to use seq_file. Implement simplistic custom buffering for * bin files. */ -static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, - char __user *user_buf, size_t count, - loff_t *ppos) +static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - ssize_t len = min_t(size_t, count, PAGE_SIZE); + struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); + ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE); const struct kernfs_ops *ops; char *buf; @@ -210,7 +210,7 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, of->event = atomic_read(&of->kn->attr.open->event); ops = kernfs_ops(of->kn); if (ops->read) - len = ops->read(of, buf, len, *ppos); + len = ops->read(of, buf, len, iocb->ki_pos); else len = -EINVAL; @@ -220,12 +220,12 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, if (len < 0) goto out_free; - if (copy_to_user(user_buf, buf, len)) { + if (copy_to_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } - *ppos += len; + iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) @@ -235,31 +235,14 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, return len; } -/** - * kernfs_fop_read - kernfs vfs read callback - * @file: file pointer - * @user_buf: data to write - * @count: number of bytes - * @ppos: starting offset - */ -static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) +static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct kernfs_open_file *of = kernfs_of(file); - - if (of->kn->flags & KERNFS_HAS_SEQ_SHOW) - return seq_read(file, user_buf, count, ppos); - else - return kernfs_file_direct_read(of, user_buf, count, ppos); + if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW) + return seq_read_iter(iocb, iter); + return kernfs_file_read_iter(iocb, iter); } -/** - * kernfs_fop_write - kernfs vfs write callback - * @file: file pointer - * @user_buf: data to write - * @count: number of bytes - * @ppos: starting offset - * +/* * Copy data in from userland and pass it to the matching kernfs write * operation. * @@ -269,20 +252,18 @@ static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf, * modify only the the value you're changing, then write entire buffer * back. */ -static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, - size_t count, loff_t *ppos) +static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct kernfs_open_file *of = kernfs_of(file); + struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); + ssize_t len = iov_iter_count(iter); const struct kernfs_ops *ops; - ssize_t len; char *buf; if (of->atomic_write_len) { - len = count; if (len > of->atomic_write_len) return -E2BIG; } else { - len = min_t(size_t, count, PAGE_SIZE); + len = min_t(size_t, len, PAGE_SIZE); } buf = of->prealloc_buf; @@ -293,7 +274,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, if (!buf) return -ENOMEM; - if (copy_from_user(buf, user_buf, len)) { + if (copy_from_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } @@ -312,7 +293,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, ops = kernfs_ops(of->kn); if (ops->write) - len = ops->write(of, buf, len, *ppos); + len = ops->write(of, buf, len, iocb->ki_pos); else len = -EINVAL; @@ -320,7 +301,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, mutex_unlock(&of->mutex); if (len > 0) - *ppos += len; + iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) @@ -673,7 +654,7 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) /* * Write path needs to atomic_write_len outside active reference. - * Cache it in open_file. See kernfs_fop_write() for details. + * Cache it in open_file. See kernfs_fop_write_iter() for details. */ of->atomic_write_len = ops->atomic_write_len; @@ -960,14 +941,16 @@ void kernfs_notify(struct kernfs_node *kn) EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { - .read = kernfs_fop_read, - .write = kernfs_fop_write, + .read_iter = kernfs_fop_read_iter, + .write_iter = kernfs_fop_write_iter, .llseek = generic_file_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, }; /** diff --git a/fs/namei.c b/fs/namei.c index 03d0e11e4f36..de74ad2bc6e2 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -630,6 +630,11 @@ static inline bool legitimize_path(struct nameidata *nd, static bool legitimize_links(struct nameidata *nd) { int i; + if (unlikely(nd->flags & LOOKUP_CACHED)) { + drop_links(nd); + nd->depth = 0; + return false; + } for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { @@ -669,17 +674,17 @@ static bool legitimize_root(struct nameidata *nd) */ /** - * unlazy_walk - try to switch to ref-walk mode. + * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data - * Returns: 0 on success, -ECHILD on failure + * Returns: true on success, false on failure * - * unlazy_walk attempts to legitimize the current nd->path and nd->root + * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. - * Nothing should touch nameidata between unlazy_walk() failure and + * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ -static int unlazy_walk(struct nameidata *nd) +static bool try_to_unlazy(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; @@ -694,30 +699,30 @@ static int unlazy_walk(struct nameidata *nd) goto out; rcu_read_unlock(); BUG_ON(nd->inode != parent->d_inode); - return 0; + return true; out1: nd->path.mnt = NULL; nd->path.dentry = NULL; out: rcu_read_unlock(); - return -ECHILD; + return false; } /** - * unlazy_child - try to switch to ref-walk mode. + * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data - * @dentry: child of nd->path.dentry - * @seq: seq number to check dentry against - * Returns: 0 on success, -ECHILD on failure + * @dentry: next dentry to step into + * @seq: seq number to check @dentry against + * Returns: true on success, false on failure * - * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry - * for ref-walk mode. @dentry must be a path found by a do_lookup call on - * @nd. Must be called from rcu-walk context. - * Nothing should touch nameidata between unlazy_child() failure and + * Similar to to try_to_unlazy(), but here we have the next dentry already + * picked by rcu-walk and want to legitimize that in addition to the current + * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. + * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ -static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq) +static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsigned seq) { BUG_ON(!(nd->flags & LOOKUP_RCU)); @@ -747,7 +752,7 @@ static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned se if (unlikely(!legitimize_root(nd))) goto out_dput; rcu_read_unlock(); - return 0; + return true; out2: nd->path.mnt = NULL; @@ -755,11 +760,11 @@ out1: nd->path.dentry = NULL; out: rcu_read_unlock(); - return -ECHILD; + return false; out_dput: rcu_read_unlock(); dput(dentry); - return -ECHILD; + return false; } static inline int d_revalidate(struct dentry *dentry, unsigned int flags) @@ -792,7 +797,8 @@ static int complete_walk(struct nameidata *nd) */ if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; - if (unlikely(unlazy_walk(nd))) + nd->flags &= ~LOOKUP_CACHED; + if (!try_to_unlazy(nd)) return -ECHILD; } @@ -1372,7 +1378,7 @@ static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, return -ENOENT; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) return 0; - if (unlazy_child(nd, dentry, seq)) + if (!try_to_unlazy_next(nd, dentry, seq)) return -ECHILD; // *path might've been clobbered by __follow_mount_rcu() path->mnt = nd->path.mnt; @@ -1466,7 +1472,7 @@ static struct dentry *lookup_fast(struct nameidata *nd, unsigned seq; dentry = __d_lookup_rcu(parent, &nd->last, &seq); if (unlikely(!dentry)) { - if (unlazy_walk(nd)) + if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); return NULL; } @@ -1493,9 +1499,9 @@ static struct dentry *lookup_fast(struct nameidata *nd, status = d_revalidate(dentry, nd->flags); if (likely(status > 0)) return dentry; - if (unlazy_child(nd, dentry, seq)) + if (!try_to_unlazy_next(nd, dentry, seq)) return ERR_PTR(-ECHILD); - if (unlikely(status == -ECHILD)) + if (status == -ECHILD) /* we'd been told to redo it in non-rcu mode */ status = d_revalidate(dentry, nd->flags); } else { @@ -1567,10 +1573,8 @@ static inline int may_lookup(struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); - if (err != -ECHILD) + if (err != -ECHILD || !try_to_unlazy(nd)) return err; - if (unlazy_walk(nd)) - return -ECHILD; } return inode_permission(nd->inode, MAY_EXEC); } @@ -1592,7 +1596,7 @@ static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq) // unlazy even if we fail to grab the link - cleanup needs it bool grabbed_link = legitimize_path(nd, link, seq); - if (unlazy_walk(nd) != 0 || !grabbed_link) + if (!try_to_unlazy(nd) != 0 || !grabbed_link) return -ECHILD; if (nd_alloc_stack(nd)) @@ -1634,7 +1638,7 @@ static const char *pick_link(struct nameidata *nd, struct path *link, touch_atime(&last->link); cond_resched(); } else if (atime_needs_update(&last->link, inode)) { - if (unlikely(unlazy_walk(nd))) + if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); touch_atime(&last->link); } @@ -1651,11 +1655,8 @@ static const char *pick_link(struct nameidata *nd, struct path *link, get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { res = get(NULL, inode, &last->done); - if (res == ERR_PTR(-ECHILD)) { - if (unlikely(unlazy_walk(nd))) - return ERR_PTR(-ECHILD); + if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd)) res = get(link->dentry, inode, &last->done); - } } else { res = get(link->dentry, inode, &last->done); } @@ -2114,8 +2115,10 @@ static int link_path_walk(const char *name, struct nameidata *nd) return PTR_ERR(name); while (*name=='/') name++; - if (!*name) + if (!*name) { + nd->dir_mode = 0; // short-circuit the 'hardening' idiocy return 0; + } /* At this point we know we have a real path component. */ for(;;) { @@ -2193,7 +2196,7 @@ OK: } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { - if (unlazy_walk(nd)) + if (!try_to_unlazy(nd)) return -ECHILD; } return -ENOTDIR; @@ -2207,6 +2210,10 @@ static const char *path_init(struct nameidata *nd, unsigned flags) int error; const char *s = nd->name->name; + /* LOOKUP_CACHED requires RCU, ask caller to retry */ + if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED) + return ERR_PTR(-EAGAIN); + if (!*s) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) @@ -3127,7 +3134,6 @@ static const char *open_last_lookups(struct nameidata *nd, struct inode *inode; struct dentry *dentry; const char *res; - int error; nd->flags |= op->intent; @@ -3151,9 +3157,8 @@ static const char *open_last_lookups(struct nameidata *nd, } else { /* create side of things */ if (nd->flags & LOOKUP_RCU) { - error = unlazy_walk(nd); - if (unlikely(error)) - return ERR_PTR(error); + if (!try_to_unlazy(nd)) + return ERR_PTR(-ECHILD); } audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* trailing slashes? */ @@ -3162,9 +3167,7 @@ static const char *open_last_lookups(struct nameidata *nd, } if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { - error = mnt_want_write(nd->path.mnt); - if (!error) - got_write = true; + got_write = !mnt_want_write(nd->path.mnt); /* * do _not_ fail yet - we might not need that or fail with * a different error; let lookup_open() decide; we'll be @@ -3323,10 +3326,8 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ error = may_open(&path, 0, op->open_flag); - if (error) - goto out2; - file->f_path.mnt = path.mnt; - error = finish_open(file, child, NULL); + if (!error) + error = vfs_open(&path, file); out2: mnt_drop_write(path.mnt); out: diff --git a/fs/namespace.c b/fs/namespace.c index 2b681f65ca04..9d33909d0f9e 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -156,10 +156,10 @@ static inline void mnt_add_count(struct mount *mnt, int n) /* * vfsmount lock must be held for write */ -unsigned int mnt_get_count(struct mount *mnt) +int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP - unsigned int count = 0; + int count = 0; int cpu; for_each_possible_cpu(cpu) { @@ -1139,6 +1139,7 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { LIST_HEAD(list); + int count; rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { @@ -1162,7 +1163,9 @@ static void mntput_no_expire(struct mount *mnt) */ smp_mb(); mnt_add_count(mnt, -1); - if (mnt_get_count(mnt)) { + count = mnt_get_count(mnt); + if (count != 0) { + WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; @@ -1710,8 +1713,6 @@ static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); - if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) - return -EINVAL; if (!may_mount()) return -EPERM; if (path->dentry != path->mnt->mnt_root) @@ -1725,6 +1726,7 @@ static int can_umount(const struct path *path, int flags) return 0; } +// caller is responsible for flags being sane int path_umount(struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); @@ -1746,6 +1748,10 @@ static int ksys_umount(char __user *name, int flags) struct path path; int ret; + // basic validity checks done first + if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) + return -EINVAL; + if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 816e1427f17e..04bf8066980c 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -1011,22 +1011,24 @@ nfs_delegation_find_inode_server(struct nfs_server *server, const struct nfs_fh *fhandle) { struct nfs_delegation *delegation; - struct inode *freeme, *res = NULL; + struct super_block *freeme = NULL; + struct inode *res = NULL; list_for_each_entry_rcu(delegation, &server->delegations, super_list) { spin_lock(&delegation->lock); if (delegation->inode != NULL && !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) && nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) { - freeme = igrab(delegation->inode); - if (freeme && nfs_sb_active(freeme->i_sb)) - res = freeme; + if (nfs_sb_active(server->super)) { + freeme = server->super; + res = igrab(delegation->inode); + } spin_unlock(&delegation->lock); if (res != NULL) return res; if (freeme) { rcu_read_unlock(); - iput(freeme); + nfs_sb_deactive(freeme); rcu_read_lock(); } return ERR_PTR(-EAGAIN); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index b840d0a91c9d..62d3189745cd 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -136,9 +136,29 @@ struct nfs_fs_context { } clone_data; }; -#define nfs_errorf(fc, fmt, ...) errorf(fc, fmt, ## __VA_ARGS__) -#define nfs_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__) -#define nfs_warnf(fc, fmt, ...) warnf(fc, fmt, ## __VA_ARGS__) +#define nfs_errorf(fc, fmt, ...) ((fc)->log.log ? \ + errorf(fc, fmt, ## __VA_ARGS__) : \ + ({ dprintk(fmt "\n", ## __VA_ARGS__); })) + +#define nfs_ferrorf(fc, fac, fmt, ...) ((fc)->log.log ? \ + errorf(fc, fmt, ## __VA_ARGS__) : \ + ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) + +#define nfs_invalf(fc, fmt, ...) ((fc)->log.log ? \ + invalf(fc, fmt, ## __VA_ARGS__) : \ + ({ dprintk(fmt "\n", ## __VA_ARGS__); -EINVAL; })) + +#define nfs_finvalf(fc, fac, fmt, ...) ((fc)->log.log ? \ + invalf(fc, fmt, ## __VA_ARGS__) : \ + ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); -EINVAL; })) + +#define nfs_warnf(fc, fmt, ...) ((fc)->log.log ? \ + warnf(fc, fmt, ## __VA_ARGS__) : \ + ({ dprintk(fmt "\n", ## __VA_ARGS__); })) + +#define nfs_fwarnf(fc, fac, fmt, ...) ((fc)->log.log ? \ + warnf(fc, fmt, ## __VA_ARGS__) : \ + ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc) { @@ -579,12 +599,14 @@ extern void nfs4_test_session_trunk(struct rpc_clnt *clnt, static inline struct inode *nfs_igrab_and_active(struct inode *inode) { - inode = igrab(inode); - if (inode != NULL && !nfs_sb_active(inode->i_sb)) { - iput(inode); - inode = NULL; + struct super_block *sb = inode->i_sb; + + if (sb && nfs_sb_active(sb)) { + if (igrab(inode)) + return inode; + nfs_sb_deactive(sb); } - return inode; + return NULL; } static inline void nfs_iput_and_deactive(struct inode *inode) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 0ce04e0e5d82..2f4679a62712 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3536,10 +3536,8 @@ static void nfs4_close_done(struct rpc_task *task, void *data) trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status); /* Handle Layoutreturn errors */ - if (pnfs_roc_done(task, calldata->inode, - &calldata->arg.lr_args, - &calldata->res.lr_res, - &calldata->res.lr_ret) == -EAGAIN) + if (pnfs_roc_done(task, &calldata->arg.lr_args, &calldata->res.lr_res, + &calldata->res.lr_ret) == -EAGAIN) goto out_restart; /* hmm. we are done with the inode, and in the process of freeing @@ -6384,10 +6382,8 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status); /* Handle Layoutreturn errors */ - if (pnfs_roc_done(task, data->inode, - &data->args.lr_args, - &data->res.lr_res, - &data->res.lr_ret) == -EAGAIN) + if (pnfs_roc_done(task, &data->args.lr_args, &data->res.lr_res, + &data->res.lr_ret) == -EAGAIN) goto out_restart; switch (task->tk_status) { @@ -6441,10 +6437,10 @@ static void nfs4_delegreturn_release(void *calldata) struct nfs4_delegreturndata *data = calldata; struct inode *inode = data->inode; + if (data->lr.roc) + pnfs_roc_release(&data->lr.arg, &data->lr.res, + data->res.lr_ret); if (inode) { - if (data->lr.roc) - pnfs_roc_release(&data->lr.arg, &data->lr.res, - data->res.lr_ret); nfs_post_op_update_inode_force_wcc(inode, &data->fattr); nfs_iput_and_deactive(inode); } @@ -6520,16 +6516,14 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, nfs_fattr_init(data->res.fattr); data->timestamp = jiffies; data->rpc_status = 0; - data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, cred); data->inode = nfs_igrab_and_active(inode); - if (data->inode) { + if (data->inode || issync) { + data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, + cred); if (data->lr.roc) { data->args.lr_args = &data->lr.arg; data->res.lr_res = &data->lr.res; } - } else if (data->lr.roc) { - pnfs_roc_release(&data->lr.arg, &data->lr.res, 0); - data->lr.roc = false; } task_setup_data.callback_data = data; @@ -7111,9 +7105,9 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f data->arg.new_lock_owner, ret); } else data->cancelled = true; + trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret); rpc_put_task(task); dprintk("%s: done, ret = %d!\n", __func__, ret); - trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret); return ret; } diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 984cc42ee54d..d09bcfd7db89 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -227,7 +227,7 @@ int nfs4_try_get_tree(struct fs_context *fc) fc, ctx->nfs_server.hostname, ctx->nfs_server.export_path); if (err) { - nfs_errorf(fc, "NFS4: Couldn't follow remote path"); + nfs_ferrorf(fc, MOUNT, "NFS4: Couldn't follow remote path"); dfprintk(MOUNT, "<-- nfs4_try_get_tree() = %d [error]\n", err); } else { dfprintk(MOUNT, "<-- nfs4_try_get_tree() = 0\n"); @@ -250,7 +250,7 @@ int nfs4_get_referral_tree(struct fs_context *fc) fc, ctx->nfs_server.hostname, ctx->nfs_server.export_path); if (err) { - nfs_errorf(fc, "NFS4: Couldn't follow remote path"); + nfs_ferrorf(fc, MOUNT, "NFS4: Couldn't follow remote path"); dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = %d [error]\n", err); } else { dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = 0\n"); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 07f59dc8cb2e..af64b4e6fd1f 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -324,6 +324,21 @@ pnfs_grab_inode_layout_hdr(struct pnfs_layout_hdr *lo) return NULL; } +/* + * Compare 2 layout stateid sequence ids, to see which is newer, + * taking into account wraparound issues. + */ +static bool pnfs_seqid_is_newer(u32 s1, u32 s2) +{ + return (s32)(s1 - s2) > 0; +} + +static void pnfs_barrier_update(struct pnfs_layout_hdr *lo, u32 newseq) +{ + if (pnfs_seqid_is_newer(newseq, lo->plh_barrier)) + lo->plh_barrier = newseq; +} + static void pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode, u32 seq) @@ -335,6 +350,7 @@ pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode, if (seq != 0) { WARN_ON_ONCE(lo->plh_return_seq != 0 && lo->plh_return_seq != seq); lo->plh_return_seq = seq; + pnfs_barrier_update(lo, seq); } } @@ -639,15 +655,6 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg, return rv; } -/* - * Compare 2 layout stateid sequence ids, to see which is newer, - * taking into account wraparound issues. - */ -static bool pnfs_seqid_is_newer(u32 s1, u32 s2) -{ - return (s32)(s1 - s2) > 0; -} - static bool pnfs_should_free_range(const struct pnfs_layout_range *lseg_range, const struct pnfs_layout_range *recall_range) @@ -984,8 +991,7 @@ pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new, new_barrier = be32_to_cpu(new->seqid); else if (new_barrier == 0) return; - if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier)) - lo->plh_barrier = new_barrier; + pnfs_barrier_update(lo, new_barrier); } static bool @@ -994,7 +1000,7 @@ pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo, { u32 seqid = be32_to_cpu(stateid->seqid); - return !pnfs_seqid_is_newer(seqid, lo->plh_barrier); + return !pnfs_seqid_is_newer(seqid, lo->plh_barrier) && lo->plh_barrier; } /* lget is set to 1 if called from inside send_layoutget call chain */ @@ -1152,7 +1158,7 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo, LIST_HEAD(freeme); spin_lock(&inode->i_lock); - if (!pnfs_layout_is_valid(lo) || !arg_stateid || + if (!pnfs_layout_is_valid(lo) || !nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid)) goto out_unlock; if (stateid) { @@ -1183,20 +1189,17 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo, return false; set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags); pnfs_get_layout_hdr(lo); + nfs4_stateid_copy(stateid, &lo->plh_stateid); + *cred = get_cred(lo->plh_lc_cred); if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) { - nfs4_stateid_copy(stateid, &lo->plh_stateid); - *cred = get_cred(lo->plh_lc_cred); if (lo->plh_return_seq != 0) stateid->seqid = cpu_to_be32(lo->plh_return_seq); if (iomode != NULL) *iomode = lo->plh_return_iomode; pnfs_clear_layoutreturn_info(lo); - return true; - } - nfs4_stateid_copy(stateid, &lo->plh_stateid); - *cred = get_cred(lo->plh_lc_cred); - if (iomode != NULL) + } else if (iomode != NULL) *iomode = IOMODE_ANY; + pnfs_barrier_update(lo, be32_to_cpu(stateid->seqid)); return true; } @@ -1509,10 +1512,8 @@ out_noroc: return false; } -int pnfs_roc_done(struct rpc_task *task, struct inode *inode, - struct nfs4_layoutreturn_args **argpp, - struct nfs4_layoutreturn_res **respp, - int *ret) +int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, + struct nfs4_layoutreturn_res **respp, int *ret) { struct nfs4_layoutreturn_args *arg = *argpp; int retval = -EAGAIN; @@ -1545,7 +1546,7 @@ int pnfs_roc_done(struct rpc_task *task, struct inode *inode, return 0; case -NFS4ERR_OLD_STATEID: if (!nfs4_layout_refresh_old_stateid(&arg->stateid, - &arg->range, inode)) + &arg->range, arg->inode)) break; *ret = -NFS4ERR_NOMATCHING_LAYOUT; return -EAGAIN; @@ -1560,23 +1561,28 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args, int ret) { struct pnfs_layout_hdr *lo = args->layout; - const nfs4_stateid *arg_stateid = NULL; + struct inode *inode = args->inode; const nfs4_stateid *res_stateid = NULL; struct nfs4_xdr_opaque_data *ld_private = args->ld_private; switch (ret) { case -NFS4ERR_NOMATCHING_LAYOUT: + spin_lock(&inode->i_lock); + if (pnfs_layout_is_valid(lo) && + nfs4_stateid_match_other(&args->stateid, &lo->plh_stateid)) + pnfs_set_plh_return_info(lo, args->range.iomode, 0); + pnfs_clear_layoutreturn_waitbit(lo); + spin_unlock(&inode->i_lock); break; case 0: if (res->lrs_present) res_stateid = &res->stateid; fallthrough; default: - arg_stateid = &args->stateid; + pnfs_layoutreturn_free_lsegs(lo, &args->stateid, &args->range, + res_stateid); } trace_nfs4_layoutreturn_on_close(args->inode, &args->stateid, ret); - pnfs_layoutreturn_free_lsegs(lo, arg_stateid, &args->range, - res_stateid); if (ld_private && ld_private->ops && ld_private->ops->free) ld_private->ops->free(ld_private); pnfs_put_layout_hdr(lo); @@ -1906,6 +1912,11 @@ static void nfs_layoutget_end(struct pnfs_layout_hdr *lo) wake_up_var(&lo->plh_outstanding); } +static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo) +{ + return test_bit(NFS_LAYOUT_FIRST_LAYOUTGET, &lo->plh_flags); +} + static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo) { unsigned long *bitlock = &lo->plh_flags; @@ -2015,6 +2026,27 @@ lookup_again: goto lookup_again; } + /* + * Because we free lsegs when sending LAYOUTRETURN, we need to wait + * for LAYOUTRETURN. + */ + if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) { + spin_unlock(&ino->i_lock); + dprintk("%s wait for layoutreturn\n", __func__); + lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo)); + if (!IS_ERR(lseg)) { + pnfs_put_layout_hdr(lo); + dprintk("%s retrying\n", __func__); + trace_pnfs_update_layout(ino, pos, count, iomode, lo, + lseg, + PNFS_UPDATE_LAYOUT_RETRY); + goto lookup_again; + } + trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, + PNFS_UPDATE_LAYOUT_RETURN); + goto out_put_layout_hdr; + } + lseg = pnfs_find_lseg(lo, &arg, strict_iomode); if (lseg) { trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, @@ -2067,28 +2099,6 @@ lookup_again: nfs4_stateid_copy(&stateid, &lo->plh_stateid); } - /* - * Because we free lsegs before sending LAYOUTRETURN, we need to wait - * for LAYOUTRETURN even if first is true. - */ - if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) { - spin_unlock(&ino->i_lock); - dprintk("%s wait for layoutreturn\n", __func__); - lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo)); - if (!IS_ERR(lseg)) { - if (first) - pnfs_clear_first_layoutget(lo); - pnfs_put_layout_hdr(lo); - dprintk("%s retrying\n", __func__); - trace_pnfs_update_layout(ino, pos, count, iomode, lo, - lseg, PNFS_UPDATE_LAYOUT_RETRY); - goto lookup_again; - } - trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, - PNFS_UPDATE_LAYOUT_RETURN); - goto out_put_layout_hdr; - } - if (pnfs_layoutgets_blocked(lo)) { trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, PNFS_UPDATE_LAYOUT_BLOCKED); @@ -2242,6 +2252,7 @@ static void _lgopen_prepare_attached(struct nfs4_opendata *data, &rng, GFP_KERNEL); if (!lgp) { pnfs_clear_first_layoutget(lo); + nfs_layoutget_end(lo); pnfs_put_layout_hdr(lo); return; } @@ -2380,23 +2391,34 @@ pnfs_layout_process(struct nfs4_layoutget *lgp) goto out_forget; } - if (!pnfs_layout_is_valid(lo)) { - /* We have a completely new layout */ - pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true); - } else if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) { + if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) { /* existing state ID, make sure the sequence number matches. */ if (pnfs_layout_stateid_blocked(lo, &res->stateid)) { + if (!pnfs_layout_is_valid(lo) && + pnfs_is_first_layoutget(lo)) + lo->plh_barrier = 0; dprintk("%s forget reply due to sequence\n", __func__); goto out_forget; } pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, false); - } else { + } else if (pnfs_layout_is_valid(lo)) { /* * We got an entirely new state ID. Mark all segments for the * inode invalid, and retry the layoutget */ - pnfs_mark_layout_stateid_invalid(lo, &free_me); + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .length = NFS4_MAX_UINT64, + }; + pnfs_set_plh_return_info(lo, IOMODE_ANY, 0); + pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + &range, 0); goto out_forget; + } else { + /* We have a completely new layout */ + if (!pnfs_is_first_layoutget(lo)) + goto out_forget; + pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true); } pnfs_get_lseg(lseg); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index bbd3de1025f2..d810ae674f4e 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -297,10 +297,8 @@ bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, const struct cred *cred); -int pnfs_roc_done(struct rpc_task *task, struct inode *inode, - struct nfs4_layoutreturn_args **argpp, - struct nfs4_layoutreturn_res **respp, - int *ret); +int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, + struct nfs4_layoutreturn_res **respp, int *ret); void pnfs_roc_release(struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, int ret); @@ -772,7 +770,7 @@ pnfs_roc(struct inode *ino, } static inline int -pnfs_roc_done(struct rpc_task *task, struct inode *inode, +pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, struct nfs4_layoutreturn_res **respp, int *ret) diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 2efcfdd348a1..49d3389bd813 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -78,22 +78,18 @@ void pnfs_generic_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo) { - struct pnfs_layout_segment *freeme = NULL; + struct pnfs_commit_bucket *bucket = NULL; if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags)) goto out; cinfo->ds->nwritten--; - if (list_is_singular(&req->wb_list)) { - struct pnfs_commit_bucket *bucket; - + if (list_is_singular(&req->wb_list)) bucket = list_first_entry(&req->wb_list, - struct pnfs_commit_bucket, - written); - freeme = pnfs_free_bucket_lseg(bucket); - } + struct pnfs_commit_bucket, written); out: nfs_request_remove_commit_list(req, cinfo); - pnfs_put_lseg(freeme); + if (bucket) + pnfs_put_lseg(pnfs_free_bucket_lseg(bucket)); } EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit); @@ -407,12 +403,16 @@ pnfs_bucket_get_committing(struct list_head *head, struct pnfs_commit_bucket *bucket, struct nfs_commit_info *cinfo) { + struct pnfs_layout_segment *lseg; struct list_head *pos; list_for_each(pos, &bucket->committing) cinfo->ds->ncommitting--; list_splice_init(&bucket->committing, head); - return pnfs_free_bucket_lseg(bucket); + lseg = pnfs_free_bucket_lseg(bucket); + if (!lseg) + lseg = pnfs_get_lseg(bucket->lseg); + return lseg; } static struct nfs_commit_data * @@ -424,8 +424,6 @@ pnfs_bucket_fetch_commitdata(struct pnfs_commit_bucket *bucket, if (!data) return NULL; data->lseg = pnfs_bucket_get_committing(&data->pages, bucket, cinfo); - if (!data->lseg) - data->lseg = pnfs_get_lseg(bucket->lseg); return data; } diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 821db21ba072..34b880211e5e 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -865,9 +865,14 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, if (isdotent(name, namlen)) { if (namlen == 2) { dchild = dget_parent(dparent); - /* filesystem root - cannot return filehandle for ".." */ + /* + * Don't return filehandle for ".." if we're at + * the filesystem or export root: + */ if (dchild == dparent) goto out; + if (dparent == exp->ex_path.dentry) + goto out; } else dchild = dget(dparent); } else diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 4727b7f03c5b..8d6d2678abad 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -50,6 +50,11 @@ #include "pnfs.h" #include "trace.h" +static bool inter_copy_offload_enable; +module_param(inter_copy_offload_enable, bool, 0644); +MODULE_PARM_DESC(inter_copy_offload_enable, + "Enable inter server to server copy offload. Default: false"); + #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #include <linux/security.h> diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 45ee6b12ce5b..eaaa1605b5b5 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -147,6 +147,25 @@ svcxdr_dupstr(struct nfsd4_compoundargs *argp, void *buf, u32 len) return p; } +static void * +svcxdr_savemem(struct nfsd4_compoundargs *argp, __be32 *p, u32 len) +{ + __be32 *tmp; + + /* + * The location of the decoded data item is stable, + * so @p is OK to use. This is the common case. + */ + if (p != argp->xdr->scratch.iov_base) + return p; + + tmp = svcxdr_tmpalloc(argp, len); + if (!tmp) + return NULL; + memcpy(tmp, p, len); + return tmp; +} + /* * NFSv4 basic data type decoders */ @@ -183,11 +202,10 @@ nfsd4_decode_opaque(struct nfsd4_compoundargs *argp, struct xdr_netobj *o) p = xdr_inline_decode(argp->xdr, len); if (!p) return nfserr_bad_xdr; - o->data = svcxdr_tmpalloc(argp, len); + o->data = svcxdr_savemem(argp, p, len); if (!o->data) return nfserr_jukebox; o->len = len; - memcpy(o->data, p, len); return nfs_ok; } @@ -205,10 +223,9 @@ nfsd4_decode_component4(struct nfsd4_compoundargs *argp, char **namp, u32 *lenp) status = check_filename((char *)p, *lenp); if (status) return status; - *namp = svcxdr_tmpalloc(argp, *lenp); + *namp = svcxdr_savemem(argp, p, *lenp); if (!*namp) return nfserr_jukebox; - memcpy(*namp, p, *lenp); return nfs_ok; } @@ -1200,10 +1217,9 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) p = xdr_inline_decode(argp->xdr, putfh->pf_fhlen); if (!p) return nfserr_bad_xdr; - putfh->pf_fhval = svcxdr_tmpalloc(argp, putfh->pf_fhlen); + putfh->pf_fhval = svcxdr_savemem(argp, p, putfh->pf_fhlen); if (!putfh->pf_fhval) return nfserr_jukebox; - memcpy(putfh->pf_fhval, p, putfh->pf_fhlen); return nfs_ok; } @@ -1318,24 +1334,20 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient p = xdr_inline_decode(argp->xdr, setclientid->se_callback_netid_len); if (!p) return nfserr_bad_xdr; - setclientid->se_callback_netid_val = svcxdr_tmpalloc(argp, + setclientid->se_callback_netid_val = svcxdr_savemem(argp, p, setclientid->se_callback_netid_len); if (!setclientid->se_callback_netid_val) return nfserr_jukebox; - memcpy(setclientid->se_callback_netid_val, p, - setclientid->se_callback_netid_len); if (xdr_stream_decode_u32(argp->xdr, &setclientid->se_callback_addr_len) < 0) return nfserr_bad_xdr; p = xdr_inline_decode(argp->xdr, setclientid->se_callback_addr_len); if (!p) return nfserr_bad_xdr; - setclientid->se_callback_addr_val = svcxdr_tmpalloc(argp, + setclientid->se_callback_addr_val = svcxdr_savemem(argp, p, setclientid->se_callback_addr_len); if (!setclientid->se_callback_addr_val) return nfserr_jukebox; - memcpy(setclientid->se_callback_addr_val, p, - setclientid->se_callback_addr_len); if (xdr_stream_decode_u32(argp->xdr, &setclientid->se_callback_ident) < 0) return nfserr_bad_xdr; @@ -1375,10 +1387,9 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify p = xdr_inline_decode(argp->xdr, verify->ve_attrlen); if (!p) return nfserr_bad_xdr; - verify->ve_attrval = svcxdr_tmpalloc(argp, verify->ve_attrlen); + verify->ve_attrval = svcxdr_savemem(argp, p, verify->ve_attrlen); if (!verify->ve_attrval) return nfserr_jukebox; - memcpy(verify->ve_attrval, p, verify->ve_attrlen); return nfs_ok; } @@ -2333,10 +2344,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) p = xdr_inline_decode(argp->xdr, argp->taglen); if (!p) return 0; - argp->tag = svcxdr_tmpalloc(argp, argp->taglen); + argp->tag = svcxdr_savemem(argp, p, argp->taglen); if (!argp->tag) return 0; - memcpy(argp->tag, p, argp->taglen); max_reply += xdr_align_size(argp->taglen); } @@ -4756,6 +4766,7 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, resp->rqstp->rq_vec, read->rd_vlen, maxcount, eof); if (nfserr) return nfserr; + xdr_truncate_encode(xdr, starting_len + 16 + xdr_align_size(*maxcount)); tmp = htonl(NFS4_CONTENT_DATA); write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); @@ -4763,6 +4774,10 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp64, 8); tmp = htonl(*maxcount); write_bytes_to_xdr_buf(xdr->buf, starting_len + 12, &tmp, 4); + + tmp = xdr_zero; + write_bytes_to_xdr_buf(xdr->buf, starting_len + 16 + *maxcount, &tmp, + xdr_pad_size(*maxcount)); return nfs_ok; } @@ -4855,14 +4870,15 @@ out: if (nfserr && segments == 0) xdr_truncate_encode(xdr, starting_len); else { - tmp = htonl(eof); - write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); - tmp = htonl(segments); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); if (nfserr) { xdr_truncate_encode(xdr, last_segment); nfserr = nfs_ok; + eof = 0; } + tmp = htonl(eof); + write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); + tmp = htonl(segments); + write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); } return nfserr; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 00384c332f9b..f9c9f4c63cc7 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -33,12 +33,6 @@ #define NFSDDBG_FACILITY NFSDDBG_SVC -bool inter_copy_offload_enable; -EXPORT_SYMBOL_GPL(inter_copy_offload_enable); -module_param(inter_copy_offload_enable, bool, 0644); -MODULE_PARM_DESC(inter_copy_offload_enable, - "Enable inter server to server copy offload. Default: false"); - extern struct svc_program nfsd_program; static int nfsd(void *vrqstp); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index a60ff5ce1a37..c300885ae75d 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -568,7 +568,6 @@ struct nfsd4_copy { struct nfs_fh c_fh; nfs4_stateid stateid; }; -extern bool inter_copy_offload_enable; struct nfsd4_seek { /* request */ diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 64bc81363c6c..e1bd592ce700 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -141,6 +141,7 @@ const struct file_operations nilfs_file_operations = { /* .release = nilfs_release_file, */ .fsync = nilfs_sync_file, .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, }; const struct inode_operations nilfs_file_inode_operations = { diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 3e01d8f2ab90..dcab112e1f00 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1285,26 +1285,23 @@ fput_and_out: return ret; } +#ifndef CONFIG_ARCH_SPLIT_ARG64 SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags, __u64, mask, int, dfd, const char __user *, pathname) { return do_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname); } +#endif -#ifdef CONFIG_COMPAT -COMPAT_SYSCALL_DEFINE6(fanotify_mark, +#if defined(CONFIG_ARCH_SPLIT_ARG64) || defined(CONFIG_COMPAT) +SYSCALL32_DEFINE6(fanotify_mark, int, fanotify_fd, unsigned int, flags, - __u32, mask0, __u32, mask1, int, dfd, + SC_ARG64(mask), int, dfd, const char __user *, pathname) { - return do_fanotify_mark(fanotify_fd, flags, -#ifdef __BIG_ENDIAN - ((__u64)mask0 << 32) | mask1, -#else - ((__u64)mask1 << 32) | mask0, -#endif - dfd, pathname); + return do_fanotify_mark(fanotify_fd, flags, SC_VAL64(__u64, mask), + dfd, pathname); } #endif diff --git a/fs/open.c b/fs/open.c index 1e06e443a565..ca5444733acd 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1091,6 +1091,12 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; + if (how->resolve & RESOLVE_CACHED) { + /* Don't bother even trying for create/truncate/tmpfile open */ + if (flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + return -EAGAIN; + lookup_flags |= LOOKUP_CACHED; + } op->lookup_flags = lookup_flags; return 0; diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index af375e049aae..ec8ae4257975 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -663,6 +663,8 @@ const struct file_operations orangefs_file_operations = { .unlocked_ioctl = orangefs_ioctl, .mmap = orangefs_file_mmap, .open = generic_file_open, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .flush = orangefs_flush, .release = orangefs_file_release, .fsync = orangefs_fsync, diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index e5b616c93e11..0fed532efa68 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -84,6 +84,14 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old, if (ovl_is_private_xattr(sb, name)) continue; + + error = security_inode_copy_up_xattr(name); + if (error < 0 && error != -EOPNOTSUPP) + break; + if (error == 1) { + error = 0; + continue; /* Discard */ + } retry: size = vfs_getxattr(old, name, value, value_size); if (size == -ERANGE) @@ -107,13 +115,6 @@ retry: goto retry; } - error = security_inode_copy_up_xattr(name); - if (error < 0 && error != -EOPNOTSUPP) - break; - if (error == 1) { - error = 0; - continue; /* Discard */ - } error = vfs_setxattr(new, name, value, size, 0); if (error) { if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name)) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 28a075b5f5b2..d1efa3a5a503 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -992,8 +992,8 @@ static char *ovl_get_redirect(struct dentry *dentry, bool abs_redirect) buflen -= thislen; memcpy(&buf[buflen], name, thislen); - tmp = dget_dlock(d->d_parent); spin_unlock(&d->d_lock); + tmp = dget_parent(d); dput(d); d = tmp; diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index bd9dd38347ae..077d3ad343f6 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -398,8 +398,9 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) const struct cred *old_cred; int ret; - if (!ovl_should_sync(OVL_FS(file_inode(file)->i_sb))) - return 0; + ret = ovl_sync_status(OVL_FS(file_inode(file)->i_sb)); + if (ret <= 0) + return ret; ret = ovl_real_fdget_meta(file, &real, !datasync); if (ret) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d739e14c6814..cf41bcb664bc 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -352,7 +352,9 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, goto out; if (!value && !upperdentry) { + old_cred = ovl_override_creds(dentry->d_sb); err = vfs_getxattr(realdentry, name, NULL, 0); + revert_creds(old_cred); if (err < 0) goto out_drop_write; } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index b487e48c7fd4..cb4e2d60ecf9 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -324,6 +324,7 @@ int ovl_check_metacopy_xattr(struct ovl_fs *ofs, struct dentry *dentry); bool ovl_is_metacopy_dentry(struct dentry *dentry); char *ovl_get_redirect_xattr(struct ovl_fs *ofs, struct dentry *dentry, int padding); +int ovl_sync_status(struct ovl_fs *ofs); static inline bool ovl_is_impuredir(struct super_block *sb, struct dentry *dentry) diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index fbd5e27ce66b..63efee554f69 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -81,6 +81,8 @@ struct ovl_fs { atomic_long_t last_ino; /* Whiteout dentry cache */ struct dentry *whiteout; + /* r/o snapshot of upperdir sb's only taken on volatile mounts */ + errseq_t errseq; }; static inline struct vfsmount *ovl_upper_mnt(struct ovl_fs *ofs) diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 01620ebae1bd..f404a78e6b60 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -865,7 +865,7 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper) struct ovl_dir_file *od = file->private_data; struct dentry *dentry = file->f_path.dentry; - struct file *realfile = od->realfile; + struct file *old, *realfile = od->realfile; if (!OVL_TYPE_UPPER(ovl_path_type(dentry))) return want_upper ? NULL : realfile; @@ -874,29 +874,20 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper) * Need to check if we started out being a lower dir, but got copied up */ if (!od->is_upper) { - struct inode *inode = file_inode(file); - realfile = READ_ONCE(od->upperfile); if (!realfile) { struct path upperpath; ovl_path_upper(dentry, &upperpath); realfile = ovl_dir_open_realfile(file, &upperpath); + if (IS_ERR(realfile)) + return realfile; - inode_lock(inode); - if (!od->upperfile) { - if (IS_ERR(realfile)) { - inode_unlock(inode); - return realfile; - } - smp_store_release(&od->upperfile, realfile); - } else { - /* somebody has beaten us to it */ - if (!IS_ERR(realfile)) - fput(realfile); - realfile = od->upperfile; + old = cmpxchg_release(&od->upperfile, NULL, realfile); + if (old) { + fput(realfile); + realfile = old; } - inode_unlock(inode); } } @@ -909,8 +900,9 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, struct file *realfile; int err; - if (!ovl_should_sync(OVL_FS(file->f_path.dentry->d_sb))) - return 0; + err = ovl_sync_status(OVL_FS(file->f_path.dentry->d_sb)); + if (err <= 0) + return err; realfile = ovl_dir_real_file(file, true); err = PTR_ERR_OR_ZERO(realfile); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 2bd570cbe8a4..d58b8f2bf9d0 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -264,11 +264,20 @@ static int ovl_sync_fs(struct super_block *sb, int wait) struct super_block *upper_sb; int ret; - if (!ovl_upper_mnt(ofs)) - return 0; + ret = ovl_sync_status(ofs); + /* + * We have to always set the err, because the return value isn't + * checked in syncfs, and instead indirectly return an error via + * the sb's writeback errseq, which VFS inspects after this call. + */ + if (ret < 0) { + errseq_set(&sb->s_wb_err, -EIO); + return -EIO; + } + + if (!ret) + return ret; - if (!ovl_should_sync(ofs)) - return 0; /* * Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC). * All the super blocks will be iterated, including upper_sb. @@ -1923,6 +1932,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) unsigned int numlower; int err; + err = -EIO; + if (WARN_ON(sb->s_user_ns != current_user_ns())) + goto out; + sb->s_d_op = &ovl_dentry_operations; err = -ENOMEM; @@ -1989,6 +2002,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &ovl_super_operations; if (ofs->config.upperdir) { + struct super_block *upper_sb; + if (!ofs->config.workdir) { pr_err("missing 'workdir'\n"); goto out_err; @@ -1998,6 +2013,16 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (err) goto out_err; + upper_sb = ovl_upper_mnt(ofs)->mnt_sb; + if (!ovl_should_sync(ofs)) { + ofs->errseq = errseq_sample(&upper_sb->s_wb_err); + if (errseq_check(&upper_sb->s_wb_err, ofs->errseq)) { + err = -EIO; + pr_err("Cannot mount volatile when upperdir has an unseen error. Sync upperdir fs to clear state.\n"); + goto out_err; + } + } + err = ovl_get_workdir(sb, ofs, &upperpath); if (err) goto out_err; @@ -2005,9 +2030,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (!ofs->workdir) sb->s_flags |= SB_RDONLY; - sb->s_stack_depth = ovl_upper_mnt(ofs)->mnt_sb->s_stack_depth; - sb->s_time_gran = ovl_upper_mnt(ofs)->mnt_sb->s_time_gran; - + sb->s_stack_depth = upper_sb->s_stack_depth; + sb->s_time_gran = upper_sb->s_time_gran; } oe = ovl_get_lowerstack(sb, splitlower, numlower, ofs, layers); err = PTR_ERR(oe); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 6569031af3cd..9826b003f1d2 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -962,3 +962,30 @@ err_free: kfree(buf); return ERR_PTR(res); } + +/* + * ovl_sync_status() - Check fs sync status for volatile mounts + * + * Returns 1 if this is not a volatile mount and a real sync is required. + * + * Returns 0 if syncing can be skipped because mount is volatile, and no errors + * have occurred on the upperdir since the mount. + * + * Returns -errno if it is a volatile mount, and the error that occurred since + * the last mount. If the error code changes, it'll return the latest error + * code. + */ + +int ovl_sync_status(struct ovl_fs *ofs) +{ + struct vfsmount *mnt; + + if (ovl_should_sync(ofs)) + return 1; + + mnt = ovl_upper_mnt(ofs); + if (!mnt) + return 0; + + return errseq_check(&mnt->mnt_sb->s_wb_err, ofs->errseq); +} diff --git a/fs/pipe.c b/fs/pipe.c index c5989cfd564d..39c96845a72f 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1206,6 +1206,7 @@ const struct file_operations pipefifo_fops = { .unlocked_ioctl = pipe_ioctl, .release = pipe_release, .fasync = pipe_fasync, + .splice_write = iter_file_splice_write, }; /* diff --git a/fs/pnode.h b/fs/pnode.h index 49a058c73e4c..26f74e092bd9 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -44,7 +44,7 @@ int propagate_mount_busy(struct mount *, int); void propagate_mount_unlock(struct mount *); void mnt_release_group_id(struct mount *); int get_dominating_id(struct mount *mnt, const struct path *root); -unsigned int mnt_get_count(struct mount *mnt); +int mnt_get_count(struct mount *mnt); void mnt_set_mountpoint(struct mount *, struct mountpoint *, struct mount *); void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 317899222d7f..d2018f70d1fa 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1770,6 +1770,12 @@ static int process_sysctl_arg(char *param, char *val, return 0; } + if (!val) + return -EINVAL; + len = strlen(val); + if (len == 0) + return -EINVAL; + /* * To set sysctl options, we use a temporary mount of proc, look up the * respective sys/ file and write to it. To avoid mounting it when no @@ -1811,7 +1817,6 @@ static int process_sysctl_arg(char *param, char *val, file, param, val); goto out; } - len = strlen(val); wret = kernel_write(file, val, len, &pos); if (wret < 0) { err = wret; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ee5a235b3056..602e3a52884d 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1035,6 +1035,25 @@ struct clear_refs_private { }; #ifdef CONFIG_MEM_SOFT_DIRTY + +#define is_cow_mapping(flags) (((flags) & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE) + +static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte) +{ + struct page *page; + + if (!pte_write(pte)) + return false; + if (!is_cow_mapping(vma->vm_flags)) + return false; + if (likely(!atomic_read(&vma->vm_mm->has_pinned))) + return false; + page = vm_normal_page(vma, addr, pte); + if (!page) + return false; + return page_maybe_dma_pinned(page); +} + static inline void clear_soft_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *pte) { @@ -1049,6 +1068,8 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, if (pte_present(ptent)) { pte_t old_pte; + if (pte_is_pinned(vma, addr, ptent)) + return; old_pte = ptep_modify_prot_start(vma, addr, pte); ptent = pte_wrprotect(old_pte); ptent = pte_clear_soft_dirty(ptent); @@ -1215,41 +1236,26 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, .type = type, }; + if (mmap_write_lock_killable(mm)) { + count = -EINTR; + goto out_mm; + } if (type == CLEAR_REFS_MM_HIWATER_RSS) { - if (mmap_write_lock_killable(mm)) { - count = -EINTR; - goto out_mm; - } - /* * Writing 5 to /proc/pid/clear_refs resets the peak * resident set size to this mm's current rss value. */ reset_mm_hiwater_rss(mm); - mmap_write_unlock(mm); - goto out_mm; + goto out_unlock; } - if (mmap_read_lock_killable(mm)) { - count = -EINTR; - goto out_mm; - } tlb_gather_mmu(&tlb, mm, 0, -1); if (type == CLEAR_REFS_SOFT_DIRTY) { for (vma = mm->mmap; vma; vma = vma->vm_next) { if (!(vma->vm_flags & VM_SOFTDIRTY)) continue; - mmap_read_unlock(mm); - if (mmap_write_lock_killable(mm)) { - count = -EINTR; - goto out_mm; - } - for (vma = mm->mmap; vma; vma = vma->vm_next) { - vma->vm_flags &= ~VM_SOFTDIRTY; - vma_set_page_prot(vma); - } - mmap_write_downgrade(mm); - break; + vma->vm_flags &= ~VM_SOFTDIRTY; + vma_set_page_prot(vma); } mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY, @@ -1261,7 +1267,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, if (type == CLEAR_REFS_SOFT_DIRTY) mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, 0, -1); - mmap_read_unlock(mm); +out_unlock: + mmap_write_unlock(mm); out_mm: mmput(mm); } diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index e59d4bb3a89e..eafb75755fa3 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -320,7 +320,8 @@ static int mountstats_open(struct inode *inode, struct file *file) const struct file_operations proc_mounts_operations = { .open = mounts_open, - .read = seq_read, + .read_iter = seq_read_iter, + .splice_read = generic_file_splice_read, .llseek = seq_lseek, .release = mounts_release, .poll = mounts_poll, @@ -328,7 +329,8 @@ const struct file_operations proc_mounts_operations = { const struct file_operations proc_mountinfo_operations = { .open = mountinfo_open, - .read = seq_read, + .read_iter = seq_read_iter, + .splice_read = generic_file_splice_read, .llseek = seq_lseek, .release = mounts_release, .poll = mounts_poll, @@ -336,7 +338,8 @@ const struct file_operations proc_mountinfo_operations = { const struct file_operations proc_mountstats_operations = { .open = mountstats_open, - .read = seq_read, + .read_iter = seq_read_iter, + .splice_read = generic_file_splice_read, .llseek = seq_lseek, .release = mounts_release, }; diff --git a/fs/read_write.c b/fs/read_write.c index 75f764b43418..9db7adf160d2 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1188,6 +1188,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, { struct fd in, out; struct inode *in_inode, *out_inode; + struct pipe_inode_info *opipe; loff_t pos; loff_t out_pos; ssize_t retval; @@ -1228,9 +1229,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, in_inode = file_inode(in.file); out_inode = file_inode(out.file); out_pos = out.file->f_pos; - retval = rw_verify_area(WRITE, out.file, &out_pos, count); - if (retval < 0) - goto fput_out; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); @@ -1253,9 +1251,18 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (in.file->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif - file_start_write(out.file); - retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); - file_end_write(out.file); + opipe = get_pipe_info(out.file, true); + if (!opipe) { + retval = rw_verify_area(WRITE, out.file, &out_pos, count); + if (retval < 0) + goto fput_out; + file_start_write(out.file); + retval = do_splice_direct(in.file, &pos, out.file, &out_pos, + count, fl); + file_end_write(out.file); + } else { + retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl); + } if (retval > 0) { add_rchar(current, retval); diff --git a/fs/select.c b/fs/select.c index ebfebdfe5c69..37aaa8317f3a 100644 --- a/fs/select.c +++ b/fs/select.c @@ -1011,14 +1011,17 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, fdcount = do_poll(head, &table, end_time); poll_freewait(&table); + if (!user_write_access_begin(ufds, nfds * sizeof(*ufds))) + goto out_fds; + for (walk = head; walk; walk = walk->next) { struct pollfd *fds = walk->entries; int j; - for (j = 0; j < walk->len; j++, ufds++) - if (__put_user(fds[j].revents, &ufds->revents)) - goto out_fds; + for (j = walk->len; j; fds++, ufds++, j--) + unsafe_put_user(fds->revents, &ufds->revents, Efault); } + user_write_access_end(); err = fdcount; out_fds: @@ -1030,6 +1033,11 @@ out_fds: } return err; + +Efault: + user_write_access_end(); + err = -EFAULT; + goto out_fds; } static long do_restart_poll(struct restart_block *restart_block) diff --git a/fs/splice.c b/fs/splice.c index 866d5c2367b2..b06846f1e6ee 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -771,11 +771,16 @@ static long do_splice_to(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { + unsigned int p_space; int ret; if (unlikely(!(in->f_mode & FMODE_READ))) return -EBADF; + /* Don't try to read more the pipe has space for. */ + p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail); + len = min_t(size_t, len, p_space << PAGE_SHIFT); + ret = rw_verify_area(READ, in, ppos, len); if (unlikely(ret < 0)) return ret; @@ -856,15 +861,10 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail)); while (len) { - unsigned int p_space; size_t read_len; loff_t pos = sd->pos, prev_pos = pos; - /* Don't try to read more the pipe has space for. */ - p_space = pipe->max_usage - - pipe_occupancy(pipe->head, pipe->tail); - read_len = min_t(size_t, len, p_space << PAGE_SHIFT); - ret = do_splice_to(in, &pos, pipe, read_len, flags); + ret = do_splice_to(in, &pos, pipe, len, flags); if (unlikely(ret <= 0)) goto out_release; @@ -1002,6 +1002,23 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags); +long splice_file_to_pipe(struct file *in, + struct pipe_inode_info *opipe, + loff_t *offset, + size_t len, unsigned int flags) +{ + long ret; + + pipe_lock(opipe); + ret = wait_for_space(opipe, flags); + if (!ret) + ret = do_splice_to(in, offset, opipe, len, flags); + pipe_unlock(opipe); + if (ret > 0) + wakeup_pipe_readers(opipe); + return ret; +} + /* * Determine where to splice to/from. */ @@ -1081,20 +1098,7 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out, if (out->f_flags & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; - pipe_lock(opipe); - ret = wait_for_space(opipe, flags); - if (!ret) { - unsigned int p_space; - - /* Don't try to read more the pipe has space for. */ - p_space = opipe->max_usage - pipe_occupancy(opipe->head, opipe->tail); - len = min_t(size_t, len, p_space << PAGE_SHIFT); - - ret = do_splice_to(in, &offset, opipe, len, flags); - } - pipe_unlock(opipe); - if (ret > 0) - wakeup_pipe_readers(opipe); + ret = splice_file_to_pipe(in, opipe, &offset, len, flags); if (!off_in) in->f_pos = offset; else diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 8a19773b5a0b..45f44425d856 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -196,9 +196,15 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, length = SQUASHFS_COMPRESSED_SIZE(length); index += 2; - TRACE("Block @ 0x%llx, %scompressed size %d\n", index, + TRACE("Block @ 0x%llx, %scompressed size %d\n", index - 2, compressed ? "" : "un", length); } + if (length < 0 || length > output->length || + (index + length) > msblk->bytes_used) { + res = -EIO; + goto out; + } + if (next_index) *next_index = index + length; diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c index ae2c87bb0fbe..eb02072d28dd 100644 --- a/fs/squashfs/export.c +++ b/fs/squashfs/export.c @@ -41,12 +41,17 @@ static long long squashfs_inode_lookup(struct super_block *sb, int ino_num) struct squashfs_sb_info *msblk = sb->s_fs_info; int blk = SQUASHFS_LOOKUP_BLOCK(ino_num - 1); int offset = SQUASHFS_LOOKUP_BLOCK_OFFSET(ino_num - 1); - u64 start = le64_to_cpu(msblk->inode_lookup_table[blk]); + u64 start; __le64 ino; int err; TRACE("Entered squashfs_inode_lookup, inode_number = %d\n", ino_num); + if (ino_num == 0 || (ino_num - 1) >= msblk->inodes) + return -EINVAL; + + start = le64_to_cpu(msblk->inode_lookup_table[blk]); + err = squashfs_read_metadata(sb, &ino, &start, &offset, sizeof(ino)); if (err < 0) return err; @@ -111,7 +116,10 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb, u64 lookup_table_start, u64 next_table, unsigned int inodes) { unsigned int length = SQUASHFS_LOOKUP_BLOCK_BYTES(inodes); + unsigned int indexes = SQUASHFS_LOOKUP_BLOCKS(inodes); + int n; __le64 *table; + u64 start, end; TRACE("In read_inode_lookup_table, length %d\n", length); @@ -121,20 +129,37 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb, if (inodes == 0) return ERR_PTR(-EINVAL); - /* length bytes should not extend into the next table - this check - * also traps instances where lookup_table_start is incorrectly larger - * than the next table start + /* + * The computed size of the lookup table (length bytes) should exactly + * match the table start and end points */ - if (lookup_table_start + length > next_table) + if (length != (next_table - lookup_table_start)) return ERR_PTR(-EINVAL); table = squashfs_read_table(sb, lookup_table_start, length); + if (IS_ERR(table)) + return table; /* - * table[0] points to the first inode lookup table metadata block, - * this should be less than lookup_table_start + * table0], table[1], ... table[indexes - 1] store the locations + * of the compressed inode lookup blocks. Each entry should be + * less than the next (i.e. table[0] < table[1]), and the difference + * between them should be SQUASHFS_METADATA_SIZE or less. + * table[indexes - 1] should be less than lookup_table_start, and + * again the difference should be SQUASHFS_METADATA_SIZE or less */ - if (!IS_ERR(table) && le64_to_cpu(table[0]) >= lookup_table_start) { + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= lookup_table_start || (lookup_table_start - start) > SQUASHFS_METADATA_SIZE) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c index 6be5afe7287d..11581bf31af4 100644 --- a/fs/squashfs/id.c +++ b/fs/squashfs/id.c @@ -35,10 +35,15 @@ int squashfs_get_id(struct super_block *sb, unsigned int index, struct squashfs_sb_info *msblk = sb->s_fs_info; int block = SQUASHFS_ID_BLOCK(index); int offset = SQUASHFS_ID_BLOCK_OFFSET(index); - u64 start_block = le64_to_cpu(msblk->id_table[block]); + u64 start_block; __le32 disk_id; int err; + if (index >= msblk->ids) + return -EINVAL; + + start_block = le64_to_cpu(msblk->id_table[block]); + err = squashfs_read_metadata(sb, &disk_id, &start_block, &offset, sizeof(disk_id)); if (err < 0) @@ -56,7 +61,10 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb, u64 id_table_start, u64 next_table, unsigned short no_ids) { unsigned int length = SQUASHFS_ID_BLOCK_BYTES(no_ids); + unsigned int indexes = SQUASHFS_ID_BLOCKS(no_ids); + int n; __le64 *table; + u64 start, end; TRACE("In read_id_index_table, length %d\n", length); @@ -67,20 +75,36 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb, return ERR_PTR(-EINVAL); /* - * length bytes should not extend into the next table - this check - * also traps instances where id_table_start is incorrectly larger - * than the next table start + * The computed size of the index table (length bytes) should exactly + * match the table start and end points */ - if (id_table_start + length > next_table) + if (length != (next_table - id_table_start)) return ERR_PTR(-EINVAL); table = squashfs_read_table(sb, id_table_start, length); + if (IS_ERR(table)) + return table; /* - * table[0] points to the first id lookup table metadata block, this - * should be less than id_table_start + * table[0], table[1], ... table[indexes - 1] store the locations + * of the compressed id blocks. Each entry should be less than + * the next (i.e. table[0] < table[1]), and the difference between them + * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] + * should be less than id_table_start, and again the difference + * should be SQUASHFS_METADATA_SIZE or less */ - if (!IS_ERR(table) && le64_to_cpu(table[0]) >= id_table_start) { + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 34c21ffb6df3..166e98806265 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -64,5 +64,6 @@ struct squashfs_sb_info { unsigned int inodes; unsigned int fragments; int xattr_ids; + unsigned int ids; }; #endif diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index d6c6593ec169..88cc94be1076 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -166,6 +166,7 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) msblk->directory_table = le64_to_cpu(sblk->directory_table_start); msblk->inodes = le32_to_cpu(sblk->inodes); msblk->fragments = le32_to_cpu(sblk->fragments); + msblk->ids = le16_to_cpu(sblk->no_ids); flags = le16_to_cpu(sblk->flags); TRACE("Found valid superblock on %pg\n", sb->s_bdev); @@ -177,7 +178,7 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) TRACE("Block size %d\n", msblk->block_size); TRACE("Number of inodes %d\n", msblk->inodes); TRACE("Number of fragments %d\n", msblk->fragments); - TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids)); + TRACE("Number of ids %d\n", msblk->ids); TRACE("sblk->inode_table_start %llx\n", msblk->inode_table); TRACE("sblk->directory_table_start %llx\n", msblk->directory_table); TRACE("sblk->fragment_table_start %llx\n", @@ -236,8 +237,7 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) allocate_id_index_table: /* Allocate and read id index table */ msblk->id_table = squashfs_read_id_index_table(sb, - le64_to_cpu(sblk->id_table_start), next_table, - le16_to_cpu(sblk->no_ids)); + le64_to_cpu(sblk->id_table_start), next_table, msblk->ids); if (IS_ERR(msblk->id_table)) { errorf(fc, "unable to read id index table"); err = PTR_ERR(msblk->id_table); diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h index 184129afd456..d8a270d3ac4c 100644 --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -17,8 +17,16 @@ extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, u64 *xattr_table_start, int *xattr_ids) { + struct squashfs_xattr_id_table *id_table; + + id_table = squashfs_read_table(sb, start, sizeof(*id_table)); + if (IS_ERR(id_table)) + return (__le64 *) id_table; + + *xattr_table_start = le64_to_cpu(id_table->xattr_table_start); + kfree(id_table); + ERROR("Xattrs in filesystem, these will be ignored\n"); - *xattr_table_start = start; return ERR_PTR(-ENOTSUPP); } diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index d99e08464554..ead66670b41a 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -31,10 +31,15 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, struct squashfs_sb_info *msblk = sb->s_fs_info; int block = SQUASHFS_XATTR_BLOCK(index); int offset = SQUASHFS_XATTR_BLOCK_OFFSET(index); - u64 start_block = le64_to_cpu(msblk->xattr_id_table[block]); + u64 start_block; struct squashfs_xattr_id id; int err; + if (index >= msblk->xattr_ids) + return -EINVAL; + + start_block = le64_to_cpu(msblk->xattr_id_table[block]); + err = squashfs_read_metadata(sb, &id, &start_block, &offset, sizeof(id)); if (err < 0) @@ -50,13 +55,17 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, /* * Read uncompressed xattr id lookup table indexes from disk into memory */ -__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, +__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, u64 *xattr_table_start, int *xattr_ids) { - unsigned int len; + struct squashfs_sb_info *msblk = sb->s_fs_info; + unsigned int len, indexes; struct squashfs_xattr_id_table *id_table; + __le64 *table; + u64 start, end; + int n; - id_table = squashfs_read_table(sb, start, sizeof(*id_table)); + id_table = squashfs_read_table(sb, table_start, sizeof(*id_table)); if (IS_ERR(id_table)) return (__le64 *) id_table; @@ -70,13 +79,52 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, if (*xattr_ids == 0) return ERR_PTR(-EINVAL); - /* xattr_table should be less than start */ - if (*xattr_table_start >= start) + len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); + indexes = SQUASHFS_XATTR_BLOCKS(*xattr_ids); + + /* + * The computed size of the index table (len bytes) should exactly + * match the table start and end points + */ + start = table_start + sizeof(*id_table); + end = msblk->bytes_used; + + if (len != (end - start)) return ERR_PTR(-EINVAL); - len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); + table = squashfs_read_table(sb, start, len); + if (IS_ERR(table)) + return table; + + /* table[0], table[1], ... table[indexes - 1] store the locations + * of the compressed xattr id blocks. Each entry should be less than + * the next (i.e. table[0] < table[1]), and the difference between them + * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] + * should be less than table_start, and again the difference + * shouls be SQUASHFS_METADATA_SIZE or less. + * + * Finally xattr_table_start should be less than table[0]. + */ + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) { + kfree(table); + return ERR_PTR(-EINVAL); + } - TRACE("In read_xattr_index_table, length %d\n", len); + if (*xattr_table_start >= le64_to_cpu(table[0])) { + kfree(table); + return ERR_PTR(-EINVAL); + } - return squashfs_read_table(sb, start + sizeof(*id_table), len); + return table; } diff --git a/fs/udf/super.c b/fs/udf/super.c index 5bef3a68395d..d0df217f4712 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -705,6 +705,7 @@ static int udf_check_vsd(struct super_block *sb) struct buffer_head *bh = NULL; int nsr = 0; struct udf_sb_info *sbi; + loff_t session_offset; sbi = UDF_SB(sb); if (sb->s_blocksize < sizeof(struct volStructDesc)) @@ -712,7 +713,8 @@ static int udf_check_vsd(struct super_block *sb) else sectorsize = sb->s_blocksize; - sector += (((loff_t)sbi->s_session) << sb->s_blocksize_bits); + session_offset = (loff_t)sbi->s_session << sb->s_blocksize_bits; + sector += session_offset; udf_debug("Starting at sector %u (%lu byte sectors)\n", (unsigned int)(sector >> sb->s_blocksize_bits), @@ -757,8 +759,7 @@ static int udf_check_vsd(struct super_block *sb) if (nsr > 0) return 1; - else if (!bh && sector - (sbi->s_session << sb->s_blocksize_bits) == - VSD_FIRST_SECTOR_OFFSET) + else if (!bh && sector - session_offset == VSD_FIRST_SECTOR_OFFSET) return -1; else return 0; diff --git a/fs/zonefs/Kconfig b/fs/zonefs/Kconfig index ef2697b78820..827278f937fe 100644 --- a/fs/zonefs/Kconfig +++ b/fs/zonefs/Kconfig @@ -3,6 +3,7 @@ config ZONEFS_FS depends on BLOCK depends on BLK_DEV_ZONED select FS_IOMAP + select CRC32 help zonefs is a simple file system which exposes zones of a zoned block device (e.g. host-managed or host-aware SMR disk drives) as files. |