diff options
Diffstat (limited to 'fs')
42 files changed, 669 insertions, 522 deletions
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 0fa95b198e6e..d48ff5f370f4 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -16,7 +16,6 @@ #include <linux/time.h> #include <linux/mm.h> #include <linux/mman.h> -#include <linux/a.out.h> #include <linux/errno.h> #include <linux/signal.h> #include <linux/binfmts.h> @@ -548,7 +547,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) struct { struct elfhdr elf_ex; struct elfhdr interp_elf_ex; - struct exec interp_ex; } *loc; loc = kmalloc(sizeof(*loc), GFP_KERNEL); @@ -680,7 +678,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) } /* Get the exec headers */ - loc->interp_ex = *((struct exec *)bprm->buf); loc->interp_elf_ex = *((struct elfhdr *)bprm->buf); break; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 470c10ceb0fb..10d8a0aa871a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -931,8 +931,16 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part) struct gendisk *disk; int ret; int part; + int perm = 0; - ret = devcgroup_inode_permission(bdev->bd_inode, file->f_mode); + if (file->f_mode & FMODE_READ) + perm |= MAY_READ; + if (file->f_mode & FMODE_WRITE) + perm |= MAY_WRITE; + /* + * hooks: /n/, see "layering violations". + */ + ret = devcgroup_inode_permission(bdev->bd_inode, perm); if (ret != 0) return ret; diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index 28e3d5c5fcac..1f3465201fdf 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -2,6 +2,11 @@ Version 1.53 ------------ DFS support added (Microsoft Distributed File System client support needed for referrals which enable a hierarchical name space among servers). +Disable temporary caching of mode bits to servers which do not support +storing of mode (e.g. Windows servers, when client mounts without cifsacl +mount option) and add new "dynperm" mount option to enable temporary caching +of mode (enable old behavior). Fix hang on mount caused when server crashes +tcp session during negotiate protocol. Version 1.52 ------------ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 5df93fd6303f..86b4d5f405ae 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -97,9 +97,6 @@ cifs_read_super(struct super_block *sb, void *data, { struct inode *inode; struct cifs_sb_info *cifs_sb; -#ifdef CONFIG_CIFS_DFS_UPCALL - int len; -#endif int rc = 0; /* BB should we make this contingent on mount parm? */ @@ -117,15 +114,17 @@ cifs_read_super(struct super_block *sb, void *data, * complex operation (mount), and in case of fail * just exit instead of doing mount and attempting * undo it if this copy fails?*/ - len = strlen(data); - cifs_sb->mountdata = kzalloc(len + 1, GFP_KERNEL); - if (cifs_sb->mountdata == NULL) { - kfree(sb->s_fs_info); - sb->s_fs_info = NULL; - return -ENOMEM; + if (data) { + int len = strlen(data); + cifs_sb->mountdata = kzalloc(len + 1, GFP_KERNEL); + if (cifs_sb->mountdata == NULL) { + kfree(sb->s_fs_info); + sb->s_fs_info = NULL; + return -ENOMEM; + } + strncpy(cifs_sb->mountdata, data, len + 1); + cifs_sb->mountdata[len] = '\0'; } - strncpy(cifs_sb->mountdata, data, len + 1); - cifs_sb->mountdata[len] = '\0'; #endif rc = cifs_mount(sb, cifs_sb, data, devname); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 08914053242b..9cfcf326ead3 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -333,7 +333,6 @@ struct cifsFileInfo { bool messageMode:1; /* for pipes: message vs byte mode */ atomic_t wrtPending; /* handle in use - defer close */ struct semaphore fh_sem; /* prevents reopen race after dead ses*/ - char *search_resume_name; /* BB removeme BB */ struct cifs_search_info srch_inf; }; @@ -626,7 +625,7 @@ GLOBAL_EXTERN atomic_t tcpSesAllocCount; GLOBAL_EXTERN atomic_t tcpSesReconnectCount; GLOBAL_EXTERN atomic_t tconInfoReconnectCount; -/* Various Debug counters to remove someday (BB) */ +/* Various Debug counters */ GLOBAL_EXTERN atomic_t bufAllocCount; /* current number allocated */ #ifdef CONFIG_CIFS_STATS2 GLOBAL_EXTERN atomic_t totBufAllocCount; /* total allocated over all time */ diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 65d58b4e6a61..0f327c224da3 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -79,6 +79,19 @@ #define TRANS2_GET_DFS_REFERRAL 0x10 #define TRANS2_REPORT_DFS_INCOSISTENCY 0x11 +/* SMB Transact (Named Pipe) subcommand codes */ +#define TRANS_SET_NMPIPE_STATE 0x0001 +#define TRANS_RAW_READ_NMPIPE 0x0011 +#define TRANS_QUERY_NMPIPE_STATE 0x0021 +#define TRANS_QUERY_NMPIPE_INFO 0x0022 +#define TRANS_PEEK_NMPIPE 0x0023 +#define TRANS_TRANSACT_NMPIPE 0x0026 +#define TRANS_RAW_WRITE_NMPIPE 0x0031 +#define TRANS_READ_NMPIPE 0x0036 +#define TRANS_WRITE_NMPIPE 0x0037 +#define TRANS_WAIT_NMPIPE 0x0053 +#define TRANS_CALL_NMPIPE 0x0054 + /* NT Transact subcommand codes */ #define NT_TRANSACT_CREATE 0x01 #define NT_TRANSACT_IOCTL 0x02 @@ -328,12 +341,13 @@ #define CREATE_COMPLETE_IF_OPLK 0x00000100 /* should be zero */ #define CREATE_NO_EA_KNOWLEDGE 0x00000200 #define CREATE_EIGHT_DOT_THREE 0x00000400 /* doc says this is obsolete - open for recovery flag - should - be zero */ + "open for recovery" flag - should + be zero in any case */ +#define CREATE_OPEN_FOR_RECOVERY 0x00000400 #define CREATE_RANDOM_ACCESS 0x00000800 #define CREATE_DELETE_ON_CLOSE 0x00001000 #define CREATE_OPEN_BY_ID 0x00002000 -#define CREATE_OPEN_BACKUP_INTN 0x00004000 +#define CREATE_OPEN_BACKUP_INTENT 0x00004000 #define CREATE_NO_COMPRESSION 0x00008000 #define CREATE_RESERVE_OPFILTER 0x00100000 /* should be zero */ #define OPEN_REPARSE_POINT 0x00200000 @@ -722,7 +736,6 @@ typedef struct smb_com_tconx_rsp_ext { #define SMB_CSC_CACHE_AUTO_REINT 0x0004 #define SMB_CSC_CACHE_VDO 0x0008 #define SMB_CSC_NO_CACHING 0x000C - #define SMB_UNIQUE_FILE_NAME 0x0010 #define SMB_EXTENDED_SIGNATURES 0x0020 @@ -806,7 +819,7 @@ typedef struct smb_com_findclose_req { #define ICOUNT_MASK 0x00FF #define PIPE_READ_MODE 0x0100 #define NAMED_PIPE_TYPE 0x0400 -#define PIPE_END_POINT 0x0800 +#define PIPE_END_POINT 0x4000 #define BLOCKING_NAMED_PIPE 0x8000 typedef struct smb_com_open_req { /* also handles create */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index fb655b4593c6..4511b708f0f3 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1728,7 +1728,7 @@ CIFSSMBLock(const int xid, struct cifsTconInfo *tcon, { int rc = 0; LOCK_REQ *pSMB = NULL; - LOCK_RSP *pSMBr = NULL; +/* LOCK_RSP *pSMBr = NULL; */ /* No response data other than rc to parse */ int bytes_returned; int timeout = 0; __u16 count; @@ -1739,8 +1739,6 @@ CIFSSMBLock(const int xid, struct cifsTconInfo *tcon, if (rc) return rc; - pSMBr = (LOCK_RSP *)pSMB; /* BB removeme BB */ - if (lockType == LOCKING_ANDX_OPLOCK_RELEASE) { timeout = CIFS_ASYNC_OP; /* no response expected */ pSMB->Timeout = 0; @@ -1774,7 +1772,7 @@ CIFSSMBLock(const int xid, struct cifsTconInfo *tcon, if (waitFlag) { rc = SendReceiveBlockingLock(xid, tcon, (struct smb_hdr *) pSMB, - (struct smb_hdr *) pSMBr, &bytes_returned); + (struct smb_hdr *) pSMB, &bytes_returned); cifs_small_buf_release(pSMB); } else { rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *)pSMB, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 023434f72c15..e8fa46c7cff2 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -653,6 +653,7 @@ multi_t2_fnd: spin_lock(&GlobalMid_Lock); server->tcpStatus = CifsExiting; spin_unlock(&GlobalMid_Lock); + wake_up_all(&server->response_q); /* don't exit until kthread_stop is called */ set_current_state(TASK_UNINTERRUPTIBLE); @@ -2120,6 +2121,10 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DIRECT_IO; } + if ((volume_info.cifs_acl) && (volume_info.dynperm)) + cERROR(1, ("mount option dynperm ignored if cifsacl " + "mount option supported")); + tcon = find_unc(sin_server.sin_addr.s_addr, volume_info.UNC, volume_info.username); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index f0b5b5f3dd2e..fb69c1fa85c9 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -260,7 +260,9 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, buf, inode->i_sb, xid, &fileHandle); if (newinode) { - newinode->i_mode = mode; + if (cifs_sb->mnt_cifs_flags & + CIFS_MOUNT_DYNPERM) + newinode->i_mode = mode; if ((oplock & CIFS_CREATE_ACTION) && (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 8636cec2642c..0aac824371a5 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -546,7 +546,6 @@ int cifs_close(struct inode *inode, struct file *file) msleep(timeout); timeout *= 8; } - kfree(pSMBFile->search_resume_name); kfree(file->private_data); file->private_data = NULL; } else @@ -605,12 +604,6 @@ int cifs_closedir(struct inode *inode, struct file *file) else cifs_buf_release(ptmp); } - ptmp = pCFileStruct->search_resume_name; - if (ptmp) { - cFYI(1, ("closedir free resume name")); - pCFileStruct->search_resume_name = NULL; - kfree(ptmp); - } kfree(file->private_data); file->private_data = NULL; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 129dbfe4dca7..722be543ceec 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -418,6 +418,7 @@ int cifs_get_inode_info(struct inode **pinode, char *buf = NULL; bool adjustTZ = false; bool is_dfs_referral = false; + umode_t default_mode; pTcon = cifs_sb->tcon; cFYI(1, ("Getting info on %s", full_path)); @@ -530,47 +531,42 @@ int cifs_get_inode_info(struct inode **pinode, inode->i_mtime.tv_sec += pTcon->ses->server->timeAdj; } - /* set default mode. will override for dirs below */ - if (atomic_read(&cifsInfo->inUse) == 0) - /* new inode, can safely set these fields */ - inode->i_mode = cifs_sb->mnt_file_mode; - else /* since we set the inode type below we need to mask off - to avoid strange results if type changes and both - get orred in */ - inode->i_mode &= ~S_IFMT; -/* if (attr & ATTR_REPARSE) */ - /* We no longer handle these as symlinks because we could not - follow them due to the absolute path with drive letter */ - if (attr & ATTR_DIRECTORY) { - /* override default perms since we do not do byte range locking - on dirs */ - inode->i_mode = cifs_sb->mnt_dir_mode; - inode->i_mode |= S_IFDIR; - } else if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) && - (cifsInfo->cifsAttrs & ATTR_SYSTEM) && - /* No need to le64 convert size of zero */ - (pfindData->EndOfFile == 0)) { - inode->i_mode = cifs_sb->mnt_file_mode; - inode->i_mode |= S_IFIFO; -/* BB Finish for SFU style symlinks and devices */ - } else if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) && - (cifsInfo->cifsAttrs & ATTR_SYSTEM)) { - if (decode_sfu_inode(inode, le64_to_cpu(pfindData->EndOfFile), - full_path, cifs_sb, xid)) - cFYI(1, ("Unrecognized sfu inode type")); - - cFYI(1, ("sfu mode 0%o", inode->i_mode)); + /* get default inode mode */ + if (attr & ATTR_DIRECTORY) + default_mode = cifs_sb->mnt_dir_mode; + else + default_mode = cifs_sb->mnt_file_mode; + + /* set permission bits */ + if (atomic_read(&cifsInfo->inUse) == 0 || + (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0) + inode->i_mode = default_mode; + else { + /* just reenable write bits if !ATTR_READONLY */ + if ((inode->i_mode & S_IWUGO) == 0 && + (attr & ATTR_READONLY) == 0) + inode->i_mode |= (S_IWUGO & default_mode); + inode->i_mode &= ~S_IFMT; + } + /* clear write bits if ATTR_READONLY is set */ + if (attr & ATTR_READONLY) + inode->i_mode &= ~S_IWUGO; + + /* set inode type */ + if ((attr & ATTR_SYSTEM) && + (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) { + /* no need to fix endianness on 0 */ + if (pfindData->EndOfFile == 0) + inode->i_mode |= S_IFIFO; + else if (decode_sfu_inode(inode, + le64_to_cpu(pfindData->EndOfFile), + full_path, cifs_sb, xid)) + cFYI(1, ("unknown SFU file type\n")); } else { - inode->i_mode |= S_IFREG; - /* treat dos attribute of read-only as read-only mode eg 555 */ - if (cifsInfo->cifsAttrs & ATTR_READONLY) - inode->i_mode &= ~(S_IWUGO); - else if ((inode->i_mode & S_IWUGO) == 0) - /* the ATTR_READONLY flag may have been */ - /* changed on server -- set any w bits */ - /* allowed by mnt_file_mode */ - inode->i_mode |= (S_IWUGO & cifs_sb->mnt_file_mode); - /* BB add code to validate if device or weird share or device type? */ + if (attr & ATTR_DIRECTORY) + inode->i_mode |= S_IFDIR; + else + inode->i_mode |= S_IFREG; } spin_lock(&inode->i_lock); @@ -1019,8 +1015,11 @@ mkdir_get_info: CIFS_MOUNT_MAP_SPECIAL_CHR); } if (direntry->d_inode) { - direntry->d_inode->i_mode = mode; - direntry->d_inode->i_mode |= S_IFDIR; + if (cifs_sb->mnt_cifs_flags & + CIFS_MOUNT_DYNPERM) + direntry->d_inode->i_mode = + (mode | S_IFDIR); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { direntry->d_inode->i_uid = @@ -1547,13 +1546,26 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) } else goto cifs_setattr_exit; } - if (attrs->ia_valid & ATTR_UID) { - cFYI(1, ("UID changed to %d", attrs->ia_uid)); - uid = attrs->ia_uid; - } - if (attrs->ia_valid & ATTR_GID) { - cFYI(1, ("GID changed to %d", attrs->ia_gid)); - gid = attrs->ia_gid; + + /* + * Without unix extensions we can't send ownership changes to the + * server, so silently ignore them. This is consistent with how + * local DOS/Windows filesystems behave (VFAT, NTFS, etc). With + * CIFSACL support + proper Windows to Unix idmapping, we may be + * able to support this in the future. + */ + if (!pTcon->unix_ext && + !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) { + attrs->ia_valid &= ~(ATTR_UID | ATTR_GID); + } else { + if (attrs->ia_valid & ATTR_UID) { + cFYI(1, ("UID changed to %d", attrs->ia_uid)); + uid = attrs->ia_uid; + } + if (attrs->ia_valid & ATTR_GID) { + cFYI(1, ("GID changed to %d", attrs->ia_gid)); + gid = attrs->ia_gid; + } } time_buf.Attributes = 0; @@ -1563,7 +1575,7 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) attrs->ia_valid &= ~ATTR_MODE; if (attrs->ia_valid & ATTR_MODE) { - cFYI(1, ("Mode changed to 0x%x", attrs->ia_mode)); + cFYI(1, ("Mode changed to 0%o", attrs->ia_mode)); mode = attrs->ia_mode; } @@ -1578,18 +1590,18 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) #ifdef CONFIG_CIFS_EXPERIMENTAL if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) rc = mode_to_acl(inode, full_path, mode); - else if ((mode & S_IWUGO) == 0) { -#else - if ((mode & S_IWUGO) == 0) { + else #endif - /* not writeable */ - if ((cifsInode->cifsAttrs & ATTR_READONLY) == 0) { - set_dosattr = true; - time_buf.Attributes = - cpu_to_le32(cifsInode->cifsAttrs | - ATTR_READONLY); - } - } else if (cifsInode->cifsAttrs & ATTR_READONLY) { + if (((mode & S_IWUGO) == 0) && + (cifsInode->cifsAttrs & ATTR_READONLY) == 0) { + set_dosattr = true; + time_buf.Attributes = cpu_to_le32(cifsInode->cifsAttrs | + ATTR_READONLY); + /* fix up mode if we're not using dynperm */ + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0) + attrs->ia_mode = inode->i_mode & ~S_IWUGO; + } else if ((mode & S_IWUGO) && + (cifsInode->cifsAttrs & ATTR_READONLY)) { /* If file is readonly on server, we would not be able to write to it - so if any write bit is enabled for user or group or other we @@ -1600,6 +1612,20 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) /* Windows ignores set to zero */ if (time_buf.Attributes == 0) time_buf.Attributes |= cpu_to_le32(ATTR_NORMAL); + + /* reset local inode permissions to normal */ + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) { + attrs->ia_mode &= ~(S_IALLUGO); + if (S_ISDIR(inode->i_mode)) + attrs->ia_mode |= + cifs_sb->mnt_dir_mode; + else + attrs->ia_mode |= + cifs_sb->mnt_file_mode; + } + } else if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) { + /* ignore mode change - ATTR_READONLY hasn't changed */ + attrs->ia_valid &= ~ATTR_MODE; } } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 1d69b8014e0b..4b17f8fe3157 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -519,8 +519,7 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv) pnotify = (struct file_notify_information *) ((char *)&pSMBr->hdr.Protocol + data_offset); cFYI(1, ("dnotify on %s Action: 0x%x", - pnotify->FileName, - pnotify->Action)); /* BB removeme BB */ + pnotify->FileName, pnotify->Action)); /* cifs_dump_mem("Rcvd notify Data: ",buf, sizeof(struct smb_hdr)+60); */ return true; diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 713c25110197..83f306954883 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -132,6 +132,7 @@ static void fill_in_inode(struct inode *tmp_inode, int new_buf_type, __u32 attr; __u64 allocation_size; __u64 end_of_file; + umode_t default_mode; /* save mtime and size */ local_mtime = tmp_inode->i_mtime; @@ -187,48 +188,54 @@ static void fill_in_inode(struct inode *tmp_inode, int new_buf_type, if (atomic_read(&cifsInfo->inUse) == 0) { tmp_inode->i_uid = cifs_sb->mnt_uid; tmp_inode->i_gid = cifs_sb->mnt_gid; - /* set default mode. will override for dirs below */ - tmp_inode->i_mode = cifs_sb->mnt_file_mode; - } else { - /* mask off the type bits since it gets set - below and we do not want to get two type - bits set */ + } + + if (attr & ATTR_DIRECTORY) + default_mode = cifs_sb->mnt_dir_mode; + else + default_mode = cifs_sb->mnt_file_mode; + + /* set initial permissions */ + if ((atomic_read(&cifsInfo->inUse) == 0) || + (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0) + tmp_inode->i_mode = default_mode; + else { + /* just reenable write bits if !ATTR_READONLY */ + if ((tmp_inode->i_mode & S_IWUGO) == 0 && + (attr & ATTR_READONLY) == 0) + tmp_inode->i_mode |= (S_IWUGO & default_mode); + tmp_inode->i_mode &= ~S_IFMT; } - if (attr & ATTR_DIRECTORY) { - *pobject_type = DT_DIR; - /* override default perms since we do not lock dirs */ - if (atomic_read(&cifsInfo->inUse) == 0) - tmp_inode->i_mode = cifs_sb->mnt_dir_mode; - tmp_inode->i_mode |= S_IFDIR; - } else if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) && - (attr & ATTR_SYSTEM)) { + /* clear write bits if ATTR_READONLY is set */ + if (attr & ATTR_READONLY) + tmp_inode->i_mode &= ~S_IWUGO; + + /* set inode type */ + if ((attr & ATTR_SYSTEM) && + (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) { if (end_of_file == 0) { - *pobject_type = DT_FIFO; tmp_inode->i_mode |= S_IFIFO; + *pobject_type = DT_FIFO; } else { - /* rather than get the type here, we mark the - inode as needing revalidate and get the real type - (blk vs chr vs. symlink) later ie in lookup */ - *pobject_type = DT_REG; + /* + * trying to get the type can be slow, so just call + * this a regular file for now, and mark for reval + */ tmp_inode->i_mode |= S_IFREG; + *pobject_type = DT_REG; cifsInfo->time = 0; } -/* we no longer mark these because we could not follow them */ -/* } else if (attr & ATTR_REPARSE) { - *pobject_type = DT_LNK; - tmp_inode->i_mode |= S_IFLNK; */ } else { - *pobject_type = DT_REG; - tmp_inode->i_mode |= S_IFREG; - if (attr & ATTR_READONLY) - tmp_inode->i_mode &= ~(S_IWUGO); - else if ((tmp_inode->i_mode & S_IWUGO) == 0) - /* the ATTR_READONLY flag may have been changed on */ - /* server -- set any w bits allowed by mnt_file_mode */ - tmp_inode->i_mode |= (S_IWUGO & cifs_sb->mnt_file_mode); - } /* could add code here - to validate if device or weird share type? */ + if (attr & ATTR_DIRECTORY) { + tmp_inode->i_mode |= S_IFDIR; + *pobject_type = DT_DIR; + } else { + tmp_inode->i_mode |= S_IFREG; + *pobject_type = DT_REG; + } + } /* can not fill in nlink here as in qpathinfo version and Unx search */ if (atomic_read(&cifsInfo->inUse) == 0) @@ -675,8 +682,6 @@ static int find_cifs_entry(const int xid, struct cifsTconInfo *pTcon, cifsFile->invalidHandle = true; CIFSFindClose(xid, pTcon, cifsFile->netfid); } - kfree(cifsFile->search_resume_name); - cifsFile->search_resume_name = NULL; if (cifsFile->srch_inf.ntwrk_buf_start) { cFYI(1, ("freeing SMB ff cache buf on search rewind")); if (cifsFile->srch_inf.smallBuf) @@ -1043,9 +1048,7 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir) } /* else { cifsFile->invalidHandle = true; CIFSFindClose(xid, pTcon, cifsFile->netfid); - } - kfree(cifsFile->search_resume_name); - cifsFile->search_resume_name = NULL; */ + } */ rc = find_cifs_entry(xid, pTcon, file, ¤t_entry, &num_to_fill); diff --git a/fs/dcache.c b/fs/dcache.c index 3ee588d5f585..6068c25b393c 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -17,6 +17,7 @@ #include <linux/syscalls.h> #include <linux/string.h> #include <linux/mm.h> +#include <linux/fdtable.h> #include <linux/fs.h> #include <linux/fsnotify.h> #include <linux/slab.h> @@ -106,9 +107,10 @@ static void dentry_lru_remove(struct dentry *dentry) /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. - * Called with dcache_lock and per dentry lock held, drops both. */ static void dentry_iput(struct dentry * dentry) + __releases(dentry->d_lock) + __releases(dcache_lock) { struct inode *inode = dentry->d_inode; if (inode) { @@ -132,12 +134,13 @@ static void dentry_iput(struct dentry * dentry) * d_kill - kill dentry and return parent * @dentry: dentry to kill * - * Called with dcache_lock and d_lock, releases both. The dentry must - * already be unhashed and removed from the LRU. + * The dentry must already be unhashed and removed from the LRU. * * If this is the root of the dentry tree, return NULL. */ static struct dentry *d_kill(struct dentry *dentry) + __releases(dentry->d_lock) + __releases(dcache_lock) { struct dentry *parent; @@ -383,11 +386,11 @@ restart: * Try to prune ancestors as well. This is necessary to prevent * quadratic behavior of shrink_dcache_parent(), but is also expected * to be beneficial in reducing dentry cache fragmentation. - * - * Called with dcache_lock, drops it and then regains. - * Called with dentry->d_lock held, drops it. */ static void prune_one_dentry(struct dentry * dentry) + __releases(dentry->d_lock) + __releases(dcache_lock) + __acquires(dcache_lock) { __d_drop(dentry); dentry = d_kill(dentry); @@ -1604,10 +1607,9 @@ static int d_isparent(struct dentry *p1, struct dentry *p2) * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... - * - * On return, dcache_lock will have been unlocked. */ static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias) + __releases(dcache_lock) { struct mutex *m1 = NULL, *m2 = NULL; struct dentry *ret; @@ -1743,11 +1745,9 @@ out_nolock: shouldnt_be_hashed: spin_unlock(&dcache_lock); BUG(); - goto shouldnt_be_hashed; } -static int prepend(char **buffer, int *buflen, const char *str, - int namelen) +static int prepend(char **buffer, int *buflen, const char *str, int namelen) { *buflen -= namelen; if (*buflen < 0) @@ -1757,8 +1757,13 @@ static int prepend(char **buffer, int *buflen, const char *str, return 0; } +static int prepend_name(char **buffer, int *buflen, struct qstr *name) +{ + return prepend(buffer, buflen, name->name, name->len); +} + /** - * d_path - return the path of a dentry + * __d_path - return the path of a dentry * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry (may be modified by this function) * @buffer: buffer to return value in @@ -1779,9 +1784,10 @@ char *__d_path(const struct path *path, struct path *root, { struct dentry *dentry = path->dentry; struct vfsmount *vfsmnt = path->mnt; - char * end = buffer+buflen; - char * retval; + char *end = buffer + buflen; + char *retval; + spin_lock(&vfsmount_lock); prepend(&end, &buflen, "\0", 1); if (!IS_ROOT(dentry) && d_unhashed(dentry) && (prepend(&end, &buflen, " (deleted)", 10) != 0)) @@ -1800,38 +1806,37 @@ char *__d_path(const struct path *path, struct path *root, break; if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) { /* Global root? */ - spin_lock(&vfsmount_lock); if (vfsmnt->mnt_parent == vfsmnt) { - spin_unlock(&vfsmount_lock); goto global_root; } dentry = vfsmnt->mnt_mountpoint; vfsmnt = vfsmnt->mnt_parent; - spin_unlock(&vfsmount_lock); continue; } parent = dentry->d_parent; prefetch(parent); - if ((prepend(&end, &buflen, dentry->d_name.name, - dentry->d_name.len) != 0) || + if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) || (prepend(&end, &buflen, "/", 1) != 0)) goto Elong; retval = end; dentry = parent; } +out: + spin_unlock(&vfsmount_lock); return retval; global_root: retval += 1; /* hit the slash */ - if (prepend(&retval, &buflen, dentry->d_name.name, - dentry->d_name.len) != 0) + if (prepend_name(&retval, &buflen, &dentry->d_name) != 0) goto Elong; root->mnt = vfsmnt; root->dentry = dentry; - return retval; + goto out; + Elong: - return ERR_PTR(-ENAMETOOLONG); + retval = ERR_PTR(-ENAMETOOLONG); + goto out; } /** @@ -1845,9 +1850,9 @@ Elong: * * Returns the buffer or an error code if the path was too long. * - * "buflen" should be positive. Caller holds the dcache_lock. + * "buflen" should be positive. */ -char *d_path(struct path *path, char *buf, int buflen) +char *d_path(const struct path *path, char *buf, int buflen) { char *res; struct path root; @@ -1915,16 +1920,11 @@ char *dentry_path(struct dentry *dentry, char *buf, int buflen) retval = end-1; *retval = '/'; - for (;;) { - struct dentry *parent; - if (IS_ROOT(dentry)) - break; + while (!IS_ROOT(dentry)) { + struct dentry *parent = dentry->d_parent; - parent = dentry->d_parent; prefetch(parent); - - if ((prepend(&end, &buflen, dentry->d_name.name, - dentry->d_name.len) != 0) || + if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) || (prepend(&end, &buflen, "/", 1) != 0)) goto Elong; @@ -1975,7 +1975,7 @@ asmlinkage long sys_getcwd(char __user *buf, unsigned long size) error = -ENOENT; /* Has the current directory has been unlinked? */ spin_lock(&dcache_lock); - if (pwd.dentry->d_parent == pwd.dentry || !d_unhashed(pwd.dentry)) { + if (IS_ROOT(pwd.dentry) || !d_unhashed(pwd.dentry)) { unsigned long len; struct path tmp = root; char * cwd; diff --git a/fs/exec.c b/fs/exec.c index 9448f1b50b4a..da94a6f05df3 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -26,7 +26,6 @@ #include <linux/file.h> #include <linux/fdtable.h> #include <linux/mman.h> -#include <linux/a.out.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/smp_lock.h> @@ -61,6 +60,11 @@ #include <linux/kmod.h> #endif +#ifdef __alpha__ +/* for /sbin/loader handling in search_binary_handler() */ +#include <linux/a.out.h> +#endif + int core_uses_pid; char core_pattern[CORENAME_MAX_SIZE] = "core"; int suid_dumpable = 0; @@ -1155,7 +1159,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) { int try,retval; struct linux_binfmt *fmt; -#if defined(__alpha__) && defined(CONFIG_ARCH_SUPPORTS_AOUT) +#ifdef __alpha__ /* handle /sbin/loader.. */ { struct exec * eh = (struct exec *) bprm->buf; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 30494c5da843..9cc80b9cc8d8 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -43,6 +43,46 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, } +static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block, + ext4_group_t block_group) +{ + ext4_group_t actual_group; + ext4_get_group_no_and_offset(sb, block, &actual_group, 0); + if (actual_group == block_group) + return 1; + return 0; +} + +static int ext4_group_used_meta_blocks(struct super_block *sb, + ext4_group_t block_group) +{ + ext4_fsblk_t tmp; + struct ext4_sb_info *sbi = EXT4_SB(sb); + /* block bitmap, inode bitmap, and inode table blocks */ + int used_blocks = sbi->s_itb_per_group + 2; + + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { + struct ext4_group_desc *gdp; + struct buffer_head *bh; + + gdp = ext4_get_group_desc(sb, block_group, &bh); + if (!ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), + block_group)) + used_blocks--; + + if (!ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), + block_group)) + used_blocks--; + + tmp = ext4_inode_table(sb, gdp); + for (; tmp < ext4_inode_table(sb, gdp) + + sbi->s_itb_per_group; tmp++) { + if (!ext4_block_in_group(sb, tmp, block_group)) + used_blocks -= 1; + } + } + return used_blocks; +} /* Initializes an uninitialized block bitmap if given, and returns the * number of blocks free in the group. */ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, @@ -105,20 +145,34 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, free_blocks = group_blocks - bit_max; if (bh) { - ext4_fsblk_t start; + ext4_fsblk_t start, tmp; + int flex_bg = 0; for (bit = 0; bit < bit_max; bit++) ext4_set_bit(bit, bh->b_data); start = ext4_group_first_block_no(sb, block_group); - /* Set bits for block and inode bitmaps, and inode table */ - ext4_set_bit(ext4_block_bitmap(sb, gdp) - start, bh->b_data); - ext4_set_bit(ext4_inode_bitmap(sb, gdp) - start, bh->b_data); - for (bit = (ext4_inode_table(sb, gdp) - start), - bit_max = bit + sbi->s_itb_per_group; bit < bit_max; bit++) - ext4_set_bit(bit, bh->b_data); + if (EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_FLEX_BG)) + flex_bg = 1; + /* Set bits for block and inode bitmaps, and inode table */ + tmp = ext4_block_bitmap(sb, gdp); + if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) + ext4_set_bit(tmp - start, bh->b_data); + + tmp = ext4_inode_bitmap(sb, gdp); + if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) + ext4_set_bit(tmp - start, bh->b_data); + + tmp = ext4_inode_table(sb, gdp); + for (; tmp < ext4_inode_table(sb, gdp) + + sbi->s_itb_per_group; tmp++) { + if (!flex_bg || + ext4_block_in_group(sb, tmp, block_group)) + ext4_set_bit(tmp - start, bh->b_data); + } /* * Also if the number of blocks within the group is * less than the blocksize * 8 ( which is the size @@ -126,8 +180,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, */ mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data); } - - return free_blocks - sbi->s_itb_per_group - 2; + return free_blocks - ext4_group_used_meta_blocks(sb, block_group); } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 873ad9b3418c..c9900aade150 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2745,8 +2745,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, sbi = EXT4_SB(sb); es = sbi->s_es; - ext4_debug("using block group %lu(%d)\n", ac->ac_b_ex.fe_group, - gdp->bg_free_blocks_count); err = -EIO; bitmap_bh = read_block_bitmap(sb, ac->ac_b_ex.fe_group); @@ -2762,6 +2760,9 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, if (!gdp) goto out_err; + ext4_debug("using block group %lu(%d)\n", ac->ac_b_ex.fe_group, + gdp->bg_free_blocks_count); + err = ext4_journal_get_write_access(handle, gdp_bh); if (err) goto out_err; @@ -3094,8 +3095,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { - unsigned len = ac->ac_o_ex.fe_len; - + unsigned int len = ac->ac_o_ex.fe_len; ext4_get_group_no_and_offset(ac->ac_sb, pa->pa_pstart, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 9f086a6a472b..9ff7b1c04239 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -563,7 +563,8 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, } blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count; - data = (__le32 *)dind->b_data + EXT4_SB(sb)->s_gdb_count; + data = (__le32 *)dind->b_data + (EXT4_SB(sb)->s_gdb_count % + EXT4_ADDR_PER_BLOCK(sb)); end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb); /* Get each reserved primary GDT block and verify it holds backups */ @@ -854,7 +855,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) */ /* Update group descriptor block for new group */ - gdp = (struct ext4_group_desc *)primary->b_data + gdb_off; + gdp = (struct ext4_group_desc *)((char *)primary->b_data + + gdb_off * EXT4_DESC_SIZE(sb)); ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */ ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 09d9359c8055..cb96f127c366 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -671,6 +671,7 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) unsigned long def_mount_opts; struct super_block *sb = vfs->mnt_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); + journal_t *journal = sbi->s_journal; struct ext4_super_block *es = sbi->s_es; def_mount_opts = le32_to_cpu(es->s_default_mount_opts); @@ -729,8 +730,15 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_printf(seq, ",commit=%u", (unsigned) (sbi->s_commit_interval / HZ)); } - if (test_opt(sb, BARRIER)) - seq_puts(seq, ",barrier=1"); + /* + * We're changing the default of barrier mount option, so + * let's always display its mount state so it's clear what its + * status is. + */ + seq_puts(seq, ",barrier="); + seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0"); + if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) + seq_puts(seq, ",journal_async_commit"); if (test_opt(sb, NOBH)) seq_puts(seq, ",nobh"); if (!test_opt(sb, EXTENTS)) @@ -1907,6 +1915,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) sbi->s_resgid = le16_to_cpu(es->s_def_resgid); set_opt(sbi->s_mount_opt, RESERVATION); + set_opt(sbi->s_mount_opt, BARRIER); /* * turn on extents feature by default in ext4 filesystem @@ -2189,6 +2198,29 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) { if (ext4_load_journal(sb, es, journal_devnum)) goto failed_mount3; + if (!(sb->s_flags & MS_RDONLY) && + EXT4_SB(sb)->s_journal->j_failed_commit) { + printk(KERN_CRIT "EXT4-fs error (device %s): " + "ext4_fill_super: Journal transaction " + "%u is corrupt\n", sb->s_id, + EXT4_SB(sb)->s_journal->j_failed_commit); + if (test_opt (sb, ERRORS_RO)) { + printk (KERN_CRIT + "Mounting filesystem read-only\n"); + sb->s_flags |= MS_RDONLY; + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + es->s_state |= cpu_to_le16(EXT4_ERROR_FS); + } + if (test_opt(sb, ERRORS_PANIC)) { + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + es->s_state |= cpu_to_le16(EXT4_ERROR_FS); + ext4_commit_super(sb, es, 1); + printk(KERN_CRIT + "EXT4-fs (device %s): mount failed\n", + sb->s_id); + goto failed_mount4; + } + } } else if (journal_inum) { if (ext4_create_journal(sb, es, journal_inum)) goto failed_mount3; diff --git a/fs/fat/file.c b/fs/fat/file.c index 27cc1164ec36..771326b8047e 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -257,26 +257,34 @@ int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) } EXPORT_SYMBOL_GPL(fat_getattr); -static int fat_check_mode(const struct msdos_sb_info *sbi, struct inode *inode, - mode_t mode) +static int fat_sanitize_mode(const struct msdos_sb_info *sbi, + struct inode *inode, umode_t *mode_ptr) { - mode_t mask, req = mode & ~S_IFMT; + mode_t mask, perm; - if (S_ISREG(mode)) + /* + * Note, the basic check is already done by a caller of + * (attr->ia_mode & ~MSDOS_VALID_MODE) + */ + + if (S_ISREG(inode->i_mode)) mask = sbi->options.fs_fmask; else mask = sbi->options.fs_dmask; + perm = *mode_ptr & ~(S_IFMT | mask); + /* * Of the r and x bits, all (subject to umask) must be present. Of the * w bits, either all (subject to umask) or none must be present. */ - req &= ~mask; - if ((req & (S_IRUGO | S_IXUGO)) != (inode->i_mode & (S_IRUGO|S_IXUGO))) + if ((perm & (S_IRUGO | S_IXUGO)) != (inode->i_mode & (S_IRUGO|S_IXUGO))) return -EPERM; - if ((req & S_IWUGO) && ((req & S_IWUGO) != (S_IWUGO & ~mask))) + if ((perm & S_IWUGO) && ((perm & S_IWUGO) != (S_IWUGO & ~mask))) return -EPERM; + *mode_ptr &= S_IFMT | perm; + return 0; } @@ -299,7 +307,7 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) { struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); struct inode *inode = dentry->d_inode; - int mask, error = 0; + int error = 0; unsigned int ia_valid; lock_kernel(); @@ -332,12 +340,13 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) error = 0; goto out; } + if (((attr->ia_valid & ATTR_UID) && (attr->ia_uid != sbi->options.fs_uid)) || ((attr->ia_valid & ATTR_GID) && (attr->ia_gid != sbi->options.fs_gid)) || ((attr->ia_valid & ATTR_MODE) && - fat_check_mode(sbi, inode, attr->ia_mode) < 0)) + (attr->ia_mode & ~MSDOS_VALID_MODE))) error = -EPERM; if (error) { @@ -346,15 +355,16 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) goto out; } - error = inode_setattr(inode, attr); - if (error) - goto out; + /* + * We don't return -EPERM here. Yes, strange, but this is too + * old behavior. + */ + if (attr->ia_valid & ATTR_MODE) { + if (fat_sanitize_mode(sbi, inode, &attr->ia_mode) < 0) + attr->ia_valid &= ~ATTR_MODE; + } - if (S_ISDIR(inode->i_mode)) - mask = sbi->options.fs_dmask; - else - mask = sbi->options.fs_fmask; - inode->i_mode &= S_IFMT | (S_IRWXUGO & ~mask); + error = inode_setattr(inode, attr); out: unlock_kernel(); return error; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 43e99513334a..3141690558c8 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -591,7 +591,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages); fc->minor = arg->minor; fc->max_write = arg->minor < 5 ? 4096 : arg->max_write; - fc->max_write = min_t(unsigned, 4096, fc->max_write); + fc->max_write = max_t(unsigned, 4096, fc->max_write); fc->conn_init = 1; } fuse_put_request(fc, req); @@ -667,7 +667,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->flags = d.flags; fc->user_id = d.user_id; fc->group_id = d.group_id; - fc->max_read = min_t(unsigned, 4096, d.max_read); + fc->max_read = max_t(unsigned, 4096, d.max_read); /* Used by get_root_inode() */ sb->s_fs_info = fc; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index c19184f2e70e..bec76b1c2bb0 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -246,15 +246,11 @@ static void find_metapath(const struct gfs2_sbd *sdp, u64 block, } -static inline unsigned int zero_metapath_length(const struct metapath *mp, - unsigned height) +static inline unsigned int metapath_branch_start(const struct metapath *mp) { - unsigned int i; - for (i = 0; i < height - 1; i++) { - if (mp->mp_list[i] != 0) - return i; - } - return height; + if (mp->mp_list[0] == 0) + return 2; + return 1; } /** @@ -436,7 +432,7 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock, struct gfs2_sbd *sdp = GFS2_SB(inode); struct buffer_head *dibh = mp->mp_bh[0]; u64 bn, dblock = 0; - unsigned n, i, blks, alloced = 0, iblks = 0, zmpl = 0; + unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0; unsigned dblks = 0; unsigned ptrs_per_blk; const unsigned end_of_metadata = height - 1; @@ -471,9 +467,8 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock, /* Building up tree height */ state = ALLOC_GROW_HEIGHT; iblks = height - ip->i_height; - zmpl = zero_metapath_length(mp, height); - iblks -= zmpl; - iblks += height; + branch_start = metapath_branch_start(mp); + iblks += (height - branch_start); } } @@ -509,13 +504,13 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock, sizeof(struct gfs2_meta_header)); *ptr = zero_bn; state = ALLOC_GROW_DEPTH; - for(i = zmpl; i < height; i++) { + for(i = branch_start; i < height; i++) { if (mp->mp_bh[i] == NULL) break; brelse(mp->mp_bh[i]); mp->mp_bh[i] = NULL; } - i = zmpl; + i = branch_start; } if (n == 0) break; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 6387523a3153..3401628d742b 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -195,7 +195,7 @@ ulong_aligned: depending on architecture. I've experimented with several ways of writing this section such as using an else before the goto but this one seems to be the fastest. */ - while ((unsigned char *)plong < end - 1) { + while ((unsigned char *)plong < end - sizeof(unsigned long)) { prefetch(plong + 1); if (((*plong) & LBITMASK) != lskipval) break; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 4d99685fdce4..a2ed72f7ceee 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -168,6 +168,7 @@ static int journal_submit_commit_record(journal_t *journal, spin_unlock(&journal->j_state_lock); /* And try again, without the barrier */ + lock_buffer(bh); set_buffer_uptodate(bh); set_buffer_dirty(bh); ret = submit_bh(WRITE, bh); diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 5d0405a9e7ca..058f50f65b76 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -344,6 +344,7 @@ static int calc_chksums(journal_t *journal, struct buffer_head *bh, *crc32_sum = crc32_be(*crc32_sum, (void *)obh->b_data, obh->b_size); } + put_bh(obh); } return 0; } @@ -610,9 +611,8 @@ static int do_one_pass(journal_t *journal, chksum_err = chksum_seen = 0; if (info->end_transaction) { - printk(KERN_ERR "JBD: Transaction %u " - "found to be corrupt.\n", - next_commit_ID - 1); + journal->j_failed_commit = + info->end_transaction; brelse(bh); break; } @@ -643,10 +643,8 @@ static int do_one_pass(journal_t *journal, if (!JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)){ - printk(KERN_ERR - "JBD: Transaction %u " - "found to be corrupt.\n", - next_commit_ID); + journal->j_failed_commit = + next_commit_ID; brelse(bh); break; } diff --git a/fs/locks.c b/fs/locks.c index 11dbf08651b7..dce8c747371c 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -561,9 +561,6 @@ static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl) /* insert into file's list */ fl->fl_next = *pos; *pos = fl; - - if (fl->fl_ops && fl->fl_ops->fl_insert) - fl->fl_ops->fl_insert(fl); } /* @@ -586,9 +583,6 @@ static void locks_delete_lock(struct file_lock **thisfl_p) fl->fl_fasync = NULL; } - if (fl->fl_ops && fl->fl_ops->fl_remove) - fl->fl_ops->fl_remove(fl); - if (fl->fl_nspid) { put_pid(fl->fl_nspid); fl->fl_nspid = NULL; diff --git a/fs/namei.c b/fs/namei.c index c7e43536c49a..01e67dddcc3d 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -581,15 +581,13 @@ static __always_inline int link_path_walk(const char *name, struct nameidata *nd int result; /* make sure the stuff we saved doesn't go away */ - dget(save.dentry); - mntget(save.mnt); + path_get(&save); result = __link_path_walk(name, nd); if (result == -ESTALE) { /* nd->path had been dropped */ nd->path = save; - dget(nd->path.dentry); - mntget(nd->path.mnt); + path_get(&nd->path); nd->flags |= LOOKUP_REVAL; result = __link_path_walk(name, nd); } @@ -1216,8 +1214,9 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, nd->flags = flags; nd->depth = 0; - nd->path.mnt = mntget(mnt); - nd->path.dentry = dget(dentry); + nd->path.dentry = dentry; + nd->path.mnt = mnt; + path_get(&nd->path); retval = path_walk(name, nd); if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry && @@ -2857,16 +2856,17 @@ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct nameidata nd; void *cookie; + int res; nd.depth = 0; cookie = dentry->d_inode->i_op->follow_link(dentry, &nd); - if (!IS_ERR(cookie)) { - int res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd)); - if (dentry->d_inode->i_op->put_link) - dentry->d_inode->i_op->put_link(dentry, &nd, cookie); - cookie = ERR_PTR(res); - } - return PTR_ERR(cookie); + if (IS_ERR(cookie)) + return PTR_ERR(cookie); + + res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd)); + if (dentry->d_inode->i_op->put_link) + dentry->d_inode->i_op->put_link(dentry, &nd, cookie); + return res; } int vfs_follow_link(struct nameidata *nd, const char *link) diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 49c7cd0502cc..779d2eb649c5 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -130,10 +130,11 @@ static int xdr_decode_fhstatus3(struct rpc_rqst *req, __be32 *p, struct mnt_fhstatus *res) { struct nfs_fh *fh = res->fh; + unsigned size; if ((res->status = ntohl(*p++)) == 0) { - int size = ntohl(*p++); - if (size <= NFS3_FHSIZE) { + size = ntohl(*p++); + if (size <= NFS3_FHSIZE && size != 0) { fh->size = size; memcpy(fh->data, p, size); } else diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 2a4a024a4e7b..614efeed5437 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1216,8 +1216,6 @@ static int nfs_validate_mount_data(void *options, { struct nfs_mount_data *data = (struct nfs_mount_data *)options; - memset(args, 0, sizeof(*args)); - if (data == NULL) goto out_no_data; @@ -1251,13 +1249,13 @@ static int nfs_validate_mount_data(void *options, case 5: memset(data->context, 0, sizeof(data->context)); case 6: - if (data->flags & NFS_MOUNT_VER3) + if (data->flags & NFS_MOUNT_VER3) { + if (data->root.size > NFS3_FHSIZE || data->root.size == 0) + goto out_invalid_fh; mntfh->size = data->root.size; - else + } else mntfh->size = NFS2_FHSIZE; - if (mntfh->size > sizeof(mntfh->data)) - goto out_invalid_fh; memcpy(mntfh->data, data->root.data, mntfh->size); if (mntfh->size < sizeof(mntfh->data)) @@ -1585,24 +1583,29 @@ static int nfs_get_sb(struct file_system_type *fs_type, { struct nfs_server *server = NULL; struct super_block *s; - struct nfs_fh mntfh; - struct nfs_parsed_mount_data data; + struct nfs_parsed_mount_data *data; + struct nfs_fh *mntfh; struct dentry *mntroot; int (*compare_super)(struct super_block *, void *) = nfs_compare_super; struct nfs_sb_mountdata sb_mntdata = { .mntflags = flags, }; - int error; + int error = -ENOMEM; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + mntfh = kzalloc(sizeof(*mntfh), GFP_KERNEL); + if (data == NULL || mntfh == NULL) + goto out_free_fh; - security_init_mnt_opts(&data.lsm_opts); + security_init_mnt_opts(&data->lsm_opts); /* Validate the mount data */ - error = nfs_validate_mount_data(raw_data, &data, &mntfh, dev_name); + error = nfs_validate_mount_data(raw_data, data, mntfh, dev_name); if (error < 0) goto out; /* Get a volume representation */ - server = nfs_create_server(&data, &mntfh); + server = nfs_create_server(data, mntfh); if (IS_ERR(server)) { error = PTR_ERR(server); goto out; @@ -1630,16 +1633,16 @@ static int nfs_get_sb(struct file_system_type *fs_type, if (!s->s_root) { /* initial superblock/root creation */ - nfs_fill_super(s, &data); + nfs_fill_super(s, data); } - mntroot = nfs_get_root(s, &mntfh); + mntroot = nfs_get_root(s, mntfh); if (IS_ERR(mntroot)) { error = PTR_ERR(mntroot); goto error_splat_super; } - error = security_sb_set_mnt_opts(s, &data.lsm_opts); + error = security_sb_set_mnt_opts(s, &data->lsm_opts); if (error) goto error_splat_root; @@ -1649,9 +1652,12 @@ static int nfs_get_sb(struct file_system_type *fs_type, error = 0; out: - kfree(data.nfs_server.hostname); - kfree(data.mount_server.hostname); - security_free_mnt_opts(&data.lsm_opts); + kfree(data->nfs_server.hostname); + kfree(data->mount_server.hostname); + security_free_mnt_opts(&data->lsm_opts); +out_free_fh: + kfree(mntfh); + kfree(data); return error; out_err_nosb: @@ -1800,8 +1806,6 @@ static int nfs4_validate_mount_data(void *options, struct nfs4_mount_data *data = (struct nfs4_mount_data *)options; char *c; - memset(args, 0, sizeof(*args)); - if (data == NULL) goto out_no_data; @@ -1959,26 +1963,31 @@ out_no_client_address: static int nfs4_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt) { - struct nfs_parsed_mount_data data; + struct nfs_parsed_mount_data *data; struct super_block *s; struct nfs_server *server; - struct nfs_fh mntfh; + struct nfs_fh *mntfh; struct dentry *mntroot; int (*compare_super)(struct super_block *, void *) = nfs_compare_super; struct nfs_sb_mountdata sb_mntdata = { .mntflags = flags, }; - int error; + int error = -ENOMEM; - security_init_mnt_opts(&data.lsm_opts); + data = kzalloc(sizeof(*data), GFP_KERNEL); + mntfh = kzalloc(sizeof(*mntfh), GFP_KERNEL); + if (data == NULL || mntfh == NULL) + goto out_free_fh; + + security_init_mnt_opts(&data->lsm_opts); /* Validate the mount data */ - error = nfs4_validate_mount_data(raw_data, &data, dev_name); + error = nfs4_validate_mount_data(raw_data, data, dev_name); if (error < 0) goto out; /* Get a volume representation */ - server = nfs4_create_server(&data, &mntfh); + server = nfs4_create_server(data, mntfh); if (IS_ERR(server)) { error = PTR_ERR(server); goto out; @@ -2009,13 +2018,13 @@ static int nfs4_get_sb(struct file_system_type *fs_type, nfs4_fill_super(s); } - mntroot = nfs4_get_root(s, &mntfh); + mntroot = nfs4_get_root(s, mntfh); if (IS_ERR(mntroot)) { error = PTR_ERR(mntroot); goto error_splat_super; } - error = security_sb_set_mnt_opts(s, &data.lsm_opts); + error = security_sb_set_mnt_opts(s, &data->lsm_opts); if (error) goto error_splat_root; @@ -2025,10 +2034,13 @@ static int nfs4_get_sb(struct file_system_type *fs_type, error = 0; out: - kfree(data.client_address); - kfree(data.nfs_server.export_path); - kfree(data.nfs_server.hostname); - security_free_mnt_opts(&data.lsm_opts); + kfree(data->client_address); + kfree(data->nfs_server.export_path); + kfree(data->nfs_server.hostname); + security_free_mnt_opts(&data->lsm_opts); +out_free_fh: + kfree(mntfh); + kfree(data); return error; out_free: diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 6d8ace3e3259..f333848fd3be 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -739,12 +739,13 @@ int nfs_updatepage(struct file *file, struct page *page, } status = nfs_writepage_setup(ctx, page, offset, count); - __set_page_dirty_nobuffers(page); + if (status < 0) + nfs_set_pageerror(page); + else + __set_page_dirty_nobuffers(page); dprintk("NFS: nfs_updatepage returns %d (isize %Ld)\n", status, (long long)i_size_read(inode)); - if (status < 0) - nfs_set_pageerror(page); return status; } diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index cf9401e8cd0b..cfdb08b484ed 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -21,7 +21,6 @@ #include <linux/kernel.h> #include <linux/module.h> -#include <linux/sysctl.h> #include <linux/configfs.h> #include "tcp.h" @@ -36,65 +35,6 @@ * cluster references throughout where nodes are looked up */ struct o2nm_cluster *o2nm_single_cluster = NULL; -#define OCFS2_MAX_HB_CTL_PATH 256 -static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; - -static ctl_table ocfs2_nm_table[] = { - { - .ctl_name = 1, - .procname = "hb_ctl_path", - .data = ocfs2_hb_ctl_path, - .maxlen = OCFS2_MAX_HB_CTL_PATH, - .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, - }, - { .ctl_name = 0 } -}; - -static ctl_table ocfs2_mod_table[] = { - { - .ctl_name = FS_OCFS2_NM, - .procname = "nm", - .data = NULL, - .maxlen = 0, - .mode = 0555, - .child = ocfs2_nm_table - }, - { .ctl_name = 0} -}; - -static ctl_table ocfs2_kern_table[] = { - { - .ctl_name = FS_OCFS2, - .procname = "ocfs2", - .data = NULL, - .maxlen = 0, - .mode = 0555, - .child = ocfs2_mod_table - }, - { .ctl_name = 0} -}; - -static ctl_table ocfs2_root_table[] = { - { - .ctl_name = CTL_FS, - .procname = "fs", - .data = NULL, - .maxlen = 0, - .mode = 0555, - .child = ocfs2_kern_table - }, - { .ctl_name = 0 } -}; - -static struct ctl_table_header *ocfs2_table_header = NULL; - -const char *o2nm_get_hb_ctl_path(void) -{ - return ocfs2_hb_ctl_path; -} -EXPORT_SYMBOL_GPL(o2nm_get_hb_ctl_path); struct o2nm_node *o2nm_get_node_by_num(u8 node_num) { @@ -941,9 +881,6 @@ void o2nm_undepend_this_node(void) static void __exit exit_o2nm(void) { - if (ocfs2_table_header) - unregister_sysctl_table(ocfs2_table_header); - /* XXX sync with hb callbacks and shut down hb? */ o2net_unregister_hb_callbacks(); configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys); @@ -964,16 +901,9 @@ static int __init init_o2nm(void) if (ret) goto out; - ocfs2_table_header = register_sysctl_table(ocfs2_root_table); - if (!ocfs2_table_header) { - printk(KERN_ERR "nodemanager: unable to register sysctl\n"); - ret = -ENOMEM; /* or something. */ - goto out_o2net; - } - ret = o2net_register_hb_callbacks(); if (ret) - goto out_sysctl; + goto out_o2net; config_group_init(&o2nm_cluster_group.cs_subsys.su_group); mutex_init(&o2nm_cluster_group.cs_subsys.su_mutex); @@ -990,8 +920,6 @@ static int __init init_o2nm(void) configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys); out_callbacks: o2net_unregister_hb_callbacks(); -out_sysctl: - unregister_sysctl_table(ocfs2_table_header); out_o2net: o2net_exit(); out: diff --git a/fs/ocfs2/cluster/nodemanager.h b/fs/ocfs2/cluster/nodemanager.h index 7c860361b8dd..c992ea0da4ad 100644 --- a/fs/ocfs2/cluster/nodemanager.h +++ b/fs/ocfs2/cluster/nodemanager.h @@ -33,10 +33,6 @@ #include <linux/configfs.h> #include <linux/rbtree.h> -#define FS_OCFS2_NM 1 - -const char *o2nm_get_hb_ctl_path(void); - struct o2nm_node { spinlock_t nd_lock; struct config_item nd_item; diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c index bbd1667aa7d3..fcd120f1493a 100644 --- a/fs/ocfs2/stack_o2cb.c +++ b/fs/ocfs2/stack_o2cb.c @@ -317,8 +317,7 @@ out: return rc; } -static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn, - int hangup_pending) +static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn) { struct dlm_ctxt *dlm = conn->cc_lockspace; struct o2dlm_private *priv = conn->cc_private; @@ -333,43 +332,6 @@ static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn, return 0; } -static void o2hb_stop(const char *group) -{ - int ret; - char *argv[5], *envp[3]; - - argv[0] = (char *)o2nm_get_hb_ctl_path(); - argv[1] = "-K"; - argv[2] = "-u"; - argv[3] = (char *)group; - argv[4] = NULL; - - mlog(0, "Run: %s %s %s %s\n", argv[0], argv[1], argv[2], argv[3]); - - /* minimal command environment taken from cpu_run_sbin_hotplug */ - envp[0] = "HOME=/"; - envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; - envp[2] = NULL; - - ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC); - if (ret < 0) - mlog_errno(ret); -} - -/* - * Hangup is a hack for tools compatibility. Older ocfs2-tools software - * expects the filesystem to call "ocfs2_hb_ctl" during unmount. This - * happens regardless of whether the DLM got started, so we can't do it - * in ocfs2_cluster_disconnect(). We bring the o2hb_stop() function into - * the glue and provide a "hangup" API for super.c to call. - * - * Other stacks will eventually provide a NULL ->hangup() pointer. - */ -static void o2cb_cluster_hangup(const char *group, int grouplen) -{ - o2hb_stop(group); -} - static int o2cb_cluster_this_node(unsigned int *node) { int node_num; @@ -388,7 +350,6 @@ static int o2cb_cluster_this_node(unsigned int *node) static struct ocfs2_stack_operations o2cb_stack_ops = { .connect = o2cb_cluster_connect, .disconnect = o2cb_cluster_disconnect, - .hangup = o2cb_cluster_hangup, .this_node = o2cb_cluster_this_node, .dlm_lock = o2cb_dlm_lock, .dlm_unlock = o2cb_dlm_unlock, diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c index 6b97d11f6bf8..c021280dd462 100644 --- a/fs/ocfs2/stack_user.c +++ b/fs/ocfs2/stack_user.c @@ -816,8 +816,7 @@ out: return rc; } -static int user_cluster_disconnect(struct ocfs2_cluster_connection *conn, - int hangup_pending) +static int user_cluster_disconnect(struct ocfs2_cluster_connection *conn) { dlm_release_lockspace(conn->cc_lockspace, 2); conn->cc_lockspace = NULL; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 119f60cea9cc..10e149ae5e3a 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -26,6 +26,7 @@ #include <linux/fs.h> #include <linux/kobject.h> #include <linux/sysfs.h> +#include <linux/sysctl.h> #include "ocfs2_fs.h" @@ -33,11 +34,13 @@ #define OCFS2_STACK_PLUGIN_O2CB "o2cb" #define OCFS2_STACK_PLUGIN_USER "user" +#define OCFS2_MAX_HB_CTL_PATH 256 static struct ocfs2_locking_protocol *lproto; static DEFINE_SPINLOCK(ocfs2_stack_lock); static LIST_HEAD(ocfs2_stack_list); static char cluster_stack_name[OCFS2_STACK_LABEL_LEN + 1]; +static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; /* * The stack currently in use. If not null, active_stack->sp_count > 0, @@ -349,7 +352,7 @@ int ocfs2_cluster_disconnect(struct ocfs2_cluster_connection *conn, BUG_ON(conn == NULL); - ret = active_stack->sp_ops->disconnect(conn, hangup_pending); + ret = active_stack->sp_ops->disconnect(conn); /* XXX Should we free it anyway? */ if (!ret) { @@ -362,13 +365,48 @@ int ocfs2_cluster_disconnect(struct ocfs2_cluster_connection *conn, } EXPORT_SYMBOL_GPL(ocfs2_cluster_disconnect); +/* + * Leave the group for this filesystem. This is executed by a userspace + * program (stored in ocfs2_hb_ctl_path). + */ +static void ocfs2_leave_group(const char *group) +{ + int ret; + char *argv[5], *envp[3]; + + argv[0] = ocfs2_hb_ctl_path; + argv[1] = "-K"; + argv[2] = "-u"; + argv[3] = (char *)group; + argv[4] = NULL; + + /* minimal command environment taken from cpu_run_sbin_hotplug */ + envp[0] = "HOME=/"; + envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; + envp[2] = NULL; + + ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC); + if (ret < 0) { + printk(KERN_ERR + "ocfs2: Error %d running user helper " + "\"%s %s %s %s\"\n", + ret, argv[0], argv[1], argv[2], argv[3]); + } +} + +/* + * Hangup is a required post-umount. ocfs2-tools software expects the + * filesystem to call "ocfs2_hb_ctl" during unmount. This happens + * regardless of whether the DLM got started, so we can't do it + * in ocfs2_cluster_disconnect(). The ocfs2_leave_group() function does + * the actual work. + */ void ocfs2_cluster_hangup(const char *group, int grouplen) { BUG_ON(group == NULL); BUG_ON(group[grouplen] != '\0'); - if (active_stack->sp_ops->hangup) - active_stack->sp_ops->hangup(group, grouplen); + ocfs2_leave_group(group); /* cluster_disconnect() was called with hangup_pending==1 */ ocfs2_stack_driver_put(); @@ -548,10 +586,83 @@ error: return ret; } +/* + * Sysctl bits + * + * The sysctl lives at /proc/sys/fs/ocfs2/nm/hb_ctl_path. The 'nm' doesn't + * make as much sense in a multiple cluster stack world, but it's safer + * and easier to preserve the name. + */ + +#define FS_OCFS2_NM 1 + +static ctl_table ocfs2_nm_table[] = { + { + .ctl_name = 1, + .procname = "hb_ctl_path", + .data = ocfs2_hb_ctl_path, + .maxlen = OCFS2_MAX_HB_CTL_PATH, + .mode = 0644, + .proc_handler = &proc_dostring, + .strategy = &sysctl_string, + }, + { .ctl_name = 0 } +}; + +static ctl_table ocfs2_mod_table[] = { + { + .ctl_name = FS_OCFS2_NM, + .procname = "nm", + .data = NULL, + .maxlen = 0, + .mode = 0555, + .child = ocfs2_nm_table + }, + { .ctl_name = 0} +}; + +static ctl_table ocfs2_kern_table[] = { + { + .ctl_name = FS_OCFS2, + .procname = "ocfs2", + .data = NULL, + .maxlen = 0, + .mode = 0555, + .child = ocfs2_mod_table + }, + { .ctl_name = 0} +}; + +static ctl_table ocfs2_root_table[] = { + { + .ctl_name = CTL_FS, + .procname = "fs", + .data = NULL, + .maxlen = 0, + .mode = 0555, + .child = ocfs2_kern_table + }, + { .ctl_name = 0 } +}; + +static struct ctl_table_header *ocfs2_table_header = NULL; + + +/* + * Initialization + */ + static int __init ocfs2_stack_glue_init(void) { strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB); + ocfs2_table_header = register_sysctl_table(ocfs2_root_table); + if (!ocfs2_table_header) { + printk(KERN_ERR + "ocfs2 stack glue: unable to register sysctl\n"); + return -ENOMEM; /* or something. */ + } + return ocfs2_sysfs_init(); } @@ -559,6 +670,8 @@ static void __exit ocfs2_stack_glue_exit(void) { lproto = NULL; ocfs2_sysfs_exit(); + if (ocfs2_table_header) + unregister_sysctl_table(ocfs2_table_header); } MODULE_AUTHOR("Oracle"); diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index 005e4f170e0f..db56281dd1be 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -134,22 +134,10 @@ struct ocfs2_stack_operations { * be freed. Thus, a stack must not return from ->disconnect() * until it will no longer reference the conn pointer. * - * If hangup_pending is zero, ocfs2_cluster_disconnect() will also - * be dropping the reference on the module. + * Once this call returns, the stack glue will be dropping this + * connection's reference on the module. */ - int (*disconnect)(struct ocfs2_cluster_connection *conn, - int hangup_pending); - - /* - * ocfs2_cluster_hangup() exists for compatibility with older - * ocfs2 tools. Only the classic stack really needs it. As such - * ->hangup() is not required of all stacks. See the comment by - * ocfs2_cluster_hangup() for more details. - * - * Note that ocfs2_cluster_hangup() can only be called if - * hangup_pending was passed to ocfs2_cluster_disconnect(). - */ - void (*hangup)(const char *group, int grouplen); + int (*disconnect)(struct ocfs2_cluster_connection *conn); /* * ->this_node() returns the cluster's unique identifier for the @@ -258,4 +246,5 @@ void ocfs2_stack_glue_set_locking_protocol(struct ocfs2_locking_protocol *proto) /* Used by stack plugins */ int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin); void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin); + #endif /* STACKGLUE_H */ diff --git a/fs/pipe.c b/fs/pipe.c index ec228bc9f882..700f4e0d9572 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1003,8 +1003,7 @@ struct file *create_write_pipe(void) void free_write_pipe(struct file *f) { free_pipe_info(f->f_dentry->d_inode); - dput(f->f_path.dentry); - mntput(f->f_path.mnt); + path_put(&f->f_path); put_filp(f); } @@ -1015,8 +1014,8 @@ struct file *create_read_pipe(struct file *wrf) return ERR_PTR(-ENFILE); /* Grab pipe from the writer */ - f->f_path.mnt = mntget(wrf->f_path.mnt); - f->f_path.dentry = dget(wrf->f_path.dentry); + f->f_path = wrf->f_path; + path_get(&wrf->f_path); f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping; f->f_pos = 0; @@ -1068,8 +1067,7 @@ int do_pipe(int *fd) err_fdr: put_unused_fd(fdr); err_read_pipe: - dput(fr->f_dentry); - mntput(fr->f_vfsmnt); + path_put(&fr->f_path); put_filp(fr); err_write_pipe: free_write_pipe(fw); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 17403629e330..ab8ccc9d14ff 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -315,9 +315,9 @@ struct mem_size_stats { }; static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, - void *private) + struct mm_walk *walk) { - struct mem_size_stats *mss = private; + struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = mss->vma; pte_t *pte, ptent; spinlock_t *ptl; @@ -365,19 +365,21 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, return 0; } -static struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range }; - static int show_smap(struct seq_file *m, void *v) { struct vm_area_struct *vma = v; struct mem_size_stats mss; int ret; + struct mm_walk smaps_walk = { + .pmd_entry = smaps_pte_range, + .mm = vma->vm_mm, + .private = &mss, + }; memset(&mss, 0, sizeof mss); mss.vma = vma; if (vma->vm_mm && !is_vm_hugetlb_page(vma)) - walk_page_range(vma->vm_mm, vma->vm_start, vma->vm_end, - &smaps_walk, &mss); + walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk); ret = show_map(m, v); if (ret) @@ -426,9 +428,9 @@ const struct file_operations proc_smaps_operations = { }; static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, - unsigned long end, void *private) + unsigned long end, struct mm_walk *walk) { - struct vm_area_struct *vma = private; + struct vm_area_struct *vma = walk->private; pte_t *pte, ptent; spinlock_t *ptl; struct page *page; @@ -452,8 +454,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, return 0; } -static struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range }; - static ssize_t clear_refs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -476,11 +476,17 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, return -ESRCH; mm = get_task_mm(task); if (mm) { + static struct mm_walk clear_refs_walk; + memset(&clear_refs_walk, 0, sizeof(clear_refs_walk)); + clear_refs_walk.pmd_entry = clear_refs_pte_range; + clear_refs_walk.mm = mm; down_read(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) + for (vma = mm->mmap; vma; vma = vma->vm_next) { + clear_refs_walk.private = vma; if (!is_vm_hugetlb_page(vma)) - walk_page_range(mm, vma->vm_start, vma->vm_end, - &clear_refs_walk, vma); + walk_page_range(vma->vm_start, vma->vm_end, + &clear_refs_walk); + } flush_tlb_mm(mm); up_read(&mm->mmap_sem); mmput(mm); @@ -528,9 +534,9 @@ static int add_to_pagemap(unsigned long addr, u64 pfn, } static int pagemap_pte_hole(unsigned long start, unsigned long end, - void *private) + struct mm_walk *walk) { - struct pagemapread *pm = private; + struct pagemapread *pm = walk->private; unsigned long addr; int err = 0; for (addr = start; addr < end; addr += PAGE_SIZE) { @@ -547,24 +553,45 @@ static u64 swap_pte_to_pagemap_entry(pte_t pte) return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT); } +static unsigned long pte_to_pagemap_entry(pte_t pte) +{ + unsigned long pme = 0; + if (is_swap_pte(pte)) + pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte)) + | PM_PSHIFT(PAGE_SHIFT) | PM_SWAP; + else if (pte_present(pte)) + pme = PM_PFRAME(pte_pfn(pte)) + | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT; + return pme; +} + static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, - void *private) + struct mm_walk *walk) { - struct pagemapread *pm = private; + struct vm_area_struct *vma; + struct pagemapread *pm = walk->private; pte_t *pte; int err = 0; + /* find the first VMA at or above 'addr' */ + vma = find_vma(walk->mm, addr); for (; addr != end; addr += PAGE_SIZE) { u64 pfn = PM_NOT_PRESENT; - pte = pte_offset_map(pmd, addr); - if (is_swap_pte(*pte)) - pfn = PM_PFRAME(swap_pte_to_pagemap_entry(*pte)) - | PM_PSHIFT(PAGE_SHIFT) | PM_SWAP; - else if (pte_present(*pte)) - pfn = PM_PFRAME(pte_pfn(*pte)) - | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT; - /* unmap so we're not in atomic when we copy to userspace */ - pte_unmap(pte); + + /* check to see if we've left 'vma' behind + * and need a new, higher one */ + if (vma && (addr >= vma->vm_end)) + vma = find_vma(walk->mm, addr); + + /* check that 'vma' actually covers this address, + * and that it isn't a huge page vma */ + if (vma && (vma->vm_start <= addr) && + !is_vm_hugetlb_page(vma)) { + pte = pte_offset_map(pmd, addr); + pfn = pte_to_pagemap_entry(*pte); + /* unmap before userspace copy */ + pte_unmap(pte); + } err = add_to_pagemap(addr, pfn, pm); if (err) return err; @@ -675,8 +702,8 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, * user buffer is tracked in "pm", and the walk * will stop when we hit the end of the buffer. */ - ret = walk_page_range(mm, start_vaddr, end_vaddr, - &pagemap_walk, &pm); + ret = walk_page_range(start_vaddr, end_vaddr, + &pagemap_walk); if (ret == PM_END_OF_BUFFER) ret = 0; /* don't need mmap_sem for these, but this looks cleaner */ diff --git a/fs/select.c b/fs/select.c index 8dda969614a9..da0e88201c3a 100644 --- a/fs/select.c +++ b/fs/select.c @@ -249,7 +249,6 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout) retval++; } } - cond_resched(); } if (res_in) *rinp = res_in; @@ -257,6 +256,7 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout) *routp = res_out; if (res_ex) *rexp = res_ex; + cond_resched(); } wait = NULL; if (retval || !*timeout || signal_pending(current)) diff --git a/fs/udf/super.c b/fs/udf/super.c index 7a5f69be6ac2..44cc702f96cc 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -682,38 +682,26 @@ static int udf_vrs(struct super_block *sb, int silent) /* * Check whether there is an anchor block in the given block */ -static int udf_check_anchor_block(struct super_block *sb, sector_t block, - bool varconv) +static int udf_check_anchor_block(struct super_block *sb, sector_t block) { - struct buffer_head *bh = NULL; - tag *t; + struct buffer_head *bh; uint16_t ident; - uint32_t location; - if (varconv) { - if (udf_fixed_to_variable(block) >= - sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits) - return 0; - bh = sb_bread(sb, udf_fixed_to_variable(block)); - } - else - bh = sb_bread(sb, block); + if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) && + udf_fixed_to_variable(block) >= + sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits) + return 0; + bh = udf_read_tagged(sb, block, block, &ident); if (!bh) return 0; - - t = (tag *)bh->b_data; - ident = le16_to_cpu(t->tagIdent); - location = le32_to_cpu(t->tagLocation); brelse(bh); - if (ident != TAG_IDENT_AVDP) - return 0; - return location == block; + + return ident == TAG_IDENT_AVDP; } /* Search for an anchor volume descriptor pointer */ -static sector_t udf_scan_anchors(struct super_block *sb, bool varconv, - sector_t lastblock) +static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock) { sector_t last[6]; int i; @@ -739,7 +727,7 @@ static sector_t udf_scan_anchors(struct super_block *sb, bool varconv, sb->s_blocksize_bits) continue; - if (udf_check_anchor_block(sb, last[i], varconv)) { + if (udf_check_anchor_block(sb, last[i])) { sbi->s_anchor[0] = last[i]; sbi->s_anchor[1] = last[i] - 256; return last[i]; @@ -748,17 +736,17 @@ static sector_t udf_scan_anchors(struct super_block *sb, bool varconv, if (last[i] < 256) continue; - if (udf_check_anchor_block(sb, last[i] - 256, varconv)) { + if (udf_check_anchor_block(sb, last[i] - 256)) { sbi->s_anchor[1] = last[i] - 256; return last[i]; } } - if (udf_check_anchor_block(sb, sbi->s_session + 256, varconv)) { + if (udf_check_anchor_block(sb, sbi->s_session + 256)) { sbi->s_anchor[0] = sbi->s_session + 256; return last[0]; } - if (udf_check_anchor_block(sb, sbi->s_session + 512, varconv)) { + if (udf_check_anchor_block(sb, sbi->s_session + 512)) { sbi->s_anchor[0] = sbi->s_session + 512; return last[0]; } @@ -780,23 +768,24 @@ static void udf_find_anchor(struct super_block *sb) int i; struct udf_sb_info *sbi = UDF_SB(sb); - lastblock = udf_scan_anchors(sb, 0, sbi->s_last_block); + lastblock = udf_scan_anchors(sb, sbi->s_last_block); if (lastblock) goto check_anchor; /* No anchor found? Try VARCONV conversion of block numbers */ + UDF_SET_FLAG(sb, UDF_FLAG_VARCONV); /* Firstly, we try to not convert number of the last block */ - lastblock = udf_scan_anchors(sb, 1, + lastblock = udf_scan_anchors(sb, udf_variable_to_fixed(sbi->s_last_block)); - if (lastblock) { - UDF_SET_FLAG(sb, UDF_FLAG_VARCONV); + if (lastblock) goto check_anchor; - } /* Secondly, we try with converted number of the last block */ - lastblock = udf_scan_anchors(sb, 1, sbi->s_last_block); - if (lastblock) - UDF_SET_FLAG(sb, UDF_FLAG_VARCONV); + lastblock = udf_scan_anchors(sb, sbi->s_last_block); + if (!lastblock) { + /* VARCONV didn't help. Clear it. */ + UDF_CLEAR_FLAG(sb, UDF_FLAG_VARCONV); + } check_anchor: /* diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 8fa9c2d70911..8ec865de5f13 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -16,7 +16,7 @@ #define UDF_PREALLOCATE #define UDF_DEFAULT_PREALLOC_BLOCKS 8 -#define UDFFS_DEBUG +#undef UDFFS_DEBUG #ifdef UDFFS_DEBUG #define udf_debug(f, a...) \ diff --git a/fs/utimes.c b/fs/utimes.c index af059d5cb485..b6b664e7145e 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -40,14 +40,9 @@ asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times) #endif -static bool nsec_special(long nsec) -{ - return nsec == UTIME_OMIT || nsec == UTIME_NOW; -} - static bool nsec_valid(long nsec) { - if (nsec_special(nsec)) + if (nsec == UTIME_OMIT || nsec == UTIME_NOW) return true; return nsec >= 0 && nsec <= 999999999; @@ -102,7 +97,11 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags if (error) goto dput_and_out; - /* Don't worry, the checks are done in inode_change_ok() */ + if (times && times[0].tv_nsec == UTIME_NOW && + times[1].tv_nsec == UTIME_NOW) + times = NULL; + + /* In most cases, the checks are done in inode_change_ok() */ newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME; if (times) { error = -EPERM; @@ -124,28 +123,34 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags newattrs.ia_mtime.tv_nsec = times[1].tv_nsec; newattrs.ia_valid |= ATTR_MTIME_SET; } - } - /* - * If times is NULL or both times are either UTIME_OMIT or - * UTIME_NOW, then need to check permissions, because - * inode_change_ok() won't do it. - */ - if (!times || (nsec_special(times[0].tv_nsec) && - nsec_special(times[1].tv_nsec))) { + /* + * For the UTIME_OMIT/UTIME_NOW and UTIME_NOW/UTIME_OMIT + * cases, we need to make an extra check that is not done by + * inode_change_ok(). + */ + if (((times[0].tv_nsec == UTIME_NOW && + times[1].tv_nsec == UTIME_OMIT) + || + (times[0].tv_nsec == UTIME_OMIT && + times[1].tv_nsec == UTIME_NOW)) + && !is_owner_or_cap(inode)) + goto mnt_drop_write_and_out; + } else { + + /* + * If times is NULL (or both times are UTIME_NOW), + * then we need to check permissions, because + * inode_change_ok() won't do it. + */ error = -EACCES; if (IS_IMMUTABLE(inode)) goto mnt_drop_write_and_out; if (!is_owner_or_cap(inode)) { - if (f) { - if (!(f->f_mode & FMODE_WRITE)) - goto mnt_drop_write_and_out; - } else { - error = vfs_permission(&nd, MAY_WRITE); - if (error) - goto mnt_drop_write_and_out; - } + error = permission(inode, MAY_WRITE, NULL); + if (error) + goto mnt_drop_write_and_out; } } mutex_lock(&inode->i_mutex); @@ -169,14 +174,6 @@ asmlinkage long sys_utimensat(int dfd, char __user *filename, struct timespec __ if (utimes) { if (copy_from_user(&tstimes, utimes, sizeof(tstimes))) return -EFAULT; - if ((tstimes[0].tv_nsec == UTIME_OMIT || - tstimes[0].tv_nsec == UTIME_NOW) && - tstimes[0].tv_sec != 0) - return -EINVAL; - if ((tstimes[1].tv_nsec == UTIME_OMIT || - tstimes[1].tv_nsec == UTIME_NOW) && - tstimes[1].tv_sec != 0) - return -EINVAL; /* Nothing to do, we must not even check the path. */ if (tstimes[0].tv_nsec == UTIME_OMIT && |