diff options
Diffstat (limited to 'fs')
43 files changed, 1408 insertions, 588 deletions
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index 5a0db6dec8d1..aaee1e6584e6 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -40,6 +40,9 @@ */ #define P9_LOCK_TIMEOUT (30*HZ) +/* flags for v9fs_stat2inode() & v9fs_stat2inode_dotl() */ +#define V9FS_STAT2INODE_KEEP_ISIZE 1 + extern struct file_system_type v9fs_fs_type; extern const struct address_space_operations v9fs_addr_operations; extern const struct file_operations v9fs_file_operations; @@ -61,8 +64,10 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t); void v9fs_evict_inode(struct inode *inode); ino_t v9fs_qid2ino(struct p9_qid *qid); -void v9fs_stat2inode(struct p9_wstat *, struct inode *, struct super_block *); -void v9fs_stat2inode_dotl(struct p9_stat_dotl *, struct inode *); +void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, + struct super_block *sb, unsigned int flags); +void v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, + unsigned int flags); int v9fs_dir_release(struct inode *inode, struct file *filp); int v9fs_file_open(struct inode *inode, struct file *file); void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat); @@ -83,4 +88,18 @@ static inline void v9fs_invalidate_inode_attr(struct inode *inode) } int v9fs_open_to_dotl_flags(int flags); + +static inline void v9fs_i_size_write(struct inode *inode, loff_t i_size) +{ + /* + * 32-bit need the lock, concurrent updates could break the + * sequences and make i_size_read() loop forever. + * 64-bit updates are atomic and can skip the locking. + */ + if (sizeof(i_size) > sizeof(long)) + spin_lock(&inode->i_lock); + i_size_write(inode, i_size); + if (sizeof(i_size) > sizeof(long)) + spin_unlock(&inode->i_lock); +} #endif diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index a25efa782fcc..9a1125305d84 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -446,7 +446,11 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) i_size = i_size_read(inode); if (iocb->ki_pos > i_size) { inode_add_bytes(inode, iocb->ki_pos - i_size); - i_size_write(inode, iocb->ki_pos); + /* + * Need to serialize against i_size_write() in + * v9fs_stat2inode() + */ + v9fs_i_size_write(inode, iocb->ki_pos); } return retval; } diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 85ff859d3af5..72b779bc0942 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -538,7 +538,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb, if (retval) goto error; - v9fs_stat2inode(st, inode, sb); + v9fs_stat2inode(st, inode, sb, 0); v9fs_cache_inode_get_cookie(inode); unlock_new_inode(inode); return inode; @@ -1092,7 +1092,7 @@ v9fs_vfs_getattr(const struct path *path, struct kstat *stat, if (IS_ERR(st)) return PTR_ERR(st); - v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb); + v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb, 0); generic_fillattr(d_inode(dentry), stat); p9stat_free(st); @@ -1170,12 +1170,13 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) * @stat: Plan 9 metadata (mistat) structure * @inode: inode to populate * @sb: superblock of filesystem + * @flags: control flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE) * */ void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, - struct super_block *sb) + struct super_block *sb, unsigned int flags) { umode_t mode; char ext[32]; @@ -1216,10 +1217,11 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, mode = p9mode2perm(v9ses, stat); mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; - i_size_write(inode, stat->length); + if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) + v9fs_i_size_write(inode, stat->length); /* not real number of blocks, but 512 byte ones ... */ - inode->i_blocks = (i_size_read(inode) + 512 - 1) >> 9; + inode->i_blocks = (stat->length + 512 - 1) >> 9; v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR; } @@ -1416,9 +1418,9 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) { int umode; dev_t rdev; - loff_t i_size; struct p9_wstat *st; struct v9fs_session_info *v9ses; + unsigned int flags; v9ses = v9fs_inode2v9ses(inode); st = p9_client_stat(fid); @@ -1431,16 +1433,13 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) if ((inode->i_mode & S_IFMT) != (umode & S_IFMT)) goto out; - spin_lock(&inode->i_lock); /* * We don't want to refresh inode->i_size, * because we may have cached data */ - i_size = inode->i_size; - v9fs_stat2inode(st, inode, inode->i_sb); - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) - inode->i_size = i_size; - spin_unlock(&inode->i_lock); + flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ? + V9FS_STAT2INODE_KEEP_ISIZE : 0; + v9fs_stat2inode(st, inode, inode->i_sb, flags); out: p9stat_free(st); kfree(st); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 4823e1c46999..a950a927a626 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -143,7 +143,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb, if (retval) goto error; - v9fs_stat2inode_dotl(st, inode); + v9fs_stat2inode_dotl(st, inode, 0); v9fs_cache_inode_get_cookie(inode); retval = v9fs_get_acl(inode, fid); if (retval) @@ -496,7 +496,7 @@ v9fs_vfs_getattr_dotl(const struct path *path, struct kstat *stat, if (IS_ERR(st)) return PTR_ERR(st); - v9fs_stat2inode_dotl(st, d_inode(dentry)); + v9fs_stat2inode_dotl(st, d_inode(dentry), 0); generic_fillattr(d_inode(dentry), stat); /* Change block size to what the server returned */ stat->blksize = st->st_blksize; @@ -607,11 +607,13 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) * v9fs_stat2inode_dotl - populate an inode structure with stat info * @stat: stat structure * @inode: inode to populate + * @flags: ctrl flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE) * */ void -v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode) +v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, + unsigned int flags) { umode_t mode; struct v9fs_inode *v9inode = V9FS_I(inode); @@ -631,7 +633,8 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode) mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; - i_size_write(inode, stat->st_size); + if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) + v9fs_i_size_write(inode, stat->st_size); inode->i_blocks = stat->st_blocks; } else { if (stat->st_result_mask & P9_STATS_ATIME) { @@ -661,8 +664,9 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode) } if (stat->st_result_mask & P9_STATS_RDEV) inode->i_rdev = new_decode_dev(stat->st_rdev); - if (stat->st_result_mask & P9_STATS_SIZE) - i_size_write(inode, stat->st_size); + if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) && + stat->st_result_mask & P9_STATS_SIZE) + v9fs_i_size_write(inode, stat->st_size); if (stat->st_result_mask & P9_STATS_BLOCKS) inode->i_blocks = stat->st_blocks; } @@ -928,9 +932,9 @@ v9fs_vfs_get_link_dotl(struct dentry *dentry, int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) { - loff_t i_size; struct p9_stat_dotl *st; struct v9fs_session_info *v9ses; + unsigned int flags; v9ses = v9fs_inode2v9ses(inode); st = p9_client_getattr_dotl(fid, P9_STATS_ALL); @@ -942,16 +946,13 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) if ((inode->i_mode & S_IFMT) != (st->st_mode & S_IFMT)) goto out; - spin_lock(&inode->i_lock); /* * We don't want to refresh inode->i_size, * because we may have cached data */ - i_size = inode->i_size; - v9fs_stat2inode_dotl(st, inode); - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) - inode->i_size = i_size; - spin_unlock(&inode->i_lock); + flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ? + V9FS_STAT2INODE_KEEP_ISIZE : 0; + v9fs_stat2inode_dotl(st, inode, flags); out: kfree(st); return 0; diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 10d3bd3f534b..d13d35cf69c0 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -172,7 +172,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, goto release_sb; } d_inode(root)->i_ino = v9fs_qid2ino(&st->qid); - v9fs_stat2inode_dotl(st, d_inode(root)); + v9fs_stat2inode_dotl(st, d_inode(root), 0); kfree(st); } else { struct p9_wstat *st = NULL; @@ -183,7 +183,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, } d_inode(root)->i_ino = v9fs_qid2ino(&st->qid); - v9fs_stat2inode(st, d_inode(root), sb); + v9fs_stat2inode(st, d_inode(root), sb, 0); p9stat_free(st); kfree(st); diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index e92a2fee3c57..13c1288b04a7 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -115,7 +115,12 @@ static void cifs_debug_tcon(struct seq_file *m, struct cifs_tcon *tcon) seq_puts(m, " type: CDROM "); else seq_printf(m, " type: %d ", dev_type); - if (tcon->seal) + + seq_printf(m, "Serial Number: 0x%x", tcon->vol_serial_number); + + if ((tcon->seal) || + (tcon->ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) || + (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA)) seq_printf(m, " Encrypted"); if (tcon->nocase) seq_printf(m, " nocase"); @@ -371,6 +376,10 @@ skip_rdma: atomic_read(&server->in_send), atomic_read(&server->num_waiters)); #endif + if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) + seq_puts(m, " encrypted"); + if (ses->sign) + seq_puts(m, " signed"); seq_puts(m, "\n\tShares:"); j = 0; diff --git a/fs/cifs/cifs_ioctl.h b/fs/cifs/cifs_ioctl.h index d8bce2f862de..086ddc5108af 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/cifs/cifs_ioctl.h @@ -43,6 +43,9 @@ struct smb_snapshot_array { /* snapshots[]; */ } __packed; +/* query_info flags */ +#define PASSTHRU_QUERY_INFO 0x00000000 +#define PASSTHRU_FSCTL 0x00000001 struct smb_query_info { __u32 info_type; __u32 file_info_class; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index f293e052e351..38feae812b47 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -479,6 +479,14 @@ struct smb_version_operations { struct cifs_tcon *tcon, __le16 *path, int is_dir, unsigned long p); + /* make unix special files (block, char, fifo, socket) */ + int (*make_node)(unsigned int xid, + struct inode *inode, + struct dentry *dentry, + struct cifs_tcon *tcon, + char *full_path, + umode_t mode, + dev_t device_number); }; struct smb_version_values { @@ -735,13 +743,13 @@ in_flight(struct TCP_Server_Info *server) } static inline bool -has_credits(struct TCP_Server_Info *server, int *credits) +has_credits(struct TCP_Server_Info *server, int *credits, int num_credits) { int num; spin_lock(&server->req_lock); num = *credits; spin_unlock(&server->req_lock); - return num > 0; + return num >= num_credits; } static inline void @@ -962,11 +970,14 @@ cap_unix(struct cifs_ses *ses) struct cached_fid { bool is_valid:1; /* Do we have a useable root fid */ + bool file_all_info_is_valid:1; + struct kref refcount; struct cifs_fid *fid; struct mutex fid_mutex; struct cifs_tcon *tcon; struct work_struct lease_break; + struct smb2_file_all_info file_all_info; }; /* @@ -1735,6 +1746,7 @@ require use of the stronger protocol */ * GlobalMid_Lock protects: * list operations on pending_mid_q and oplockQ * updates to XID counters, multiplex id and SMB sequence numbers + * list operations on global DnotifyReqList * tcp_ses_lock protects: * list operations on tcp and SMB session lists * tcon->open_file_lock protects the list of open files hanging off the tcon diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index b95db2b593cb..a8e9738db691 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1191,10 +1191,6 @@ next_pdu: continue; } - if (server->large_buf) - buf = server->bigbuf; - - server->lstrp = jiffies; for (i = 0; i < num_mids; i++) { diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 907e85d65bb4..f26a48dd2e39 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -621,20 +621,10 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode, { int rc = -EPERM; unsigned int xid; - int create_options = CREATE_NOT_DIR | CREATE_OPTION_SPECIAL; struct cifs_sb_info *cifs_sb; struct tcon_link *tlink; struct cifs_tcon *tcon; - struct cifs_io_parms io_parms; char *full_path = NULL; - struct inode *newinode = NULL; - __u32 oplock = 0; - struct cifs_fid fid; - struct cifs_open_parms oparms; - FILE_ALL_INFO *buf = NULL; - unsigned int bytes_written; - struct win_dev *pdev; - struct kvec iov[2]; if (!old_valid_dev(device_number)) return -EINVAL; @@ -654,103 +644,12 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode, goto mknod_out; } - if (tcon->unix_ext) { - struct cifs_unix_set_info_args args = { - .mode = mode & ~current_umask(), - .ctime = NO_CHANGE_64, - .atime = NO_CHANGE_64, - .mtime = NO_CHANGE_64, - .device = device_number, - }; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { - args.uid = current_fsuid(); - args.gid = current_fsgid(); - } else { - args.uid = INVALID_UID; /* no change */ - args.gid = INVALID_GID; /* no change */ - } - rc = CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args, - cifs_sb->local_nls, - cifs_remap(cifs_sb)); - if (rc) - goto mknod_out; - - rc = cifs_get_inode_info_unix(&newinode, full_path, - inode->i_sb, xid); - - if (rc == 0) - d_instantiate(direntry, newinode); - goto mknod_out; - } - - if (!S_ISCHR(mode) && !S_ISBLK(mode)) - goto mknod_out; - - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) - goto mknod_out; - - - cifs_dbg(FYI, "sfu compat create special file\n"); - - buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); - if (buf == NULL) { - rc = -ENOMEM; - goto mknod_out; - } - - if (backup_cred(cifs_sb)) - create_options |= CREATE_OPEN_BACKUP_INTENT; - - oparms.tcon = tcon; - oparms.cifs_sb = cifs_sb; - oparms.desired_access = GENERIC_WRITE; - oparms.create_options = create_options; - oparms.disposition = FILE_CREATE; - oparms.path = full_path; - oparms.fid = &fid; - oparms.reconnect = false; - - if (tcon->ses->server->oplocks) - oplock = REQ_OPLOCK; - else - oplock = 0; - rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, buf); - if (rc) - goto mknod_out; - - /* - * BB Do not bother to decode buf since no local inode yet to put - * timestamps in, but we can reuse it safely. - */ - - pdev = (struct win_dev *)buf; - io_parms.pid = current->tgid; - io_parms.tcon = tcon; - io_parms.offset = 0; - io_parms.length = sizeof(struct win_dev); - iov[1].iov_base = buf; - iov[1].iov_len = sizeof(struct win_dev); - if (S_ISCHR(mode)) { - memcpy(pdev->type, "IntxCHR", 8); - pdev->major = cpu_to_le64(MAJOR(device_number)); - pdev->minor = cpu_to_le64(MINOR(device_number)); - rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms, - &bytes_written, iov, 1); - } else if (S_ISBLK(mode)) { - memcpy(pdev->type, "IntxBLK", 8); - pdev->major = cpu_to_le64(MAJOR(device_number)); - pdev->minor = cpu_to_le64(MINOR(device_number)); - rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms, - &bytes_written, iov, 1); - } - tcon->ses->server->ops->close(xid, tcon, &fid); - d_drop(direntry); - - /* FIXME: add code here to set EAs */ + rc = tcon->ses->server->ops->make_node(xid, inode, direntry, tcon, + full_path, mode, + device_number); mknod_out: kfree(full_path); - kfree(buf); free_xid(xid); cifs_put_tlink(tlink); return rc; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 4c144c1f50eb..2a6d20c0ce02 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1645,8 +1645,20 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, rc = server->ops->mand_unlock_range(cfile, flock, xid); out: - if (flock->fl_flags & FL_POSIX && !rc) + if (flock->fl_flags & FL_POSIX) { + /* + * If this is a request to remove all locks because we + * are closing the file, it doesn't matter if the + * unlocking failed as both cifs.ko and the SMB server + * remove the lock on file close + */ + if (rc) { + cifs_dbg(VFS, "%s failed rc=%d\n", __func__, rc); + if (!(flock->fl_flags & FL_CLOSE)) + return rc; + } rc = locks_lock_file_wait(file, flock); + } return rc; } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index f0ce27c3c6e4..c711f1f39bf2 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -1027,6 +1027,131 @@ cifs_can_echo(struct TCP_Server_Info *server) return false; } +static int +cifs_make_node(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + char *full_path, umode_t mode, dev_t dev) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct inode *newinode = NULL; + int rc = -EPERM; + int create_options = CREATE_NOT_DIR | CREATE_OPTION_SPECIAL; + FILE_ALL_INFO *buf = NULL; + struct cifs_io_parms io_parms; + __u32 oplock = 0; + struct cifs_fid fid; + struct cifs_open_parms oparms; + unsigned int bytes_written; + struct win_dev *pdev; + struct kvec iov[2]; + + if (tcon->unix_ext) { + /* + * SMB1 Unix Extensions: requires server support but + * works with all special files + */ + struct cifs_unix_set_info_args args = { + .mode = mode & ~current_umask(), + .ctime = NO_CHANGE_64, + .atime = NO_CHANGE_64, + .mtime = NO_CHANGE_64, + .device = dev, + }; + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { + args.uid = current_fsuid(); + args.gid = current_fsgid(); + } else { + args.uid = INVALID_UID; /* no change */ + args.gid = INVALID_GID; /* no change */ + } + rc = CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args, + cifs_sb->local_nls, + cifs_remap(cifs_sb)); + if (rc) + goto out; + + rc = cifs_get_inode_info_unix(&newinode, full_path, + inode->i_sb, xid); + + if (rc == 0) + d_instantiate(dentry, newinode); + goto out; + } + + /* + * SMB1 SFU emulation: should work with all servers, but only + * support block and char device (no socket & fifo) + */ + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) + goto out; + + if (!S_ISCHR(mode) && !S_ISBLK(mode)) + goto out; + + cifs_dbg(FYI, "sfu compat create special file\n"); + + buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); + if (buf == NULL) { + rc = -ENOMEM; + goto out; + } + + if (backup_cred(cifs_sb)) + create_options |= CREATE_OPEN_BACKUP_INTENT; + + oparms.tcon = tcon; + oparms.cifs_sb = cifs_sb; + oparms.desired_access = GENERIC_WRITE; + oparms.create_options = create_options; + oparms.disposition = FILE_CREATE; + oparms.path = full_path; + oparms.fid = &fid; + oparms.reconnect = false; + + if (tcon->ses->server->oplocks) + oplock = REQ_OPLOCK; + else + oplock = 0; + rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, buf); + if (rc) + goto out; + + /* + * BB Do not bother to decode buf since no local inode yet to put + * timestamps in, but we can reuse it safely. + */ + + pdev = (struct win_dev *)buf; + io_parms.pid = current->tgid; + io_parms.tcon = tcon; + io_parms.offset = 0; + io_parms.length = sizeof(struct win_dev); + iov[1].iov_base = buf; + iov[1].iov_len = sizeof(struct win_dev); + if (S_ISCHR(mode)) { + memcpy(pdev->type, "IntxCHR", 8); + pdev->major = cpu_to_le64(MAJOR(dev)); + pdev->minor = cpu_to_le64(MINOR(dev)); + rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms, + &bytes_written, iov, 1); + } else if (S_ISBLK(mode)) { + memcpy(pdev->type, "IntxBLK", 8); + pdev->major = cpu_to_le64(MAJOR(dev)); + pdev->minor = cpu_to_le64(MINOR(dev)); + rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms, + &bytes_written, iov, 1); + } + tcon->ses->server->ops->close(xid, tcon, &fid); + d_drop(dentry); + + /* FIXME: add code here to set EAs */ +out: + kfree(buf); + return rc; +} + + + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -1110,6 +1235,7 @@ struct smb_version_operations smb1_operations = { .get_acl_by_fid = get_cifs_acl_by_fid, .set_acl = set_cifs_acl, #endif /* CIFS_ACL */ + .make_node = cifs_make_node, }; struct smb_version_values smb1_values = { diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 01a76bccdb8d..278405d26c47 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -37,6 +37,16 @@ #include "smb2pdu.h" #include "smb2proto.h" +static void +free_set_inf_compound(struct smb_rqst *rqst) +{ + if (rqst[1].rq_iov) + SMB2_set_info_free(&rqst[1]); + if (rqst[2].rq_iov) + SMB2_close_free(&rqst[2]); +} + + static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, @@ -112,14 +122,18 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, PATH_MAX * 2, 0, NULL); smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); + trace_smb3_query_info_compound_enter(xid, ses->Suid, tcon->tid, + full_path); break; case SMB2_OP_DELETE: + trace_smb3_delete_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_MKDIR: /* * Directories are created through parameters in the * SMB2_open() call. */ + trace_smb3_mkdir_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_RMDIR: memset(&si_iov, 0, sizeof(si_iov)); @@ -135,6 +149,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, SMB2_O_INFO_FILE, 0, data, size); smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); + trace_smb3_rmdir_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_SET_EOF: memset(&si_iov, 0, sizeof(si_iov)); @@ -150,6 +165,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, SMB2_O_INFO_FILE, 0, data, size); smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); + trace_smb3_set_eof_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_SET_INFO: memset(&si_iov, 0, sizeof(si_iov)); @@ -166,6 +182,8 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, SMB2_O_INFO_FILE, 0, data, size); smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); + trace_smb3_set_info_compound_enter(xid, ses->Suid, tcon->tid, + full_path); break; case SMB2_OP_RENAME: memset(&si_iov, 0, sizeof(si_iov)); @@ -190,6 +208,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, SMB2_O_INFO_FILE, 0, data, size); smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); + trace_smb3_rename_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_HARDLINK: memset(&si_iov, 0, sizeof(si_iov)); @@ -214,6 +233,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, SMB2_O_INFO_FILE, 0, data, size); smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); + trace_smb3_hardlink_enter(xid, ses->Suid, tcon->tid, full_path); break; default: cifs_dbg(VFS, "Invalid command\n"); @@ -252,21 +272,65 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, SMB2_query_info_free(&rqst[1]); if (rqst[2].rq_iov) SMB2_close_free(&rqst[2]); + if (rc) + trace_smb3_query_info_compound_err(xid, ses->Suid, + tcon->tid, rc); + else + trace_smb3_query_info_compound_done(xid, ses->Suid, + tcon->tid); break; case SMB2_OP_DELETE: + if (rc) + trace_smb3_delete_err(xid, ses->Suid, tcon->tid, rc); + else + trace_smb3_delete_done(xid, ses->Suid, tcon->tid); + if (rqst[1].rq_iov) + SMB2_close_free(&rqst[1]); + break; case SMB2_OP_MKDIR: + if (rc) + trace_smb3_mkdir_err(xid, ses->Suid, tcon->tid, rc); + else + trace_smb3_mkdir_done(xid, ses->Suid, tcon->tid); if (rqst[1].rq_iov) SMB2_close_free(&rqst[1]); break; case SMB2_OP_HARDLINK: + if (rc) + trace_smb3_hardlink_err(xid, ses->Suid, tcon->tid, rc); + else + trace_smb3_hardlink_done(xid, ses->Suid, tcon->tid); + free_set_inf_compound(rqst); + break; case SMB2_OP_RENAME: + if (rc) + trace_smb3_rename_err(xid, ses->Suid, tcon->tid, rc); + else + trace_smb3_rename_done(xid, ses->Suid, tcon->tid); + free_set_inf_compound(rqst); + break; case SMB2_OP_RMDIR: + if (rc) + trace_smb3_rmdir_err(xid, ses->Suid, tcon->tid, rc); + else + trace_smb3_rmdir_done(xid, ses->Suid, tcon->tid); + free_set_inf_compound(rqst); + break; case SMB2_OP_SET_EOF: + if (rc) + trace_smb3_set_eof_err(xid, ses->Suid, tcon->tid, rc); + else + trace_smb3_set_eof_done(xid, ses->Suid, tcon->tid); + free_set_inf_compound(rqst); + break; case SMB2_OP_SET_INFO: - if (rqst[1].rq_iov) - SMB2_set_info_free(&rqst[1]); - if (rqst[2].rq_iov) - SMB2_close_free(&rqst[2]); + if (rc) + trace_smb3_set_info_compound_err(xid, ses->Suid, + tcon->tid, rc); + else + trace_smb3_set_info_compound_done(xid, ses->Suid, + tcon->tid); + free_set_inf_compound(rqst); break; } free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); @@ -309,12 +373,17 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, rc = open_shroot(xid, tcon, &fid); if (rc) goto out; - rc = SMB2_query_info(xid, tcon, fid.persistent_fid, - fid.volatile_fid, smb2_data); + + if (tcon->crfid.file_all_info_is_valid) { + move_smb2_info_to_cifs(data, + &tcon->crfid.file_all_info); + } else { + rc = SMB2_query_info(xid, tcon, fid.persistent_fid, + fid.volatile_fid, smb2_data); + if (!rc) + move_smb2_info_to_cifs(data, smb2_data); + } close_shroot(&tcon->crfid); - if (rc) - goto out; - move_smb2_info_to_cifs(data, smb2_data); goto out; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 085e91436da7..1022a3771e14 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -185,7 +185,7 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, spin_unlock(&server->req_lock); cifs_num_waiters_inc(server); rc = wait_event_killable(server->request_q, - has_credits(server, &server->credits)); + has_credits(server, &server->credits, 1)); cifs_num_waiters_dec(server); if (rc) return rc; @@ -619,6 +619,7 @@ smb2_close_cached_fid(struct kref *ref) SMB2_close(0, cfid->tcon, cfid->fid->persistent_fid, cfid->fid->volatile_fid); cfid->is_valid = false; + cfid->file_all_info_is_valid = false; } } @@ -643,9 +644,18 @@ smb2_cached_lease_break(struct work_struct *work) */ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) { - struct cifs_open_parms oparams; - int rc; - __le16 srch_path = 0; /* Null - since an open of top of share */ + struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = ses->server; + struct cifs_open_parms oparms; + struct smb2_create_rsp *o_rsp = NULL; + struct smb2_query_info_rsp *qi_rsp = NULL; + int resp_buftype[2]; + struct smb_rqst rqst[2]; + struct kvec rsp_iov[2]; + struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; + struct kvec qi_iov[1]; + int rc, flags = 0; + __le16 utf16_path = 0; /* Null - since an open of top of share */ u8 oplock = SMB2_OPLOCK_LEVEL_II; mutex_lock(&tcon->crfid.fid_mutex); @@ -657,22 +667,89 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) return 0; } - oparams.tcon = tcon; - oparams.create_options = 0; - oparams.desired_access = FILE_READ_ATTRIBUTES; - oparams.disposition = FILE_OPEN; - oparams.fid = pfid; - oparams.reconnect = false; - - rc = SMB2_open(xid, &oparams, &srch_path, &oplock, NULL, NULL, NULL); - if (rc == 0) { - memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid)); - tcon->crfid.tcon = tcon; - tcon->crfid.is_valid = true; - kref_init(&tcon->crfid.refcount); - kref_get(&tcon->crfid.refcount); - } + if (smb3_encryption_required(tcon)) + flags |= CIFS_TRANSFORM_REQ; + + memset(rqst, 0, sizeof(rqst)); + resp_buftype[0] = resp_buftype[1] = CIFS_NO_BUFFER; + memset(rsp_iov, 0, sizeof(rsp_iov)); + + /* Open */ + memset(&open_iov, 0, sizeof(open_iov)); + rqst[0].rq_iov = open_iov; + rqst[0].rq_nvec = SMB2_CREATE_IOV_SIZE; + + oparms.tcon = tcon; + oparms.create_options = 0; + oparms.desired_access = FILE_READ_ATTRIBUTES; + oparms.disposition = FILE_OPEN; + oparms.fid = pfid; + oparms.reconnect = false; + + rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, &utf16_path); + if (rc) + goto oshr_exit; + smb2_set_next_command(tcon, &rqst[0]); + + memset(&qi_iov, 0, sizeof(qi_iov)); + rqst[1].rq_iov = qi_iov; + rqst[1].rq_nvec = 1; + + rc = SMB2_query_info_init(tcon, &rqst[1], COMPOUND_FID, + COMPOUND_FID, FILE_ALL_INFORMATION, + SMB2_O_INFO_FILE, 0, + sizeof(struct smb2_file_all_info) + + PATH_MAX * 2, 0, NULL); + if (rc) + goto oshr_exit; + + smb2_set_related(&rqst[1]); + + rc = compound_send_recv(xid, ses, flags, 2, rqst, + resp_buftype, rsp_iov); + if (rc) + goto oshr_exit; + + o_rsp = (struct smb2_create_rsp *)rsp_iov[0].iov_base; + oparms.fid->persistent_fid = o_rsp->PersistentFileId; + oparms.fid->volatile_fid = o_rsp->VolatileFileId; +#ifdef CONFIG_CIFS_DEBUG2 + oparms.fid->mid = le64_to_cpu(o_rsp->sync_hdr.MessageId); +#endif /* CIFS_DEBUG2 */ + + if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) + oplock = smb2_parse_lease_state(server, o_rsp, + &oparms.fid->epoch, + oparms.fid->lease_key); + else + goto oshr_exit; + + + memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid)); + tcon->crfid.tcon = tcon; + tcon->crfid.is_valid = true; + kref_init(&tcon->crfid.refcount); + kref_get(&tcon->crfid.refcount); + + + qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; + if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info)) + goto oshr_exit; + rc = smb2_validate_and_copy_iov( + le16_to_cpu(qi_rsp->OutputBufferOffset), + sizeof(struct smb2_file_all_info), + &rsp_iov[1], sizeof(struct smb2_file_all_info), + (char *)&tcon->crfid.file_all_info); + if (rc) + goto oshr_exit; + tcon->crfid.file_all_info_is_valid = 1; + + oshr_exit: mutex_unlock(&tcon->crfid.fid_mutex); + SMB2_open_free(&rqst[0]); + SMB2_query_info_free(&rqst[1]); + free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); + free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); return rc; } @@ -1253,7 +1330,8 @@ smb2_ioctl_query_info(const unsigned int xid, struct smb_query_info __user *pqi; int rc = 0; int flags = 0; - struct smb2_query_info_rsp *rsp = NULL; + struct smb2_query_info_rsp *qi_rsp = NULL; + struct smb2_ioctl_rsp *io_rsp = NULL; void *buffer = NULL; struct smb_rqst rqst[3]; int resp_buftype[3]; @@ -1263,6 +1341,7 @@ smb2_ioctl_query_info(const unsigned int xid, u8 oplock = SMB2_OPLOCK_LEVEL_NONE; struct cifs_fid fid; struct kvec qi_iov[1]; + struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; struct kvec close_iov[1]; memset(rqst, 0, sizeof(rqst)); @@ -1313,15 +1392,35 @@ smb2_ioctl_query_info(const unsigned int xid, smb2_set_next_command(tcon, &rqst[0]); /* Query */ - memset(&qi_iov, 0, sizeof(qi_iov)); - rqst[1].rq_iov = qi_iov; - rqst[1].rq_nvec = 1; - - rc = SMB2_query_info_init(tcon, &rqst[1], COMPOUND_FID, COMPOUND_FID, - qi.file_info_class, qi.info_type, - qi.additional_information, + if (qi.flags & PASSTHRU_FSCTL) { + /* Can eventually relax perm check since server enforces too */ + if (!capable(CAP_SYS_ADMIN)) + rc = -EPERM; + else { + memset(&io_iov, 0, sizeof(io_iov)); + rqst[1].rq_iov = io_iov; + rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE; + + rc = SMB2_ioctl_init(tcon, &rqst[1], + COMPOUND_FID, COMPOUND_FID, + qi.info_type, true, NULL, + 0); + } + } else if (qi.flags == PASSTHRU_QUERY_INFO) { + memset(&qi_iov, 0, sizeof(qi_iov)); + rqst[1].rq_iov = qi_iov; + rqst[1].rq_nvec = 1; + + rc = SMB2_query_info_init(tcon, &rqst[1], COMPOUND_FID, + COMPOUND_FID, qi.file_info_class, + qi.info_type, qi.additional_information, qi.input_buffer_length, qi.output_buffer_length, buffer); + } else { /* unknown flags */ + cifs_dbg(VFS, "invalid passthru query flags: 0x%x\n", qi.flags); + rc = -EINVAL; + } + if (rc) goto iqinf_exit; smb2_set_next_command(tcon, &rqst[1]); @@ -1341,24 +1440,44 @@ smb2_ioctl_query_info(const unsigned int xid, resp_buftype, rsp_iov); if (rc) goto iqinf_exit; - pqi = (struct smb_query_info __user *)arg; - rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; - if (le32_to_cpu(rsp->OutputBufferLength) < qi.input_buffer_length) - qi.input_buffer_length = le32_to_cpu(rsp->OutputBufferLength); - if (copy_to_user(&pqi->input_buffer_length, &qi.input_buffer_length, - sizeof(qi.input_buffer_length))) { - rc = -EFAULT; - goto iqinf_exit; - } - if (copy_to_user(pqi + 1, rsp->Buffer, qi.input_buffer_length)) { - rc = -EFAULT; - goto iqinf_exit; + if (qi.flags & PASSTHRU_FSCTL) { + pqi = (struct smb_query_info __user *)arg; + io_rsp = (struct smb2_ioctl_rsp *)rsp_iov[1].iov_base; + if (le32_to_cpu(io_rsp->OutputCount) < qi.input_buffer_length) + qi.input_buffer_length = le32_to_cpu(io_rsp->OutputCount); + if (copy_to_user(&pqi->input_buffer_length, &qi.input_buffer_length, + sizeof(qi.input_buffer_length))) { + rc = -EFAULT; + goto iqinf_exit; + } + if (copy_to_user(pqi + 1, &io_rsp[1], qi.input_buffer_length)) { + rc = -EFAULT; + goto iqinf_exit; + } + } else { + pqi = (struct smb_query_info __user *)arg; + qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; + if (le32_to_cpu(qi_rsp->OutputBufferLength) < qi.input_buffer_length) + qi.input_buffer_length = le32_to_cpu(qi_rsp->OutputBufferLength); + if (copy_to_user(&pqi->input_buffer_length, &qi.input_buffer_length, + sizeof(qi.input_buffer_length))) { + rc = -EFAULT; + goto iqinf_exit; + } + if (copy_to_user(pqi + 1, qi_rsp->Buffer, qi.input_buffer_length)) { + rc = -EFAULT; + goto iqinf_exit; + } } iqinf_exit: kfree(buffer); SMB2_open_free(&rqst[0]); - SMB2_query_info_free(&rqst[1]); + if (qi.flags & PASSTHRU_FSCTL) + SMB2_ioctl_free(&rqst[1]); + else + SMB2_query_info_free(&rqst[1]); + SMB2_close_free(&rqst[2]); free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); @@ -2472,22 +2591,38 @@ get_smb2_acl(struct cifs_sb_info *cifs_sb, static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, loff_t offset, loff_t len, bool keep_size) { + struct cifs_ses *ses = tcon->ses; struct inode *inode; struct cifsInodeInfo *cifsi; struct cifsFileInfo *cfile = file->private_data; struct file_zero_data_information fsctl_buf; + struct smb_rqst rqst[2]; + int resp_buftype[2]; + struct kvec rsp_iov[2]; + struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; + struct kvec si_iov[1]; + unsigned int size[1]; + void *data[1]; long rc; unsigned int xid; + int num = 0, flags = 0; + __le64 eof; xid = get_xid(); inode = d_inode(cfile->dentry); cifsi = CIFS_I(inode); + trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, + ses->Suid, offset, len); + + /* if file not oplocked can't be sure whether asking to extend size */ if (!CIFS_CACHE_READ(cifsi)) if (keep_size == false) { rc = -EOPNOTSUPP; + trace_smb3_zero_err(xid, cfile->fid.persistent_fid, + tcon->tid, ses->Suid, offset, len, rc); free_xid(xid); return rc; } @@ -2498,33 +2633,73 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, */ if (!(cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE)) { rc = -EOPNOTSUPP; + trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, + ses->Suid, offset, len, rc); free_xid(xid); return rc; } - /* - * need to make sure we are not asked to extend the file since the SMB3 - * fsctl does not change the file size. In the future we could change - * this to zero the first part of the range then set the file size - * which for a non sparse file would zero the newly extended range - */ - if (keep_size == false) - if (i_size_read(inode) < offset + len) { - rc = -EOPNOTSUPP; - free_xid(xid); - return rc; - } - cifs_dbg(FYI, "offset %lld len %lld", offset, len); fsctl_buf.FileOffset = cpu_to_le64(offset); fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); - rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, - cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, - true /* is_fctl */, (char *)&fsctl_buf, - sizeof(struct file_zero_data_information), NULL, NULL); + if (smb3_encryption_required(tcon)) + flags |= CIFS_TRANSFORM_REQ; + + memset(rqst, 0, sizeof(rqst)); + resp_buftype[0] = resp_buftype[1] = CIFS_NO_BUFFER; + memset(rsp_iov, 0, sizeof(rsp_iov)); + + + memset(&io_iov, 0, sizeof(io_iov)); + rqst[num].rq_iov = io_iov; + rqst[num].rq_nvec = SMB2_IOCTL_IOV_SIZE; + rc = SMB2_ioctl_init(tcon, &rqst[num++], cfile->fid.persistent_fid, + cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, + true /* is_fctl */, (char *)&fsctl_buf, + sizeof(struct file_zero_data_information)); + if (rc) + goto zero_range_exit; + + /* + * do we also need to change the size of the file? + */ + if (keep_size == false && i_size_read(inode) < offset + len) { + smb2_set_next_command(tcon, &rqst[0]); + + memset(&si_iov, 0, sizeof(si_iov)); + rqst[num].rq_iov = si_iov; + rqst[num].rq_nvec = 1; + + eof = cpu_to_le64(offset + len); + size[0] = 8; /* sizeof __le64 */ + data[0] = &eof; + + rc = SMB2_set_info_init(tcon, &rqst[num++], + cfile->fid.persistent_fid, + cfile->fid.persistent_fid, + current->tgid, + FILE_END_OF_FILE_INFORMATION, + SMB2_O_INFO_FILE, 0, data, size); + smb2_set_related(&rqst[1]); + } + + rc = compound_send_recv(xid, ses, flags, num, rqst, + resp_buftype, rsp_iov); + + zero_range_exit: + SMB2_ioctl_free(&rqst[0]); + SMB2_set_info_free(&rqst[1]); + free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); + free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); free_xid(xid); + if (rc) + trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, + ses->Suid, offset, len, rc); + else + trace_smb3_zero_done(xid, cfile->fid.persistent_fid, tcon->tid, + ses->Suid, offset, len); return rc; } @@ -2573,15 +2748,20 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, struct cifsFileInfo *cfile = file->private_data; long rc = -EOPNOTSUPP; unsigned int xid; + __le64 eof; xid = get_xid(); inode = d_inode(cfile->dentry); cifsi = CIFS_I(inode); + trace_smb3_falloc_enter(xid, cfile->fid.persistent_fid, tcon->tid, + tcon->ses->Suid, off, len); /* if file not oplocked can't be sure whether asking to extend size */ if (!CIFS_CACHE_READ(cifsi)) if (keep_size == false) { + trace_smb3_falloc_err(xid, cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, off, len, rc); free_xid(xid); return rc; } @@ -2601,6 +2781,12 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, /* BB: in future add else clause to extend file */ else rc = -EOPNOTSUPP; + if (rc) + trace_smb3_falloc_err(xid, cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, off, len, rc); + else + trace_smb3_falloc_done(xid, cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, off, len); free_xid(xid); return rc; } @@ -2616,14 +2802,31 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, */ if ((off > 8192) || (off + len + 8192 < i_size_read(inode))) { rc = -EOPNOTSUPP; + trace_smb3_falloc_err(xid, cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, off, len, rc); free_xid(xid); return rc; } - rc = smb2_set_sparse(xid, tcon, cfile, inode, false); + smb2_set_sparse(xid, tcon, cfile, inode, false); + rc = 0; + } else { + smb2_set_sparse(xid, tcon, cfile, inode, false); + rc = 0; + if (i_size_read(inode) < off + len) { + eof = cpu_to_le64(off + len); + rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid, cfile->pid, + &eof); + } } - /* BB: else ... in future add code to extend file and set sparse */ + if (rc) + trace_smb3_falloc_err(xid, cfile->fid.persistent_fid, tcon->tid, + tcon->ses->Suid, off, len, rc); + else + trace_smb3_falloc_done(xid, cfile->fid.persistent_fid, tcon->tid, + tcon->ses->Suid, off, len); free_xid(xid); return rc; @@ -3604,6 +3807,104 @@ smb2_next_header(char *buf) return le32_to_cpu(hdr->NextCommand); } +static int +smb2_make_node(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + char *full_path, umode_t mode, dev_t dev) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + int rc = -EPERM; + int create_options = CREATE_NOT_DIR | CREATE_OPTION_SPECIAL; + FILE_ALL_INFO *buf = NULL; + struct cifs_io_parms io_parms; + __u32 oplock = 0; + struct cifs_fid fid; + struct cifs_open_parms oparms; + unsigned int bytes_written; + struct win_dev *pdev; + struct kvec iov[2]; + + /* + * Check if mounted with mount parm 'sfu' mount parm. + * SFU emulation should work with all servers, but only + * supports block and char device (no socket & fifo), + * and was used by default in earlier versions of Windows + */ + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) + goto out; + + /* + * TODO: Add ability to create instead via reparse point. Windows (e.g. + * their current NFS server) uses this approach to expose special files + * over SMB2/SMB3 and Samba will do this with SMB3.1.1 POSIX Extensions + */ + + if (!S_ISCHR(mode) && !S_ISBLK(mode)) + goto out; + + cifs_dbg(FYI, "sfu compat create special file\n"); + + buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); + if (buf == NULL) { + rc = -ENOMEM; + goto out; + } + + if (backup_cred(cifs_sb)) + create_options |= CREATE_OPEN_BACKUP_INTENT; + + oparms.tcon = tcon; + oparms.cifs_sb = cifs_sb; + oparms.desired_access = GENERIC_WRITE; + oparms.create_options = create_options; + oparms.disposition = FILE_CREATE; + oparms.path = full_path; + oparms.fid = &fid; + oparms.reconnect = false; + + if (tcon->ses->server->oplocks) + oplock = REQ_OPLOCK; + else + oplock = 0; + rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, buf); + if (rc) + goto out; + + /* + * BB Do not bother to decode buf since no local inode yet to put + * timestamps in, but we can reuse it safely. + */ + + pdev = (struct win_dev *)buf; + io_parms.pid = current->tgid; + io_parms.tcon = tcon; + io_parms.offset = 0; + io_parms.length = sizeof(struct win_dev); + iov[1].iov_base = buf; + iov[1].iov_len = sizeof(struct win_dev); + if (S_ISCHR(mode)) { + memcpy(pdev->type, "IntxCHR", 8); + pdev->major = cpu_to_le64(MAJOR(dev)); + pdev->minor = cpu_to_le64(MINOR(dev)); + rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms, + &bytes_written, iov, 1); + } else if (S_ISBLK(mode)) { + memcpy(pdev->type, "IntxBLK", 8); + pdev->major = cpu_to_le64(MAJOR(dev)); + pdev->minor = cpu_to_le64(MINOR(dev)); + rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms, + &bytes_written, iov, 1); + } + tcon->ses->server->ops->close(xid, tcon, &fid); + d_drop(dentry); + + /* FIXME: add code here to set EAs */ +out: + kfree(buf); + return rc; +} + + struct smb_version_operations smb20_operations = { .compare_fids = smb2_compare_fids, .setup_request = smb2_setup_request, @@ -3698,6 +3999,7 @@ struct smb_version_operations smb20_operations = { #endif /* CIFS_ACL */ .next_header = smb2_next_header, .ioctl_query_info = smb2_ioctl_query_info, + .make_node = smb2_make_node, }; struct smb_version_operations smb21_operations = { @@ -3796,6 +4098,7 @@ struct smb_version_operations smb21_operations = { #endif /* CIFS_ACL */ .next_header = smb2_next_header, .ioctl_query_info = smb2_ioctl_query_info, + .make_node = smb2_make_node, }; struct smb_version_operations smb30_operations = { @@ -3903,6 +4206,7 @@ struct smb_version_operations smb30_operations = { #endif /* CIFS_ACL */ .next_header = smb2_next_header, .ioctl_query_info = smb2_ioctl_query_info, + .make_node = smb2_make_node, }; struct smb_version_operations smb311_operations = { @@ -4011,6 +4315,7 @@ struct smb_version_operations smb311_operations = { #endif /* CIFS_ACL */ .next_header = smb2_next_header, .ioctl_query_info = smb2_ioctl_query_info, + .make_node = smb2_make_node, }; struct smb_version_values smb20_values = { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 60fbe306f604..c399e09b76e6 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1797,9 +1797,10 @@ create_reconnect_durable_buf(struct cifs_fid *fid) return buf; } -static __u8 -parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key) +__u8 +smb2_parse_lease_state(struct TCP_Server_Info *server, + struct smb2_create_rsp *rsp, + unsigned int *epoch, char *lease_key) { char *data_offset; struct create_context *cc; @@ -2456,8 +2457,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } if (rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) - *oplock = parse_lease_state(server, rsp, &oparms->fid->epoch, - oparms->fid->lease_key); + *oplock = smb2_parse_lease_state(server, rsp, + &oparms->fid->epoch, + oparms->fid->lease_key); else *oplock = rsp->OplockLevel; creat_exit: @@ -2466,65 +2468,46 @@ creat_exit: return rc; } -/* - * SMB2 IOCTL is used for both IOCTLs and FSCTLs - */ int -SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, - u64 volatile_fid, u32 opcode, bool is_fsctl, - char *in_data, u32 indatalen, - char **out_data, u32 *plen /* returned data len */) +SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, + u64 persistent_fid, u64 volatile_fid, u32 opcode, + bool is_fsctl, char *in_data, u32 indatalen) { - struct smb_rqst rqst; struct smb2_ioctl_req *req; - struct smb2_ioctl_rsp *rsp; - struct cifs_ses *ses; - struct kvec iov[2]; - struct kvec rsp_iov; - int resp_buftype; - int n_iov; - int rc = 0; - int flags = 0; + struct kvec *iov = rqst->rq_iov; unsigned int total_len; - - cifs_dbg(FYI, "SMB2 IOCTL\n"); - - if (out_data != NULL) - *out_data = NULL; - - /* zero out returned data len, in case of error */ - if (plen) - *plen = 0; - - if (tcon) - ses = tcon->ses; - else - return -EIO; - - if (!ses || !(ses->server)) - return -EIO; + int rc; rc = smb2_plain_req_init(SMB2_IOCTL, tcon, (void **) &req, &total_len); if (rc) return rc; - if (smb3_encryption_required(tcon)) - flags |= CIFS_TRANSFORM_REQ; - req->CtlCode = cpu_to_le32(opcode); req->PersistentFileId = persistent_fid; req->VolatileFileId = volatile_fid; + iov[0].iov_base = (char *)req; + /* + * If no input data, the size of ioctl struct in + * protocol spec still includes a 1 byte data buffer, + * but if input data passed to ioctl, we do not + * want to double count this, so we do not send + * the dummy one byte of data in iovec[0] if sending + * input data (in iovec[1]). + */ if (indatalen) { req->InputCount = cpu_to_le32(indatalen); /* do not set InputOffset if no input data */ req->InputOffset = cpu_to_le32(offsetof(struct smb2_ioctl_req, Buffer)); + rqst->rq_nvec = 2; + iov[0].iov_len = total_len - 1; iov[1].iov_base = in_data; iov[1].iov_len = indatalen; - n_iov = 2; - } else - n_iov = 1; + } else { + rqst->rq_nvec = 1; + iov[0].iov_len = total_len; + } req->OutputOffset = 0; req->OutputCount = 0; /* MBZ */ @@ -2546,33 +2529,70 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, else req->Flags = 0; - iov[0].iov_base = (char *)req; - - /* - * If no input data, the size of ioctl struct in - * protocol spec still includes a 1 byte data buffer, - * but if input data passed to ioctl, we do not - * want to double count this, so we do not send - * the dummy one byte of data in iovec[0] if sending - * input data (in iovec[1]). - */ - - if (indatalen) { - iov[0].iov_len = total_len - 1; - } else - iov[0].iov_len = total_len; - /* validate negotiate request must be signed - see MS-SMB2 3.2.5.5 */ if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO) req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED; + return 0; +} + +void +SMB2_ioctl_free(struct smb_rqst *rqst) +{ + if (rqst && rqst->rq_iov) + cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */ +} + +/* + * SMB2 IOCTL is used for both IOCTLs and FSCTLs + */ +int +SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, + u64 volatile_fid, u32 opcode, bool is_fsctl, + char *in_data, u32 indatalen, + char **out_data, u32 *plen /* returned data len */) +{ + struct smb_rqst rqst; + struct smb2_ioctl_rsp *rsp = NULL; + struct cifs_ses *ses; + struct kvec iov[SMB2_IOCTL_IOV_SIZE]; + struct kvec rsp_iov = {NULL, 0}; + int resp_buftype = CIFS_NO_BUFFER; + int rc = 0; + int flags = 0; + + cifs_dbg(FYI, "SMB2 IOCTL\n"); + + if (out_data != NULL) + *out_data = NULL; + + /* zero out returned data len, in case of error */ + if (plen) + *plen = 0; + + if (tcon) + ses = tcon->ses; + else + return -EIO; + + if (!ses || !(ses->server)) + return -EIO; + + if (smb3_encryption_required(tcon)) + flags |= CIFS_TRANSFORM_REQ; + memset(&rqst, 0, sizeof(struct smb_rqst)); + memset(&iov, 0, sizeof(iov)); rqst.rq_iov = iov; - rqst.rq_nvec = n_iov; + rqst.rq_nvec = SMB2_IOCTL_IOV_SIZE; + + rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid, + opcode, is_fsctl, in_data, indatalen); + if (rc) + goto ioctl_exit; rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); rsp = (struct smb2_ioctl_rsp *)rsp_iov.iov_base; if (rc != 0) @@ -2622,6 +2642,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, } ioctl_exit: + SMB2_ioctl_free(&rqst); free_rsp_buf(resp_buftype, rsp); return rc; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 0bd4d4802701..ee8977688e21 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -959,6 +959,13 @@ struct duplicate_extents_to_file { __le64 ByteCount; /* Bytes to be copied */ } __packed; +/* + * Maximum number of iovs we need for an ioctl request. + * [0] : struct smb2_ioctl_req + * [1] : in_data + */ +#define SMB2_IOCTL_IOV_SIZE 2 + struct smb2_ioctl_req { struct smb2_sync_hdr sync_hdr; __le16 StructureSize; /* Must be 57 */ diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 87733b27a65f..3c32d0cfea69 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -144,6 +144,10 @@ extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, bool is_fsctl, char *in_data, u32 indatalen, char **out_data, u32 *plen /* returned data len */); +extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, + u64 persistent_fid, u64 volatile_fid, u32 opcode, + bool is_fsctl, char *in_data, u32 indatalen); +extern void SMB2_ioctl_free(struct smb_rqst *rqst); extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id); extern int SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon, @@ -223,6 +227,9 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); +extern __u8 smb2_parse_lease_state(struct TCP_Server_Info *server, + struct smb2_create_rsp *rsp, + unsigned int *epoch, char *lease_key); extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); diff --git a/fs/cifs/smb2status.h b/fs/cifs/smb2status.h index 3d5f62150de4..447c0c6e4c64 100644 --- a/fs/cifs/smb2status.h +++ b/fs/cifs/smb2status.h @@ -30,9 +30,9 @@ */ #define STATUS_SEVERITY_SUCCESS __constant_cpu_to_le32(0x0000) -#define STATUS_SEVERITY_INFORMATIONAL __constanst_cpu_to_le32(0x0001) -#define STATUS_SEVERITY_WARNING __constanst_cpu_to_le32(0x0002) -#define STATUS_SEVERITY_ERROR __constanst_cpu_to_le32(0x0003) +#define STATUS_SEVERITY_INFORMATIONAL cpu_to_le32(0x0001) +#define STATUS_SEVERITY_WARNING cpu_to_le32(0x0002) +#define STATUS_SEVERITY_ERROR cpu_to_le32(0x0003) struct ntstatus { /* Facility is the high 12 bits of the following field */ diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index d8b049afa606..fa226de48ef3 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -59,6 +59,8 @@ DEFINE_EVENT(smb3_rw_err_class, smb3_##name, \ DEFINE_SMB3_RW_ERR_EVENT(write_err); DEFINE_SMB3_RW_ERR_EVENT(read_err); DEFINE_SMB3_RW_ERR_EVENT(query_dir_err); +DEFINE_SMB3_RW_ERR_EVENT(zero_err); +DEFINE_SMB3_RW_ERR_EVENT(falloc_err); /* For logging successful read or write */ @@ -104,9 +106,13 @@ DEFINE_EVENT(smb3_rw_done_class, smb3_##name, \ DEFINE_SMB3_RW_DONE_EVENT(write_enter); DEFINE_SMB3_RW_DONE_EVENT(read_enter); DEFINE_SMB3_RW_DONE_EVENT(query_dir_enter); +DEFINE_SMB3_RW_DONE_EVENT(zero_enter); +DEFINE_SMB3_RW_DONE_EVENT(falloc_enter); DEFINE_SMB3_RW_DONE_EVENT(write_done); DEFINE_SMB3_RW_DONE_EVENT(read_done); DEFINE_SMB3_RW_DONE_EVENT(query_dir_done); +DEFINE_SMB3_RW_DONE_EVENT(zero_done); +DEFINE_SMB3_RW_DONE_EVENT(falloc_done); /* * For handle based calls other than read and write, and get/set info @@ -242,6 +248,123 @@ DEFINE_SMB3_INF_ERR_EVENT(query_info_err); DEFINE_SMB3_INF_ERR_EVENT(set_info_err); DEFINE_SMB3_INF_ERR_EVENT(fsctl_err); +DECLARE_EVENT_CLASS(smb3_inf_compound_enter_class, + TP_PROTO(unsigned int xid, + __u32 tid, + __u64 sesid, + const char *full_path), + TP_ARGS(xid, tid, sesid, full_path), + TP_STRUCT__entry( + __field(unsigned int, xid) + __field(__u32, tid) + __field(__u64, sesid) + __string(path, full_path) + ), + TP_fast_assign( + __entry->xid = xid; + __entry->tid = tid; + __entry->sesid = sesid; + __assign_str(path, full_path); + ), + TP_printk("xid=%u sid=0x%llx tid=0x%x path=%s", + __entry->xid, __entry->sesid, __entry->tid, + __get_str(path)) +) + +#define DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(name) \ +DEFINE_EVENT(smb3_inf_compound_enter_class, smb3_##name, \ + TP_PROTO(unsigned int xid, \ + __u32 tid, \ + __u64 sesid, \ + const char *full_path), \ + TP_ARGS(xid, tid, sesid, full_path)) + +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_info_compound_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(hardlink_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rename_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rmdir_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_eof_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_info_compound_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(delete_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mkdir_enter); + + +DECLARE_EVENT_CLASS(smb3_inf_compound_done_class, + TP_PROTO(unsigned int xid, + __u32 tid, + __u64 sesid), + TP_ARGS(xid, tid, sesid), + TP_STRUCT__entry( + __field(unsigned int, xid) + __field(__u32, tid) + __field(__u64, sesid) + ), + TP_fast_assign( + __entry->xid = xid; + __entry->tid = tid; + __entry->sesid = sesid; + ), + TP_printk("xid=%u sid=0x%llx tid=0x%x", + __entry->xid, __entry->sesid, __entry->tid) +) + +#define DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(name) \ +DEFINE_EVENT(smb3_inf_compound_done_class, smb3_##name, \ + TP_PROTO(unsigned int xid, \ + __u32 tid, \ + __u64 sesid), \ + TP_ARGS(xid, tid, sesid)) + +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_info_compound_done); +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(hardlink_done); +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rename_done); +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rmdir_done); +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_eof_done); +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_info_compound_done); +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(delete_done); +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mkdir_done); + + +DECLARE_EVENT_CLASS(smb3_inf_compound_err_class, + TP_PROTO(unsigned int xid, + __u32 tid, + __u64 sesid, + int rc), + TP_ARGS(xid, tid, sesid, rc), + TP_STRUCT__entry( + __field(unsigned int, xid) + __field(__u32, tid) + __field(__u64, sesid) + __field(int, rc) + ), + TP_fast_assign( + __entry->xid = xid; + __entry->tid = tid; + __entry->sesid = sesid; + __entry->rc = rc; + ), + TP_printk("xid=%u sid=0x%llx tid=0x%x rc=%d", + __entry->xid, __entry->sesid, __entry->tid, + __entry->rc) +) + +#define DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(name) \ +DEFINE_EVENT(smb3_inf_compound_err_class, smb3_##name, \ + TP_PROTO(unsigned int xid, \ + __u32 tid, \ + __u64 sesid, \ + int rc), \ + TP_ARGS(xid, tid, sesid, rc)) + +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_info_compound_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(hardlink_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rename_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rmdir_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_eof_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_info_compound_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mkdir_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(delete_err); + /* * For logging SMB3 Status code and Command for responses which return errors */ @@ -713,6 +836,7 @@ DEFINE_EVENT(smb3_credit_class, smb3_##name, \ TP_ARGS(currmid, hostname, credits)) DEFINE_SMB3_CREDIT_EVENT(reconnect_with_invalid_credits); +DEFINE_SMB3_CREDIT_EVENT(credit_timeout); #endif /* _CIFS_TRACE_H */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 7ce8a585abd6..1de8e996e566 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -486,15 +486,31 @@ smb_send(struct TCP_Server_Info *server, struct smb_hdr *smb_buffer, } static int -wait_for_free_credits(struct TCP_Server_Info *server, const int timeout, - int *credits, unsigned int *instance) +wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, + const int timeout, const int flags, + unsigned int *instance) { int rc; + int *credits; + int optype; + long int t; + + if (timeout < 0) + t = MAX_JIFFY_OFFSET; + else + t = msecs_to_jiffies(timeout); + + optype = flags & CIFS_OP_MASK; *instance = 0; + credits = server->ops->get_credits_field(server, optype); + /* Since an echo is already inflight, no need to wait to send another */ + if (*credits <= 0 && optype == CIFS_ECHO_OP) + return -EAGAIN; + spin_lock(&server->req_lock); - if (timeout == CIFS_ASYNC_OP) { + if ((flags & CIFS_TIMEOUT_MASK) == CIFS_ASYNC_OP) { /* oplock breaks must not be held up */ server->in_flight++; *credits -= 1; @@ -504,14 +520,21 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int timeout, } while (1) { - if (*credits <= 0) { + if (*credits < num_credits) { spin_unlock(&server->req_lock); cifs_num_waiters_inc(server); - rc = wait_event_killable(server->request_q, - has_credits(server, credits)); + rc = wait_event_killable_timeout(server->request_q, + has_credits(server, credits, num_credits), t); cifs_num_waiters_dec(server); - if (rc) - return rc; + if (!rc) { + trace_smb3_credit_timeout(server->CurrentMid, + server->hostname, num_credits); + cifs_dbg(VFS, "wait timed out after %d ms\n", + timeout); + return -ENOTSUPP; + } + if (rc == -ERESTARTSYS) + return -ERESTARTSYS; spin_lock(&server->req_lock); } else { if (server->tcpStatus == CifsExiting) { @@ -520,14 +543,52 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int timeout, } /* + * For normal commands, reserve the last MAX_COMPOUND + * credits to compound requests. + * Otherwise these compounds could be permanently + * starved for credits by single-credit requests. + * + * To prevent spinning CPU, block this thread until + * there are >MAX_COMPOUND credits available. + * But only do this is we already have a lot of + * credits in flight to avoid triggering this check + * for servers that are slow to hand out credits on + * new sessions. + */ + if (!optype && num_credits == 1 && + server->in_flight > 2 * MAX_COMPOUND && + *credits <= MAX_COMPOUND) { + spin_unlock(&server->req_lock); + cifs_num_waiters_inc(server); + rc = wait_event_killable_timeout( + server->request_q, + has_credits(server, credits, + MAX_COMPOUND + 1), + t); + cifs_num_waiters_dec(server); + if (!rc) { + trace_smb3_credit_timeout( + server->CurrentMid, + server->hostname, num_credits); + cifs_dbg(VFS, "wait timed out after %d ms\n", + timeout); + return -ENOTSUPP; + } + if (rc == -ERESTARTSYS) + return -ERESTARTSYS; + spin_lock(&server->req_lock); + continue; + } + + /* * Can not count locking commands against total * as they are allowed to block on server. */ /* update # of requests on the wire to server */ - if (timeout != CIFS_BLOCKING_OP) { - *credits -= 1; - server->in_flight++; + if ((flags & CIFS_TIMEOUT_MASK) != CIFS_BLOCKING_OP) { + *credits -= num_credits; + server->in_flight += num_credits; *instance = server->reconnect_instance; } spin_unlock(&server->req_lock); @@ -538,16 +599,36 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int timeout, } static int -wait_for_free_request(struct TCP_Server_Info *server, const int timeout, - const int optype, unsigned int *instance) +wait_for_free_request(struct TCP_Server_Info *server, const int flags, + unsigned int *instance) { - int *val; + return wait_for_free_credits(server, 1, -1, flags, + instance); +} - val = server->ops->get_credits_field(server, optype); - /* Since an echo is already inflight, no need to wait to send another */ - if (*val <= 0 && optype == CIFS_ECHO_OP) - return -EAGAIN; - return wait_for_free_credits(server, timeout, val, instance); +static int +wait_for_compound_request(struct TCP_Server_Info *server, int num, + const int flags, unsigned int *instance) +{ + int *credits; + + credits = server->ops->get_credits_field(server, flags & CIFS_OP_MASK); + + spin_lock(&server->req_lock); + if (*credits < num) { + /* + * Return immediately if not too many requests in flight since + * we will likely be stuck on waiting for credits. + */ + if (server->in_flight < num - *credits) { + spin_unlock(&server->req_lock); + return -ENOTSUPP; + } + } + spin_unlock(&server->req_lock); + + return wait_for_free_credits(server, num, 60000, flags, + instance); } int @@ -646,16 +727,16 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, mid_handle_t *handle, void *cbdata, const int flags, const struct cifs_credits *exist_credits) { - int rc, timeout, optype; + int rc; struct mid_q_entry *mid; struct cifs_credits credits = { .value = 0, .instance = 0 }; unsigned int instance; + int optype; - timeout = flags & CIFS_TIMEOUT_MASK; optype = flags & CIFS_OP_MASK; if ((flags & CIFS_HAS_CREDITS) == 0) { - rc = wait_for_free_request(server, timeout, optype, &instance); + rc = wait_for_free_request(server, flags, &instance); if (rc) return rc; credits.value = 1; @@ -871,18 +952,15 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, const int flags, const int num_rqst, struct smb_rqst *rqst, int *resp_buf_type, struct kvec *resp_iov) { - int i, j, rc = 0; - int timeout, optype; + int i, j, optype, rc = 0; struct mid_q_entry *midQ[MAX_COMPOUND]; bool cancelled_mid[MAX_COMPOUND] = {false}; struct cifs_credits credits[MAX_COMPOUND] = { { .value = 0, .instance = 0 } }; unsigned int instance; - unsigned int first_instance = 0; char *buf; - timeout = flags & CIFS_TIMEOUT_MASK; optype = flags & CIFS_OP_MASK; for (i = 0; i < num_rqst; i++) @@ -896,81 +974,24 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, if (ses->server->tcpStatus == CifsExiting) return -ENOENT; - spin_lock(&ses->server->req_lock); - if (ses->server->credits < num_rqst) { - /* - * Return immediately if not too many requests in flight since - * we will likely be stuck on waiting for credits. - */ - if (ses->server->in_flight < num_rqst - ses->server->credits) { - spin_unlock(&ses->server->req_lock); - return -ENOTSUPP; - } - } else { - /* enough credits to send the whole compounded request */ - ses->server->credits -= num_rqst; - ses->server->in_flight += num_rqst; - first_instance = ses->server->reconnect_instance; - } - spin_unlock(&ses->server->req_lock); - - if (first_instance) { - cifs_dbg(FYI, "Acquired %d credits at once\n", num_rqst); - for (i = 0; i < num_rqst; i++) { - credits[i].value = 1; - credits[i].instance = first_instance; - } - goto setup_rqsts; - } - /* - * There are not enough credits to send the whole compound request but - * there are requests in flight that may bring credits from the server. + * Wait for all the requests to become available. * This approach still leaves the possibility to be stuck waiting for * credits if the server doesn't grant credits to the outstanding - * requests. This should be fixed by returning immediately and letting - * a caller fallback to sequential commands instead of compounding. - * Ensure we obtain 1 credit per request in the compound chain. + * requests and if the client is completely idle, not generating any + * other requests. + * This can be handled by the eventual session reconnect. */ - for (i = 0; i < num_rqst; i++) { - rc = wait_for_free_request(ses->server, timeout, optype, - &instance); - - if (rc == 0) { - credits[i].value = 1; - credits[i].instance = instance; - /* - * All parts of the compound chain must get credits from - * the same session, otherwise we may end up using more - * credits than the server granted. If there were - * reconnects in between, return -EAGAIN and let callers - * handle it. - */ - if (i == 0) - first_instance = instance; - else if (first_instance != instance) { - i++; - rc = -EAGAIN; - } - } + rc = wait_for_compound_request(ses->server, num_rqst, flags, + &instance); + if (rc) + return rc; - if (rc) { - /* - * We haven't sent an SMB packet to the server yet but - * we already obtained credits for i requests in the - * compound chain - need to return those credits back - * for future use. Note that we need to call add_credits - * multiple times to match the way we obtained credits - * in the first place and to account for in flight - * requests correctly. - */ - for (j = 0; j < i; j++) - add_credits(ses->server, &credits[j], optype); - return rc; - } + for (i = 0; i < num_rqst; i++) { + credits[i].value = 1; + credits[i].instance = instance; } -setup_rqsts: /* * Make sure that we sign in the same order that we send on this socket * and avoid races inside tcp sendmsg code that could cause corruption @@ -981,14 +1002,12 @@ setup_rqsts: /* * All the parts of the compound chain belong obtained credits from the - * same session (see the appropriate checks above). In the same time - * there might be reconnects after those checks but before we acquired - * the srv_mutex. We can not use credits obtained from the previous + * same session. We can not use credits obtained from the previous * session to send this request. Check if there were reconnects after * we obtained credits and return -EAGAIN in such cases to let callers * handle it. */ - if (first_instance != ses->server->reconnect_instance) { + if (instance != ses->server->reconnect_instance) { mutex_unlock(&ses->server->srv_mutex); for (j = 0; j < num_rqst; j++) add_credits(ses->server, &credits[j], optype); @@ -1057,7 +1076,7 @@ setup_rqsts: smb311_update_preauth_hash(ses, rqst[0].rq_iov, rqst[0].rq_nvec); - if (timeout == CIFS_ASYNC_OP) + if ((flags & CIFS_TIMEOUT_MASK) == CIFS_ASYNC_OP) goto out; for (i = 0; i < num_rqst; i++) { @@ -1194,7 +1213,7 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses, int SendReceive(const unsigned int xid, struct cifs_ses *ses, struct smb_hdr *in_buf, struct smb_hdr *out_buf, - int *pbytes_returned, const int timeout) + int *pbytes_returned, const int flags) { int rc = 0; struct mid_q_entry *midQ; @@ -1225,7 +1244,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, return -EIO; } - rc = wait_for_free_request(ses->server, timeout, 0, &credits.instance); + rc = wait_for_free_request(ses->server, flags, &credits.instance); if (rc) return rc; @@ -1264,7 +1283,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, if (rc < 0) goto out; - if (timeout == CIFS_ASYNC_OP) + if ((flags & CIFS_TIMEOUT_MASK) == CIFS_ASYNC_OP) goto out; rc = wait_for_response(ses->server, midQ); @@ -1367,8 +1386,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, return -EIO; } - rc = wait_for_free_request(ses->server, CIFS_BLOCKING_OP, 0, - &instance); + rc = wait_for_free_request(ses->server, CIFS_BLOCKING_OP, &instance); if (rc) return rc; diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index f955cd3e0677..a98e1b02279e 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -306,8 +306,9 @@ static int f2fs_write_meta_pages(struct address_space *mapping, goto skip_write; /* collect a number of dirty meta pages and write together */ - if (wbc->for_kupdate || - get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META)) + if (wbc->sync_mode != WB_SYNC_ALL && + get_pages(sbi, F2FS_DIRTY_META) < + nr_pages_to_skip(sbi, META)) goto skip_write; /* if locked failed, cp will flush dirty pages instead */ @@ -405,7 +406,7 @@ static int f2fs_set_meta_page_dirty(struct page *page) if (!PageDirty(page)) { __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); return 1; } @@ -956,7 +957,7 @@ void f2fs_update_dirty_page(struct inode *inode, struct page *page) inode_inc_dirty_pages(inode); spin_unlock(&sbi->inode_lock[type]); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); } @@ -1259,10 +1260,17 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) else __clear_ckpt_flags(ckpt, CP_DISABLED_FLAG); + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK)) + __set_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG); + else + __clear_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG); + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); - else - __clear_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + /* + * TODO: we count on fsck.f2fs to clear this flag until we figure out + * missing cases which clear it incorrectly. + */ if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 568e1d09eb48..9727944139f2 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -301,9 +301,10 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, for (; start < F2FS_IO_SIZE(sbi); start++) { struct page *page = mempool_alloc(sbi->write_io_dummy, - GFP_NOIO | __GFP_ZERO | __GFP_NOFAIL); + GFP_NOIO | __GFP_NOFAIL); f2fs_bug_on(sbi, !page); + zero_user_segment(page, 0, PAGE_SIZE); SetPagePrivate(page); set_page_private(page, (unsigned long)DUMMY_WRITTEN_PAGE); lock_page(page); @@ -1553,6 +1554,9 @@ static int f2fs_mpage_readpages(struct address_space *mapping, if (last_block > last_block_in_file) last_block = last_block_in_file; + /* just zeroing out page which is beyond EOF */ + if (block_in_file >= last_block) + goto zero_out; /* * Map blocks using the previous result first. */ @@ -1565,16 +1569,11 @@ static int f2fs_mpage_readpages(struct address_space *mapping, * Then do more f2fs_map_blocks() calls until we are * done with this page. */ - map.m_flags = 0; - - if (block_in_file < last_block) { - map.m_lblk = block_in_file; - map.m_len = last_block - block_in_file; + map.m_lblk = block_in_file; + map.m_len = last_block - block_in_file; - if (f2fs_map_blocks(inode, &map, 0, - F2FS_GET_BLOCK_DEFAULT)) - goto set_error_page; - } + if (f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT)) + goto set_error_page; got_it: if ((map.m_flags & F2FS_MAP_MAPPED)) { block_nr = map.m_pblk + block_in_file - map.m_lblk; @@ -1589,6 +1588,7 @@ got_it: DATA_GENERIC)) goto set_error_page; } else { +zero_out: zero_user_segment(page, 0, PAGE_SIZE); if (!PageUptodate(page)) SetPageUptodate(page); @@ -1863,8 +1863,13 @@ got_it: if (fio->need_lock == LOCK_REQ) f2fs_unlock_op(fio->sbi); err = f2fs_inplace_write_data(fio); - if (err && PageWriteback(page)) - end_page_writeback(page); + if (err) { + if (f2fs_encrypted_file(inode)) + fscrypt_pullback_bio_page(&fio->encrypted_page, + true); + if (PageWriteback(page)) + end_page_writeback(page); + } trace_f2fs_do_write_data_page(fio->page, IPU); set_inode_flag(inode, FI_UPDATE_WRITE); return err; @@ -2315,7 +2320,8 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to) down_write(&F2FS_I(inode)->i_mmap_sem); truncate_pagecache(inode, i_size); - f2fs_truncate_blocks(inode, i_size, true, true); + if (!IS_NOQUOTA(inode)) + f2fs_truncate_blocks(inode, i_size, true); up_write(&F2FS_I(inode)->i_mmap_sem); up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); @@ -2585,14 +2591,11 @@ static void f2fs_dio_submit_bio(struct bio *bio, struct inode *inode, { struct f2fs_private_dio *dio; bool write = (bio_op(bio) == REQ_OP_WRITE); - int err; dio = f2fs_kzalloc(F2FS_I_SB(inode), sizeof(struct f2fs_private_dio), GFP_NOFS); - if (!dio) { - err = -ENOMEM; + if (!dio) goto out; - } dio->inode = inode; dio->orig_end_io = bio->bi_end_io; @@ -2710,12 +2713,10 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, clear_cold_data(page); - /* This is atomic written page, keep Private */ if (IS_ATOMIC_WRITTEN_PAGE(page)) return f2fs_drop_inmem_page(inode, page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); } int f2fs_release_page(struct page *page, gfp_t wait) @@ -2729,8 +2730,7 @@ int f2fs_release_page(struct page *page, gfp_t wait) return 0; clear_cold_data(page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); return 1; } @@ -2798,12 +2798,8 @@ int f2fs_migrate_page(struct address_space *mapping, return -EAGAIN; } - /* - * A reference is expected if PagePrivate set when move mapping, - * however F2FS breaks this for maintaining dirty page counts when - * truncating pages. So here adjusting the 'extra_count' make it work. - */ - extra_count = (atomic_written ? 1 : 0) - page_has_private(page); + /* one extra reference was held for atomic_write page */ + extra_count = atomic_written ? 1 : 0; rc = migrate_page_move_mapping(mapping, newpage, page, mode, extra_count); if (rc != MIGRATEPAGE_SUCCESS) { @@ -2824,9 +2820,10 @@ int f2fs_migrate_page(struct address_space *mapping, get_page(newpage); } - if (PagePrivate(page)) - SetPagePrivate(newpage); - set_page_private(newpage, page_private(page)); + if (PagePrivate(page)) { + f2fs_set_page_private(newpage, page_private(page)); + f2fs_clear_page_private(page); + } if (mode != MIGRATE_SYNC_NO_COPY) migrate_page_copy(newpage, page); diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index fd7f170e2f2d..99e9a5c37b71 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -96,8 +96,10 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->free_secs = free_sections(sbi); si->prefree_count = prefree_segments(sbi); si->dirty_count = dirty_segments(sbi); - si->node_pages = NODE_MAPPING(sbi)->nrpages; - si->meta_pages = META_MAPPING(sbi)->nrpages; + if (sbi->node_inode) + si->node_pages = NODE_MAPPING(sbi)->nrpages; + if (sbi->meta_inode) + si->meta_pages = META_MAPPING(sbi)->nrpages; si->nats = NM_I(sbi)->nat_cnt; si->dirty_nats = NM_I(sbi)->dirty_nat_cnt; si->sits = MAIN_SEGS(sbi); @@ -175,7 +177,6 @@ static void update_sit_info(struct f2fs_sb_info *sbi) static void update_mem_info(struct f2fs_sb_info *sbi) { struct f2fs_stat_info *si = F2FS_STAT(sbi); - unsigned npages; int i; if (si->base_mem) @@ -258,10 +259,14 @@ get_cache: sizeof(struct extent_node); si->page_mem = 0; - npages = NODE_MAPPING(sbi)->nrpages; - si->page_mem += (unsigned long long)npages << PAGE_SHIFT; - npages = META_MAPPING(sbi)->nrpages; - si->page_mem += (unsigned long long)npages << PAGE_SHIFT; + if (sbi->node_inode) { + unsigned npages = NODE_MAPPING(sbi)->nrpages; + si->page_mem += (unsigned long long)npages << PAGE_SHIFT; + } + if (sbi->meta_inode) { + unsigned npages = META_MAPPING(sbi)->nrpages; + si->page_mem += (unsigned long long)npages << PAGE_SHIFT; + } } static int stat_show(struct seq_file *s, void *v) diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 713b36a10a79..59bc46017855 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -728,7 +728,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, !f2fs_truncate_hole(dir, page->index, page->index + 1)) { f2fs_clear_page_cache_dirty_tag(page); clear_page_dirty_for_io(page); - ClearPagePrivate(page); + f2fs_clear_page_private(page); ClearPageUptodate(page); clear_cold_data(page); inode_dec_dirty_pages(dir); @@ -800,6 +800,10 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, if (de->name_len == 0) { bit_pos++; ctx->pos = start_pos + bit_pos; + printk_ratelimited( + "%s, invalid namelen(0), ino:%u, run fsck to fix.", + KERN_WARNING, le32_to_cpu(de->ino)); + set_sbi_flag(sbi, SBI_NEED_FSCK); continue; } @@ -810,7 +814,8 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, /* check memory boundary before moving forward */ bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); - if (unlikely(bit_pos > d->max)) { + if (unlikely(bit_pos > d->max || + le16_to_cpu(de->name_len) > F2FS_NAME_LEN)) { f2fs_msg(sbi->sb, KERN_WARNING, "%s: corrupted namelen=%d, run fsck to fix.", __func__, le16_to_cpu(de->name_len)); @@ -891,7 +896,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) page_cache_sync_readahead(inode->i_mapping, ra, file, n, min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES)); - dentry_page = f2fs_get_lock_data_page(inode, n, false); + dentry_page = f2fs_find_data_page(inode, n); if (IS_ERR(dentry_page)) { err = PTR_ERR(dentry_page); if (err == -ENOENT) { @@ -909,11 +914,11 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) err = f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr); if (err) { - f2fs_put_page(dentry_page, 1); + f2fs_put_page(dentry_page, 0); break; } - f2fs_put_page(dentry_page, 1); + f2fs_put_page(dentry_page, 0); } out_free: fscrypt_fname_free_buffer(&fstr); diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 1cb0fcc67d2d..caf77fe8ac07 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -506,7 +506,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode, unsigned int end = fofs + len; unsigned int pos = (unsigned int)fofs; bool updated = false; - bool leftmost; + bool leftmost = false; if (!et) return; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 7ea5c9cede37..87f75ebd2fd6 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -190,6 +190,8 @@ enum { #define DEF_CP_INTERVAL 60 /* 60 secs */ #define DEF_IDLE_INTERVAL 5 /* 5 secs */ #define DEF_DISABLE_INTERVAL 5 /* 5 secs */ +#define DEF_DISABLE_QUICK_INTERVAL 1 /* 1 secs */ +#define DEF_UMOUNT_DISCARD_TIMEOUT 5 /* 5 secs */ struct cp_control { int reason; @@ -253,7 +255,7 @@ struct discard_entry { /* max discard pend list number */ #define MAX_PLIST_NUM 512 #define plist_idx(blk_num) ((blk_num) >= MAX_PLIST_NUM ? \ - (MAX_PLIST_NUM - 1) : (blk_num - 1)) + (MAX_PLIST_NUM - 1) : ((blk_num) - 1)) enum { D_PREP, /* initial */ @@ -309,6 +311,7 @@ struct discard_policy { bool sync; /* submit discard with REQ_SYNC flag */ bool ordered; /* issue discard by lba order */ unsigned int granularity; /* discard granularity */ + int timeout; /* discard timeout for put_super */ }; struct discard_cmd_control { @@ -455,7 +458,6 @@ struct f2fs_flush_device { /* for inline stuff */ #define DEF_INLINE_RESERVED_SIZE 1 -#define DEF_MIN_INLINE_SIZE 1 static inline int get_extra_isize(struct inode *inode); static inline int get_inline_xattr_addrs(struct inode *inode); #define MAX_INLINE_DATA(inode) (sizeof(__le32) * \ @@ -1098,6 +1100,7 @@ enum { SBI_IS_SHUTDOWN, /* shutdown by ioctl */ SBI_IS_RECOVERED, /* recovered orphan/data */ SBI_CP_DISABLED, /* CP was disabled last mount */ + SBI_CP_DISABLED_QUICK, /* CP was disabled quickly */ SBI_QUOTA_NEED_FLUSH, /* need to flush quota info in CP */ SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */ SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */ @@ -1109,6 +1112,7 @@ enum { DISCARD_TIME, GC_TIME, DISABLE_TIME, + UMOUNT_DISCARD_TIMEOUT, MAX_TIME, }; @@ -1237,8 +1241,6 @@ struct f2fs_sb_info { unsigned int nquota_files; /* # of quota sysfile */ - u32 s_next_generation; /* for NFS support */ - /* # of pages, see count_type */ atomic_t nr_pages[NR_COUNT_TYPE]; /* # of allocated blocks */ @@ -1798,13 +1800,12 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) { atomic_inc(&sbi->nr_pages[count_type]); - if (count_type == F2FS_DIRTY_DATA || count_type == F2FS_INMEM_PAGES || - count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA || - count_type == F2FS_RD_DATA || count_type == F2FS_RD_NODE || - count_type == F2FS_RD_META) - return; - - set_sbi_flag(sbi, SBI_IS_DIRTY); + if (count_type == F2FS_DIRTY_DENTS || + count_type == F2FS_DIRTY_NODES || + count_type == F2FS_DIRTY_META || + count_type == F2FS_DIRTY_QDATA || + count_type == F2FS_DIRTY_IMETA) + set_sbi_flag(sbi, SBI_IS_DIRTY); } static inline void inode_inc_dirty_pages(struct inode *inode) @@ -2156,10 +2157,17 @@ static inline bool is_idle(struct f2fs_sb_info *sbi, int type) get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) || get_pages(sbi, F2FS_WB_CP_DATA) || get_pages(sbi, F2FS_DIO_READ) || - get_pages(sbi, F2FS_DIO_WRITE) || - atomic_read(&SM_I(sbi)->dcc_info->queued_discard) || - atomic_read(&SM_I(sbi)->fcc_info->queued_flush)) + get_pages(sbi, F2FS_DIO_WRITE)) return false; + + if (SM_I(sbi) && SM_I(sbi)->dcc_info && + atomic_read(&SM_I(sbi)->dcc_info->queued_discard)) + return false; + + if (SM_I(sbi) && SM_I(sbi)->fcc_info && + atomic_read(&SM_I(sbi)->fcc_info->queued_flush)) + return false; + return f2fs_time_over(sbi, type); } @@ -2300,11 +2308,12 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr) #define F2FS_EXTENTS_FL 0x00080000 /* Inode uses extents */ #define F2FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */ #define F2FS_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ +#define F2FS_NOCOW_FL 0x00800000 /* Do not cow file */ #define F2FS_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ #define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define F2FS_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ -#define F2FS_FL_USER_VISIBLE 0x304BDFFF /* User visible flags */ +#define F2FS_FL_USER_VISIBLE 0x30CBDFFF /* User visible flags */ #define F2FS_FL_USER_MODIFIABLE 0x204BC0FF /* User modifiable flags */ /* Flags we can manipulate with through F2FS_IOC_FSSETXATTR */ @@ -2761,9 +2770,9 @@ static inline int get_inline_xattr_addrs(struct inode *inode) #define F2FS_OLD_ATTRIBUTE_SIZE (offsetof(struct f2fs_inode, i_addr)) #define F2FS_FITS_IN_INODE(f2fs_inode, extra_isize, field) \ - ((offsetof(typeof(*f2fs_inode), field) + \ + ((offsetof(typeof(*(f2fs_inode)), field) + \ sizeof((f2fs_inode)->field)) \ - <= (F2FS_OLD_ATTRIBUTE_SIZE + extra_isize)) \ + <= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize))) \ static inline void f2fs_reset_iostat(struct f2fs_sb_info *sbi) { @@ -2792,8 +2801,8 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi, #define __is_large_section(sbi) ((sbi)->segs_per_sec > 1) -#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO(fio->type) == META && \ - (!is_read_io(fio->op) || fio->is_meta)) +#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META && \ + (!is_read_io((fio)->op) || (fio)->is_meta)) bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); @@ -2825,13 +2834,33 @@ static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi, return true; } +static inline void f2fs_set_page_private(struct page *page, + unsigned long data) +{ + if (PagePrivate(page)) + return; + + get_page(page); + SetPagePrivate(page); + set_page_private(page, data); +} + +static inline void f2fs_clear_page_private(struct page *page) +{ + if (!PagePrivate(page)) + return; + + set_page_private(page, 0); + ClearPagePrivate(page); + f2fs_put_page(page, 0); +} + /* * file.c */ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); void f2fs_truncate_data_blocks(struct dnode_of_data *dn); -int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, - bool buf_write); +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate(struct inode *inode); int f2fs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); @@ -3005,7 +3034,7 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi); void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi); -bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi); +bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi); void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi); @@ -3610,8 +3639,6 @@ extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, #define f2fs_build_fault_attr(sbi, rate, type) do { } while (0) #endif -#endif - static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) { #ifdef CONFIG_QUOTA @@ -3624,3 +3651,5 @@ static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) #endif return false; } + +#endif diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ba5954f41e14..5742ab8b57dc 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -589,8 +589,7 @@ truncate_out: return 0; } -int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, - bool buf_write) +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; @@ -598,7 +597,6 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, int count = 0, err = 0; struct page *ipage; bool truncate_page = false; - int flag = buf_write ? F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO; trace_f2fs_truncate_blocks_enter(inode, from); @@ -608,7 +606,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, goto free_partial; if (lock) - __do_map_lock(sbi, flag, true); + f2fs_lock_op(sbi); ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { @@ -646,7 +644,7 @@ free_next: err = f2fs_truncate_inode_blocks(inode, free_from); out: if (lock) - __do_map_lock(sbi, flag, false); + f2fs_unlock_op(sbi); free_partial: /* lastly zero out the first data page */ if (!err) @@ -681,7 +679,7 @@ int f2fs_truncate(struct inode *inode) return err; } - err = f2fs_truncate_blocks(inode, i_size_read(inode), true, false); + err = f2fs_truncate_blocks(inode, i_size_read(inode), true); if (err) return err; @@ -768,7 +766,6 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int err; - bool size_changed = false; if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; @@ -843,8 +840,6 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) down_write(&F2FS_I(inode)->i_sem); F2FS_I(inode)->last_disk_size = i_size_read(inode); up_write(&F2FS_I(inode)->i_sem); - - size_changed = true; } __setattr_copy(inode, attr); @@ -858,7 +853,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) } /* file size may changed here */ - f2fs_mark_inode_dirty_sync(inode, size_changed); + f2fs_mark_inode_dirty_sync(inode, true); /* inode change will produce dirty node pages flushed by checkpoint */ f2fs_balance_fs(F2FS_I_SB(inode), true); @@ -1262,7 +1257,7 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) new_size = i_size_read(inode) - len; truncate_pagecache(inode, new_size); - ret = f2fs_truncate_blocks(inode, new_size, true, false); + ret = f2fs_truncate_blocks(inode, new_size, true); up_write(&F2FS_I(inode)->i_mmap_sem); if (!ret) f2fs_i_size_write(inode, new_size); @@ -1447,7 +1442,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); down_write(&F2FS_I(inode)->i_mmap_sem); - ret = f2fs_truncate_blocks(inode, i_size_read(inode), true, false); + ret = f2fs_truncate_blocks(inode, i_size_read(inode), true); up_write(&F2FS_I(inode)->i_mmap_sem); if (ret) return ret; @@ -1651,6 +1646,8 @@ static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) flags |= F2FS_ENCRYPT_FL; if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) flags |= F2FS_INLINE_DATA_FL; + if (is_inode_flag_set(inode, FI_PIN_FILE)) + flags |= F2FS_NOCOW_FL; flags &= F2FS_FL_USER_VISIBLE; @@ -1750,10 +1747,12 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - if (!get_dirty_pages(inode)) - goto skip_flush; - - f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, + /* + * Should wait end_io to count F2FS_WB_CP_DATA correctly by + * f2fs_is_atomic_file. + */ + if (get_dirty_pages(inode)) + f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, "Unexpected flush for atomic writes: ino=%lu, npages=%u", inode->i_ino, get_dirty_pages(inode)); ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); @@ -1761,7 +1760,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); goto out; } -skip_flush: + set_inode_flag(inode, FI_ATOMIC_FILE); clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); @@ -1968,11 +1967,11 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) break; case F2FS_GOING_DOWN_NEED_FSCK: set_sbi_flag(sbi, SBI_NEED_FSCK); + set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); + set_sbi_flag(sbi, SBI_IS_DIRTY); /* do checkpoint only */ ret = f2fs_sync_fs(sb, 1); - if (ret) - goto out; - break; + goto out; default: ret = -EINVAL; goto out; @@ -1988,6 +1987,9 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) out: if (in != F2FS_GOING_DOWN_FULLSYNC) mnt_drop_write_file(filp); + + trace_f2fs_shutdown(sbi, in, ret); + return ret; } @@ -2871,8 +2873,8 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) __u32 pin; int ret = 0; - if (!inode_owner_or_capable(inode)) - return -EACCES; + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; if (get_user(pin, (__u32 __user *)arg)) return -EFAULT; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index d636cbcf68f2..bb6a152310ef 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -298,7 +298,7 @@ process_inline: clear_inode_flag(inode, FI_INLINE_DATA); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { - if (f2fs_truncate_blocks(inode, 0, false, false)) + if (f2fs_truncate_blocks(inode, 0, false)) return false; goto process_inline; } @@ -470,7 +470,7 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) return 0; punch_dentry_pages: truncate_inode_pages(&dir->i_data, 0); - f2fs_truncate_blocks(dir, 0, false, false); + f2fs_truncate_blocks(dir, 0, false); f2fs_remove_dirty_inode(dir); return err; } @@ -659,6 +659,12 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, if (IS_ERR(ipage)) return PTR_ERR(ipage); + /* + * f2fs_readdir was protected by inode.i_rwsem, it is safe to access + * ipage without page's lock held. + */ + unlock_page(ipage); + inline_dentry = inline_data_addr(inode, ipage); make_dentry_ptr_inline(inode, &d, inline_dentry); @@ -667,7 +673,7 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, if (!err) ctx->pos = d.max; - f2fs_put_page(ipage, 1); + f2fs_put_page(ipage, 0); return err < 0 ? err : 0; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index d910a820ae67..e7f2e8759315 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -14,6 +14,7 @@ #include "f2fs.h" #include "node.h" #include "segment.h" +#include "xattr.h" #include <trace/events/f2fs.h> @@ -248,6 +249,20 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) return false; } + if (f2fs_has_extra_attr(inode) && + f2fs_sb_has_flexible_inline_xattr(sbi) && + f2fs_has_inline_xattr(inode) && + (!fi->i_inline_xattr_size || + fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: inode (ino=%lx) has corrupted " + "i_inline_xattr_size: %d, max: %zu", + __func__, inode->i_ino, fi->i_inline_xattr_size, + MAX_INLINE_XATTR_SIZE); + return false; + } + if (F2FS_I(inode)->extent_tree) { struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest; diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index e967d27c1a89..f5e34e467003 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -10,6 +10,7 @@ #include <linux/pagemap.h> #include <linux/sched.h> #include <linux/ctype.h> +#include <linux/random.h> #include <linux/dcache.h> #include <linux/namei.h> #include <linux/quotaops.h> @@ -50,7 +51,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); F2FS_I(inode)->i_crtime = inode->i_mtime; - inode->i_generation = sbi->s_next_generation++; + inode->i_generation = prandom_u32(); if (S_ISDIR(inode->i_mode)) F2FS_I(inode)->i_current_depth = 1; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 4f450e573312..3f99ab288695 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1920,7 +1920,9 @@ static int f2fs_write_node_pages(struct address_space *mapping, f2fs_balance_fs_bg(sbi); /* collect a number of dirty node pages and write together */ - if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE)) + if (wbc->sync_mode != WB_SYNC_ALL && + get_pages(sbi, F2FS_DIRTY_NODES) < + nr_pages_to_skip(sbi, NODE)) goto skip_write; if (wbc->sync_mode == WB_SYNC_ALL) @@ -1959,7 +1961,7 @@ static int f2fs_set_node_page_dirty(struct page *page) if (!PageDirty(page)) { __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); return 1; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 9b79056d705d..aa7fe79b62b2 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -191,8 +191,7 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page) f2fs_trace_pid(page); - set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE); - SetPagePrivate(page); + f2fs_set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE); new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS); @@ -215,7 +214,8 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page) } static int __revoke_inmem_pages(struct inode *inode, - struct list_head *head, bool drop, bool recover) + struct list_head *head, bool drop, bool recover, + bool trylock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct inmem_pages *cur, *tmp; @@ -227,7 +227,16 @@ static int __revoke_inmem_pages(struct inode *inode, if (drop) trace_f2fs_commit_inmem_page(page, INMEM_DROP); - lock_page(page); + if (trylock) { + /* + * to avoid deadlock in between page lock and + * inmem_lock. + */ + if (!trylock_page(page)) + continue; + } else { + lock_page(page); + } f2fs_wait_on_page_writeback(page, DATA, true, true); @@ -270,8 +279,7 @@ next: ClearPageUptodate(page); clear_cold_data(page); } - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); f2fs_put_page(page, 1); list_del(&cur->list); @@ -318,13 +326,19 @@ void f2fs_drop_inmem_pages(struct inode *inode) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); - mutex_lock(&fi->inmem_lock); - __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); - spin_lock(&sbi->inode_lock[ATOMIC_FILE]); - if (!list_empty(&fi->inmem_ilist)) - list_del_init(&fi->inmem_ilist); - spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); - mutex_unlock(&fi->inmem_lock); + while (!list_empty(&fi->inmem_pages)) { + mutex_lock(&fi->inmem_lock); + __revoke_inmem_pages(inode, &fi->inmem_pages, + true, false, true); + + if (list_empty(&fi->inmem_pages)) { + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (!list_empty(&fi->inmem_ilist)) + list_del_init(&fi->inmem_ilist); + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + } + mutex_unlock(&fi->inmem_lock); + } clear_inode_flag(inode, FI_ATOMIC_FILE); fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0; @@ -354,8 +368,7 @@ void f2fs_drop_inmem_page(struct inode *inode, struct page *page) kmem_cache_free(inmem_entry_slab, cur); ClearPageUptodate(page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); f2fs_put_page(page, 0); trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE); @@ -429,12 +442,15 @@ retry: * recovery or rewrite & commit last transaction. For other * error number, revoking was done by filesystem itself. */ - err = __revoke_inmem_pages(inode, &revoke_list, false, true); + err = __revoke_inmem_pages(inode, &revoke_list, + false, true, false); /* drop all uncommitted pages */ - __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); + __revoke_inmem_pages(inode, &fi->inmem_pages, + true, false, false); } else { - __revoke_inmem_pages(inode, &revoke_list, false, false); + __revoke_inmem_pages(inode, &revoke_list, + false, false, false); } return err; @@ -542,9 +558,13 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) static int __submit_flush_wait(struct f2fs_sb_info *sbi, struct block_device *bdev) { - struct bio *bio = f2fs_bio_alloc(sbi, 0, true); + struct bio *bio; int ret; + bio = f2fs_bio_alloc(sbi, 0, false); + if (!bio) + return -ENOMEM; + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; bio_set_dev(bio, bdev); ret = submit_bio_wait(bio); @@ -868,6 +888,9 @@ int f2fs_disable_cp_again(struct f2fs_sb_info *sbi) if (holes[DATA] > ovp || holes[NODE] > ovp) return -EAGAIN; + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) && + dirty_segments(sbi) > overprovision_segments(sbi)) + return -EAGAIN; return 0; } @@ -1037,6 +1060,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi, dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST; dpolicy->io_aware_gran = MAX_PLIST_NUM; + dpolicy->timeout = 0; if (discard_type == DPOLICY_BG) { dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; @@ -1059,6 +1083,8 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi, } else if (discard_type == DPOLICY_UMOUNT) { dpolicy->max_requests = UINT_MAX; dpolicy->io_aware = false; + /* we need to issue all to keep CP_TRIMMED_FLAG */ + dpolicy->granularity = 1; } } @@ -1424,7 +1450,14 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi, int i, issued = 0; bool io_interrupted = false; + if (dpolicy->timeout != 0) + f2fs_update_time(sbi, dpolicy->timeout); + for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { + if (dpolicy->timeout != 0 && + f2fs_time_over(sbi, dpolicy->timeout)) + break; + if (i + 1 < dpolicy->granularity) break; @@ -1611,7 +1644,7 @@ void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi) } /* This comes from f2fs_put_super */ -bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi) +bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_policy dpolicy; @@ -1619,6 +1652,7 @@ bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi) __init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT, dcc->discard_granularity); + dpolicy.timeout = UMOUNT_DISCARD_TIMEOUT; __issue_discard_cmd(sbi, &dpolicy); dropped = __drop_discard_cmd(sbi); @@ -3164,10 +3198,10 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) stat_inc_inplace_blocks(fio->sbi); err = f2fs_submit_page_bio(fio); - if (!err) + if (!err) { update_device_state(fio); - - f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); + f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); + } return err; } diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index a77f76f528b6..5c7ed0442d6e 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -865,7 +865,7 @@ static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force) } } mutex_unlock(&dcc->cmd_lock); - if (!wakeup) + if (!wakeup || !is_idle(sbi, DISCARD_TIME)) return; wake_up: dcc->discard_wake = 1; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d1ccc52afc93..f2aaa2cc6b3e 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -269,7 +269,7 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype, if (!qname) { f2fs_msg(sb, KERN_ERR, "Not enough memory for storing quotafile name"); - return -EINVAL; + return -ENOMEM; } if (F2FS_OPTION(sbi).s_qf_names[qtype]) { if (strcmp(F2FS_OPTION(sbi).s_qf_names[qtype], qname) == 0) @@ -586,7 +586,7 @@ static int parse_options(struct super_block *sb, char *options) case Opt_io_size_bits: if (args->from && match_int(args, &arg)) return -EINVAL; - if (arg > __ilog2_u32(BIO_MAX_PAGES)) { + if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_PAGES)) { f2fs_msg(sb, KERN_WARNING, "Not support %d, larger than %d", 1 << arg, BIO_MAX_PAGES); @@ -821,6 +821,8 @@ static int parse_options(struct super_block *sb, char *options) } if (test_opt(sbi, INLINE_XATTR_SIZE)) { + int min_size, max_size; + if (!f2fs_sb_has_extra_attr(sbi) || !f2fs_sb_has_flexible_inline_xattr(sbi)) { f2fs_msg(sb, KERN_ERR, @@ -834,14 +836,15 @@ static int parse_options(struct super_block *sb, char *options) "set with inline_xattr option"); return -EINVAL; } - if (!F2FS_OPTION(sbi).inline_xattr_size || - F2FS_OPTION(sbi).inline_xattr_size >= - DEF_ADDRS_PER_INODE - - F2FS_TOTAL_EXTRA_ATTR_SIZE - - DEF_INLINE_RESERVED_SIZE - - DEF_MIN_INLINE_SIZE) { + + min_size = sizeof(struct f2fs_xattr_header) / sizeof(__le32); + max_size = MAX_INLINE_XATTR_SIZE; + + if (F2FS_OPTION(sbi).inline_xattr_size < min_size || + F2FS_OPTION(sbi).inline_xattr_size > max_size) { f2fs_msg(sb, KERN_ERR, - "inline xattr size is out of range"); + "inline xattr size is out of range: %d ~ %d", + min_size, max_size); return -EINVAL; } } @@ -915,6 +918,10 @@ static int f2fs_drop_inode(struct inode *inode) sb_start_intwrite(inode->i_sb); f2fs_i_size_write(inode, 0); + f2fs_submit_merged_write_cond(F2FS_I_SB(inode), + inode, NULL, 0, DATA); + truncate_inode_pages_final(inode->i_mapping); + if (F2FS_HAS_BLOCKS(inode)) f2fs_truncate(inode); @@ -1048,7 +1055,7 @@ static void f2fs_put_super(struct super_block *sb) } /* be sure to wait for any on-going discard commands */ - dropped = f2fs_wait_discard_bios(sbi); + dropped = f2fs_issue_discard_timeout(sbi); if ((f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) && !sbi->discard_blks && !dropped) { @@ -1075,7 +1082,10 @@ static void f2fs_put_super(struct super_block *sb) f2fs_bug_on(sbi, sbi->fsync_node_num); iput(sbi->node_inode); + sbi->node_inode = NULL; + iput(sbi->meta_inode); + sbi->meta_inode = NULL; /* * iput() can update stat information, if f2fs_write_checkpoint() @@ -1455,9 +1465,16 @@ static int f2fs_enable_quotas(struct super_block *sb); static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) { + unsigned int s_flags = sbi->sb->s_flags; struct cp_control cpc; - int err; + int err = 0; + int ret; + if (s_flags & SB_RDONLY) { + f2fs_msg(sbi->sb, KERN_ERR, + "checkpoint=disable on readonly fs"); + return -EINVAL; + } sbi->sb->s_flags |= SB_ACTIVE; f2fs_update_time(sbi, DISABLE_TIME); @@ -1465,18 +1482,24 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) while (!f2fs_time_over(sbi, DISABLE_TIME)) { mutex_lock(&sbi->gc_mutex); err = f2fs_gc(sbi, true, false, NULL_SEGNO); - if (err == -ENODATA) + if (err == -ENODATA) { + err = 0; break; + } if (err && err != -EAGAIN) - return err; + break; } - err = sync_filesystem(sbi->sb); - if (err) - return err; + ret = sync_filesystem(sbi->sb); + if (ret || err) { + err = ret ? ret: err; + goto restore_flag; + } - if (f2fs_disable_cp_again(sbi)) - return -EAGAIN; + if (f2fs_disable_cp_again(sbi)) { + err = -EAGAIN; + goto restore_flag; + } mutex_lock(&sbi->gc_mutex); cpc.reason = CP_PAUSE; @@ -1485,7 +1508,9 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) sbi->unusable_block_count = 0; mutex_unlock(&sbi->gc_mutex); - return 0; +restore_flag: + sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ + return err; } static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) @@ -2023,6 +2048,12 @@ void f2fs_quota_off_umount(struct super_block *sb) set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); } } + /* + * In case of checkpoint=disable, we must flush quota blocks. + * This can cause NULL exception for node_inode in end_io, since + * put_super already dropped it. + */ + sync_filesystem(sb); } static void f2fs_truncate_quota_inode_pages(struct super_block *sb) @@ -2703,6 +2734,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->interval_time[DISCARD_TIME] = DEF_IDLE_INTERVAL; sbi->interval_time[GC_TIME] = DEF_IDLE_INTERVAL; sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_INTERVAL; + sbi->interval_time[UMOUNT_DISCARD_TIMEOUT] = + DEF_UMOUNT_DISCARD_TIMEOUT; clear_sbi_flag(sbi, SBI_NEED_FSCK); for (i = 0; i < NR_COUNT_TYPE; i++) @@ -3022,10 +3055,11 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) struct f2fs_super_block *raw_super; struct inode *root; int err; - bool retry = true, need_fsck = false; + bool skip_recovery = false, need_fsck = false; char *options = NULL; int recovery, i, valid_super_block; struct curseg_info *seg_i; + int retry_cnt = 1; try_onemore: err = -EINVAL; @@ -3097,7 +3131,6 @@ try_onemore: sb->s_maxbytes = sbi->max_file_blocks << le32_to_cpu(raw_super->log_blocksize); sb->s_max_links = F2FS_LINK_MAX; - get_random_bytes(&sbi->s_next_generation, sizeof(u32)); #ifdef CONFIG_QUOTA sb->dq_op = &f2fs_quota_operations; @@ -3200,6 +3233,10 @@ try_onemore: if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_QUOTA_NEED_FSCK_FLAG)) set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_DISABLED_QUICK_FLAG)) { + set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); + sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_QUICK_INTERVAL; + } /* Initialize device list */ err = f2fs_scan_devices(sbi); @@ -3288,7 +3325,7 @@ try_onemore: sb->s_root = d_make_root(root); /* allocate root dentry */ if (!sb->s_root) { err = -ENOMEM; - goto free_root_inode; + goto free_node_inode; } err = f2fs_register_sysfs(sbi); @@ -3310,7 +3347,7 @@ try_onemore: goto free_meta; if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG))) - goto skip_recovery; + goto reset_checkpoint; /* recover fsynced data */ if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) { @@ -3327,11 +3364,13 @@ try_onemore: if (need_fsck) set_sbi_flag(sbi, SBI_NEED_FSCK); - if (!retry) - goto skip_recovery; + if (skip_recovery) + goto reset_checkpoint; err = f2fs_recover_fsync_data(sbi, false); if (err < 0) { + if (err != -ENOMEM) + skip_recovery = true; need_fsck = true; f2fs_msg(sb, KERN_ERR, "Cannot recover all fsync data errno=%d", err); @@ -3347,14 +3386,14 @@ try_onemore: goto free_meta; } } -skip_recovery: +reset_checkpoint: /* f2fs_recover_fsync_data() cleared this already */ clear_sbi_flag(sbi, SBI_POR_DOING); if (test_opt(sbi, DISABLE_CHECKPOINT)) { err = f2fs_disable_checkpoint(sbi); if (err) - goto free_meta; + goto sync_free_meta; } else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) { f2fs_enable_checkpoint(sbi); } @@ -3367,7 +3406,7 @@ skip_recovery: /* After POR, we can run background GC thread.*/ err = f2fs_start_gc_thread(sbi); if (err) - goto free_meta; + goto sync_free_meta; } kvfree(options); @@ -3387,8 +3426,14 @@ skip_recovery: cur_cp_version(F2FS_CKPT(sbi))); f2fs_update_time(sbi, CP_TIME); f2fs_update_time(sbi, REQ_TIME); + clear_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); return 0; +sync_free_meta: + /* safe to flush all the data */ + sync_filesystem(sbi->sb); + retry_cnt = 0; + free_meta: #ifdef CONFIG_QUOTA f2fs_truncate_quota_inode_pages(sb); @@ -3402,6 +3447,8 @@ free_meta: * falls into an infinite loop in f2fs_sync_meta_pages(). */ truncate_inode_pages_final(META_MAPPING(sbi)); + /* evict some inodes being cached by GC */ + evict_inodes(sb); f2fs_unregister_sysfs(sbi); free_root_inode: dput(sb->s_root); @@ -3410,6 +3457,7 @@ free_node_inode: f2fs_release_ino_entry(sbi, true); truncate_inode_pages_final(NODE_MAPPING(sbi)); iput(sbi->node_inode); + sbi->node_inode = NULL; free_stats: f2fs_destroy_stats(sbi); free_nm: @@ -3422,6 +3470,7 @@ free_devices: free_meta_inode: make_bad_inode(sbi->meta_inode); iput(sbi->meta_inode); + sbi->meta_inode = NULL; free_io_dummy: mempool_destroy(sbi->write_io_dummy); free_percpu: @@ -3443,8 +3492,8 @@ free_sbi: kvfree(sbi); /* give only one another chance */ - if (retry) { - retry = false; + if (retry_cnt > 0 && skip_recovery) { + retry_cnt--; shrink_dcache_sb(sb); goto try_onemore; } diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 70da6801c86f..729f46a3c9ee 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -222,6 +222,8 @@ out: #ifdef CONFIG_F2FS_FAULT_INJECTION if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX)) return -EINVAL; + if (a->struct_type == FAULT_INFO_RATE && t >= UINT_MAX) + return -EINVAL; #endif if (a->struct_type == RESERVED_BLOCKS) { spin_lock(&sbi->stat_lock); @@ -278,10 +280,16 @@ out: return count; } - *ui = t; - if (!strcmp(a->attr.name, "iostat_enable") && *ui == 0) - f2fs_reset_iostat(sbi); + if (!strcmp(a->attr.name, "iostat_enable")) { + sbi->iostat_enable = !!t; + if (!sbi->iostat_enable) + f2fs_reset_iostat(sbi); + return count; + } + + *ui = (unsigned int)t; + return count; } @@ -418,6 +426,8 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, discard_idle_interval, interval_time[DISCARD_TIME]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle_interval, interval_time[GC_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, + umount_discard_timeout, interval_time[UMOUNT_DISCARD_TIMEOUT]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold); @@ -475,6 +485,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(idle_interval), ATTR_LIST(discard_idle_interval), ATTR_LIST(gc_idle_interval), + ATTR_LIST(umount_discard_timeout), ATTR_LIST(iostat_enable), ATTR_LIST(readdir_ra), ATTR_LIST(gc_pin_file_thresh), diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c index ce2a5eb210b6..d0ab533a9ce8 100644 --- a/fs/f2fs/trace.c +++ b/fs/f2fs/trace.c @@ -14,7 +14,7 @@ #include "trace.h" static RADIX_TREE(pids, GFP_ATOMIC); -static struct mutex pids_lock; +static spinlock_t pids_lock; static struct last_io_info last_io; static inline void __print_last_io(void) @@ -58,23 +58,29 @@ void f2fs_trace_pid(struct page *page) set_page_private(page, (unsigned long)pid); +retry: if (radix_tree_preload(GFP_NOFS)) return; - mutex_lock(&pids_lock); + spin_lock(&pids_lock); p = radix_tree_lookup(&pids, pid); if (p == current) goto out; if (p) radix_tree_delete(&pids, pid); - f2fs_radix_tree_insert(&pids, pid, current); + if (radix_tree_insert(&pids, pid, current)) { + spin_unlock(&pids_lock); + radix_tree_preload_end(); + cond_resched(); + goto retry; + } trace_printk("%3x:%3x %4x %-16s\n", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), pid, current->comm); out: - mutex_unlock(&pids_lock); + spin_unlock(&pids_lock); radix_tree_preload_end(); } @@ -119,7 +125,7 @@ void f2fs_trace_ios(struct f2fs_io_info *fio, int flush) void f2fs_build_trace_ios(void) { - mutex_init(&pids_lock); + spin_lock_init(&pids_lock); } #define PIDVEC_SIZE 128 @@ -147,7 +153,7 @@ void f2fs_destroy_trace_ios(void) pid_t next_pid = 0; unsigned int found; - mutex_lock(&pids_lock); + spin_lock(&pids_lock); while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) { unsigned idx; @@ -155,5 +161,5 @@ void f2fs_destroy_trace_ios(void) for (idx = 0; idx < found; idx++) radix_tree_delete(&pids, pid[idx]); } - mutex_unlock(&pids_lock); + spin_unlock(&pids_lock); } diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 18d5ffbc5e8c..848a785abe25 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -224,11 +224,11 @@ static struct f2fs_xattr_entry *__find_inline_xattr(struct inode *inode, { struct f2fs_xattr_entry *entry; unsigned int inline_size = inline_xattr_size(inode); + void *max_addr = base_addr + inline_size; list_for_each_xattr(entry, base_addr) { - if ((void *)entry + sizeof(__u32) > base_addr + inline_size || - (void *)XATTR_NEXT_ENTRY(entry) + sizeof(__u32) > - base_addr + inline_size) { + if ((void *)entry + sizeof(__u32) > max_addr || + (void *)XATTR_NEXT_ENTRY(entry) > max_addr) { *last_addr = entry; return NULL; } @@ -239,6 +239,13 @@ static struct f2fs_xattr_entry *__find_inline_xattr(struct inode *inode, if (!memcmp(entry->e_name, name, len)) break; } + + /* inline xattr header or entry across max inline xattr size */ + if (IS_XATTR_LAST_ENTRY(entry) && + (void *)entry + sizeof(__u32) > max_addr) { + *last_addr = entry; + return NULL; + } return entry; } @@ -340,7 +347,7 @@ check: *base_addr = txattr_addr; return 0; out: - kzfree(txattr_addr); + kvfree(txattr_addr); return err; } @@ -383,7 +390,7 @@ static int read_all_xattrs(struct inode *inode, struct page *ipage, *base_addr = txattr_addr; return 0; fail: - kzfree(txattr_addr); + kvfree(txattr_addr); return err; } @@ -510,7 +517,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, } error = size; out: - kzfree(base_addr); + kvfree(base_addr); return error; } @@ -538,7 +545,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) if (!handler || (handler->list && !handler->list(dentry))) continue; - prefix = handler->prefix ?: handler->name; + prefix = xattr_prefix(handler); prefix_len = strlen(prefix); size = prefix_len + entry->e_name_len + 1; if (buffer) { @@ -556,7 +563,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) } error = buffer_size - rest; cleanup: - kzfree(base_addr); + kvfree(base_addr); return error; } @@ -687,7 +694,7 @@ static int __f2fs_setxattr(struct inode *inode, int index, if (!error && S_ISDIR(inode->i_mode)) set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP); exit: - kzfree(base_addr); + kvfree(base_addr); return error; } diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 67db134da0f5..9172ee082ca8 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -78,6 +78,12 @@ struct f2fs_xattr_entry { sizeof(struct f2fs_xattr_header) - \ sizeof(struct f2fs_xattr_entry)) +#define MAX_INLINE_XATTR_SIZE \ + (DEF_ADDRS_PER_INODE - \ + F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - \ + DEF_INLINE_RESERVED_SIZE - \ + MIN_INLINE_DENTRY_SIZE / sizeof(__le32)) + /* * On-disk structure of f2fs_xattr * We use inline xattrs space + 1 block for xattr. diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 8247bd1634cb..7066cd7c7aff 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1889,7 +1889,7 @@ lookup_again: atomic_read(&lo->plh_outstanding) != 0) { spin_unlock(&ino->i_lock); lseg = ERR_PTR(wait_var_event_killable(&lo->plh_outstanding, - atomic_read(&lo->plh_outstanding))); + !atomic_read(&lo->plh_outstanding))); if (IS_ERR(lseg) || !list_empty(&lo->plh_segs)) goto out_put_layout_hdr; pnfs_put_layout_hdr(lo); diff --git a/fs/proc/base.c b/fs/proc/base.c index f5ebdd87afb2..ddef482f1334 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3074,6 +3074,15 @@ static const struct file_operations proc_tgid_base_operations = { .llseek = generic_file_llseek, }; +struct pid *tgid_pidfd_to_pid(const struct file *file) +{ + if (!d_is_dir(file->f_path.dentry) || + (file->f_op != &proc_tgid_base_operations)) + return ERR_PTR(-EBADF); + + return proc_pid(file_inode(file)); +} + static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 4cb21b558a85..1b56686ab178 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -71,9 +71,11 @@ static int sysfs_init_fs_context(struct fs_context *fc) kfc->magic = SYSFS_MAGIC; fc->fs_private = kfc; fc->ops = &sysfs_fs_context_ops; - if (fc->user_ns) - put_user_ns(fc->user_ns); - fc->user_ns = get_user_ns(netns->user_ns); + if (netns) { + if (fc->user_ns) + put_user_ns(fc->user_ns); + fc->user_ns = get_user_ns(netns->user_ns); + } fc->global = true; return 0; } diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c index 9a3767818c50..9c2a0a13ed61 100644 --- a/fs/xfs/libxfs/xfs_dir2_leaf.c +++ b/fs/xfs/libxfs/xfs_dir2_leaf.c @@ -563,43 +563,40 @@ xfs_dir3_leaf_find_entry( */ int /* error */ xfs_dir2_leaf_addname( - xfs_da_args_t *args) /* operation arguments */ + struct xfs_da_args *args) /* operation arguments */ { + struct xfs_dir3_icleaf_hdr leafhdr; + struct xfs_trans *tp = args->trans; __be16 *bestsp; /* freespace table in leaf */ - int compact; /* need to compact leaves */ - xfs_dir2_data_hdr_t *hdr; /* data block header */ + __be16 *tagp; /* end of data entry */ struct xfs_buf *dbp; /* data block buffer */ - xfs_dir2_data_entry_t *dep; /* data block entry */ - xfs_inode_t *dp; /* incore directory inode */ - xfs_dir2_data_unused_t *dup; /* data unused entry */ + struct xfs_buf *lbp; /* leaf's buffer */ + struct xfs_dir2_leaf *leaf; /* leaf structure */ + struct xfs_inode *dp = args->dp; /* incore directory inode */ + struct xfs_dir2_data_hdr *hdr; /* data block header */ + struct xfs_dir2_data_entry *dep; /* data block entry */ + struct xfs_dir2_leaf_entry *lep; /* leaf entry table pointer */ + struct xfs_dir2_leaf_entry *ents; + struct xfs_dir2_data_unused *dup; /* data unused entry */ + struct xfs_dir2_leaf_tail *ltp; /* leaf tail pointer */ + struct xfs_dir2_data_free *bf; /* bestfree table */ + int compact; /* need to compact leaves */ int error; /* error return value */ int grown; /* allocated new data block */ - int highstale; /* index of next stale leaf */ + int highstale = 0; /* index of next stale leaf */ int i; /* temporary, index */ int index; /* leaf table position */ - struct xfs_buf *lbp; /* leaf's buffer */ - xfs_dir2_leaf_t *leaf; /* leaf structure */ int length; /* length of new entry */ - xfs_dir2_leaf_entry_t *lep; /* leaf entry table pointer */ int lfloglow; /* low leaf logging index */ int lfloghigh; /* high leaf logging index */ - int lowstale; /* index of prev stale leaf */ - xfs_dir2_leaf_tail_t *ltp; /* leaf tail pointer */ + int lowstale = 0; /* index of prev stale leaf */ int needbytes; /* leaf block bytes needed */ int needlog; /* need to log data header */ int needscan; /* need to rescan data free */ - __be16 *tagp; /* end of data entry */ - xfs_trans_t *tp; /* transaction pointer */ xfs_dir2_db_t use_block; /* data block number */ - struct xfs_dir2_data_free *bf; /* bestfree table */ - struct xfs_dir2_leaf_entry *ents; - struct xfs_dir3_icleaf_hdr leafhdr; trace_xfs_dir2_leaf_addname(args); - dp = args->dp; - tp = args->trans; - error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, -1, &lbp); if (error) return error; diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index 3b03703c5c3d..16731d2d684b 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -426,24 +426,22 @@ xfs_dir2_leaf_to_node( static int /* error */ xfs_dir2_leafn_add( struct xfs_buf *bp, /* leaf buffer */ - xfs_da_args_t *args, /* operation arguments */ + struct xfs_da_args *args, /* operation arguments */ int index) /* insertion pt for new entry */ { + struct xfs_dir3_icleaf_hdr leafhdr; + struct xfs_inode *dp = args->dp; + struct xfs_dir2_leaf *leaf = bp->b_addr; + struct xfs_dir2_leaf_entry *lep; + struct xfs_dir2_leaf_entry *ents; int compact; /* compacting stale leaves */ - xfs_inode_t *dp; /* incore directory inode */ - int highstale; /* next stale entry */ - xfs_dir2_leaf_t *leaf; /* leaf structure */ - xfs_dir2_leaf_entry_t *lep; /* leaf entry */ + int highstale = 0; /* next stale entry */ int lfloghigh; /* high leaf entry logging */ int lfloglow; /* low leaf entry logging */ - int lowstale; /* previous stale entry */ - struct xfs_dir3_icleaf_hdr leafhdr; - struct xfs_dir2_leaf_entry *ents; + int lowstale = 0; /* previous stale entry */ trace_xfs_dir2_leafn_add(args, index); - dp = args->dp; - leaf = bp->b_addr; dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf); ents = dp->d_ops->leaf_ents_p(leaf); |