diff options
Diffstat (limited to 'fs')
95 files changed, 2031 insertions, 1627 deletions
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 3263084eef9e..4a551af6f3fc 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -30,7 +30,7 @@ config COMPAT_BINFMT_ELF config BINFMT_ELF_FDPIC bool "Kernel support for FDPIC ELF binaries" default y - depends on (FRV || BLACKFIN) + depends on (FRV || BLACKFIN || (SUPERH32 && !MMU)) help ELF FDPIC binaries are based on ELF, but allow the individual load segments of a binary to be located in memory independently of each diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index d051a32e6270..54a526e57f9f 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -477,6 +477,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, char __user *u_platform, *p; long hwcap; int loop; + int nr; /* reset for each csp adjustment */ /* we're going to shovel a whole load of stuff onto the stack */ #ifdef CONFIG_MMU @@ -549,10 +550,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, /* force 16 byte _final_ alignment here for generality */ #define DLINFO_ITEMS 13 - nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0); -#ifdef DLINFO_ARCH_ITEMS - nitems += DLINFO_ARCH_ITEMS; -#endif + nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0) + AT_VECTOR_SIZE_ARCH; csp = sp; sp -= nitems * 2 * sizeof(unsigned long); @@ -564,39 +562,46 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, sp -= sp & 15UL; /* put the ELF interpreter info on the stack */ -#define NEW_AUX_ENT(nr, id, val) \ +#define NEW_AUX_ENT(id, val) \ do { \ struct { unsigned long _id, _val; } __user *ent; \ \ ent = (void __user *) csp; \ __put_user((id), &ent[nr]._id); \ __put_user((val), &ent[nr]._val); \ + nr++; \ } while (0) + nr = 0; csp -= 2 * sizeof(unsigned long); - NEW_AUX_ENT(0, AT_NULL, 0); + NEW_AUX_ENT(AT_NULL, 0); if (k_platform) { + nr = 0; csp -= 2 * sizeof(unsigned long); - NEW_AUX_ENT(0, AT_PLATFORM, + NEW_AUX_ENT(AT_PLATFORM, (elf_addr_t) (unsigned long) u_platform); } + nr = 0; csp -= DLINFO_ITEMS * 2 * sizeof(unsigned long); - NEW_AUX_ENT( 0, AT_HWCAP, hwcap); - NEW_AUX_ENT( 1, AT_PAGESZ, PAGE_SIZE); - NEW_AUX_ENT( 2, AT_CLKTCK, CLOCKS_PER_SEC); - NEW_AUX_ENT( 3, AT_PHDR, exec_params->ph_addr); - NEW_AUX_ENT( 4, AT_PHENT, sizeof(struct elf_phdr)); - NEW_AUX_ENT( 5, AT_PHNUM, exec_params->hdr.e_phnum); - NEW_AUX_ENT( 6, AT_BASE, interp_params->elfhdr_addr); - NEW_AUX_ENT( 7, AT_FLAGS, 0); - NEW_AUX_ENT( 8, AT_ENTRY, exec_params->entry_addr); - NEW_AUX_ENT( 9, AT_UID, (elf_addr_t) current->uid); - NEW_AUX_ENT(10, AT_EUID, (elf_addr_t) current->euid); - NEW_AUX_ENT(11, AT_GID, (elf_addr_t) current->gid); - NEW_AUX_ENT(12, AT_EGID, (elf_addr_t) current->egid); + NEW_AUX_ENT(AT_HWCAP, hwcap); + NEW_AUX_ENT(AT_PAGESZ, PAGE_SIZE); + NEW_AUX_ENT(AT_CLKTCK, CLOCKS_PER_SEC); + NEW_AUX_ENT(AT_PHDR, exec_params->ph_addr); + NEW_AUX_ENT(AT_PHENT, sizeof(struct elf_phdr)); + NEW_AUX_ENT(AT_PHNUM, exec_params->hdr.e_phnum); + NEW_AUX_ENT(AT_BASE, interp_params->elfhdr_addr); + NEW_AUX_ENT(AT_FLAGS, 0); + NEW_AUX_ENT(AT_ENTRY, exec_params->entry_addr); + NEW_AUX_ENT(AT_UID, (elf_addr_t) current->uid); + NEW_AUX_ENT(AT_EUID, (elf_addr_t) current->euid); + NEW_AUX_ENT(AT_GID, (elf_addr_t) current->gid); + NEW_AUX_ENT(AT_EGID, (elf_addr_t) current->egid); #ifdef ARCH_DLINFO + nr = 0; + csp -= AT_VECTOR_SIZE_ARCH * 2 * sizeof(unsigned long); + /* ARCH_DLINFO must come last so platform specific code can enforce * special alignment requirements on the AUXV if necessary (eg. PPC). */ 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/coda/psdev.c b/fs/coda/psdev.c index e3eb3556622b..40c36f7352a6 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -362,8 +362,9 @@ static int init_coda_psdev(void) goto out_chrdev; } for (i = 0; i < MAX_CODADEVS; i++) - device_create(coda_psdev_class, NULL, - MKDEV(CODA_PSDEV_MAJOR,i), "cfs%d", i); + device_create_drvdata(coda_psdev_class, NULL, + MKDEV(CODA_PSDEV_MAJOR, i), + NULL, "cfs%d", i); coda_sysctl_init(); goto out; diff --git a/fs/dcache.c b/fs/dcache.c index 3ee588d5f585..40e4d511c4ea 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1191,6 +1191,107 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) return new; } +/** + * d_add_ci - lookup or allocate new dentry with case-exact name + * @inode: the inode case-insensitive lookup has found + * @dentry: the negative dentry that was passed to the parent's lookup func + * @name: the case-exact name to be associated with the returned dentry + * + * This is to avoid filling the dcache with case-insensitive names to the + * same inode, only the actual correct case is stored in the dcache for + * case-insensitive filesystems. + * + * For a case-insensitive lookup match and if the the case-exact dentry + * already exists in in the dcache, use it and return it. + * + * If no entry exists with the exact case name, allocate new dentry with + * the exact case, and return the spliced entry. + */ +struct dentry *d_add_ci(struct inode *inode, struct dentry *dentry, + struct qstr *name) +{ + int error; + struct dentry *found; + struct dentry *new; + + /* Does a dentry matching the name exist already? */ + found = d_hash_and_lookup(dentry->d_parent, name); + /* If not, create it now and return */ + if (!found) { + new = d_alloc(dentry->d_parent, name); + if (!new) { + error = -ENOMEM; + goto err_out; + } + found = d_splice_alias(inode, new); + if (found) { + dput(new); + return found; + } + return new; + } + /* Matching dentry exists, check if it is negative. */ + if (found->d_inode) { + if (unlikely(found->d_inode != inode)) { + /* This can't happen because bad inodes are unhashed. */ + BUG_ON(!is_bad_inode(inode)); + BUG_ON(!is_bad_inode(found->d_inode)); + } + /* + * Already have the inode and the dentry attached, decrement + * the reference count to balance the iget() done + * earlier on. We found the dentry using d_lookup() so it + * cannot be disconnected and thus we do not need to worry + * about any NFS/disconnectedness issues here. + */ + iput(inode); + return found; + } + /* + * Negative dentry: instantiate it unless the inode is a directory and + * has a 'disconnected' dentry (i.e. IS_ROOT and DCACHE_DISCONNECTED), + * in which case d_move() that in place of the found dentry. + */ + if (!S_ISDIR(inode->i_mode)) { + /* Not a directory; everything is easy. */ + d_instantiate(found, inode); + return found; + } + spin_lock(&dcache_lock); + if (list_empty(&inode->i_dentry)) { + /* + * Directory without a 'disconnected' dentry; we need to do + * d_instantiate() by hand because it takes dcache_lock which + * we already hold. + */ + list_add(&found->d_alias, &inode->i_dentry); + found->d_inode = inode; + spin_unlock(&dcache_lock); + security_d_instantiate(found, inode); + return found; + } + /* + * Directory with a 'disconnected' dentry; get a reference to the + * 'disconnected' dentry. + */ + new = list_entry(inode->i_dentry.next, struct dentry, d_alias); + dget_locked(new); + spin_unlock(&dcache_lock); + /* Do security vodoo. */ + security_d_instantiate(found, inode); + /* Move new in place of found. */ + d_move(new, found); + /* Balance the iget() we did above. */ + iput(inode); + /* Throw away found. */ + dput(found); + /* Use new as the actual dentry. */ + return new; + +err_out: + iput(inode); + return ERR_PTR(error); +} /** * d_lookup - search for a dentry @@ -2228,6 +2329,7 @@ EXPORT_SYMBOL(d_path); EXPORT_SYMBOL(d_prune_aliases); EXPORT_SYMBOL(d_rehash); EXPORT_SYMBOL(d_splice_alias); +EXPORT_SYMBOL(d_add_ci); EXPORT_SYMBOL(d_validate); EXPORT_SYMBOL(dget_locked); EXPORT_SYMBOL(dput); diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 2d3d1027ce2b..7ba9586a0943 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1782,7 +1782,8 @@ static void grant_pending_locks(struct dlm_rsb *r) list_for_each_entry_safe(lkb, s, &r->res_grantqueue, lkb_statequeue) { if (lkb->lkb_bastfn && lock_requires_bast(lkb, high, cw)) { - if (cw && high == DLM_LOCK_PR) + if (cw && high == DLM_LOCK_PR && + lkb->lkb_grmode == DLM_LOCK_PR) queue_bast(r, lkb, DLM_LOCK_CW); else queue_bast(r, lkb, high); diff --git a/fs/dlm/user.c b/fs/dlm/user.c index ebbcf38fd33b..1aa76b32d056 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -538,7 +538,7 @@ static ssize_t device_write(struct file *file, const char __user *buf, /* do we really need this? can a write happen after a close? */ if ((kbuf->cmd == DLM_USER_LOCK || kbuf->cmd == DLM_USER_UNLOCK) && - test_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags)) + (proc && test_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags))) return -EINVAL; sigfillset(&allsigs); diff --git a/fs/jfs/jfs_debug.c b/fs/jfs/jfs_debug.c index bf6ab19b86ee..6a73de84bcef 100644 --- a/fs/jfs/jfs_debug.c +++ b/fs/jfs/jfs_debug.c @@ -21,6 +21,7 @@ #include <linux/ctype.h> #include <linux/module.h> #include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <asm/uaccess.h> #include "jfs_incore.h" #include "jfs_filsys.h" @@ -30,29 +31,19 @@ static struct proc_dir_entry *base; #ifdef CONFIG_JFS_DEBUG -static int loglevel_read(char *page, char **start, off_t off, - int count, int *eof, void *data) +static int jfs_loglevel_proc_show(struct seq_file *m, void *v) { - int len; - - len = sprintf(page, "%d\n", jfsloglevel); - - len -= off; - *start = page + off; - - if (len > count) - len = count; - else - *eof = 1; - - if (len < 0) - len = 0; + seq_printf(m, "%d\n", jfsloglevel); + return 0; +} - return len; +static int jfs_loglevel_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, jfs_loglevel_proc_show, NULL); } -static int loglevel_write(struct file *file, const char __user *buffer, - unsigned long count, void *data) +static ssize_t jfs_loglevel_proc_write(struct file *file, + const char __user *buffer, size_t count, loff_t *ppos) { char c; @@ -65,22 +56,30 @@ static int loglevel_write(struct file *file, const char __user *buffer, jfsloglevel = c - '0'; return count; } + +static const struct file_operations jfs_loglevel_proc_fops = { + .owner = THIS_MODULE, + .open = jfs_loglevel_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = jfs_loglevel_proc_write, +}; #endif static struct { const char *name; - read_proc_t *read_fn; - write_proc_t *write_fn; + const struct file_operations *proc_fops; } Entries[] = { #ifdef CONFIG_JFS_STATISTICS - { "lmstats", jfs_lmstats_read, }, - { "txstats", jfs_txstats_read, }, - { "xtstat", jfs_xtstat_read, }, - { "mpstat", jfs_mpstat_read, }, + { "lmstats", &jfs_lmstats_proc_fops, }, + { "txstats", &jfs_txstats_proc_fops, }, + { "xtstat", &jfs_xtstat_proc_fops, }, + { "mpstat", &jfs_mpstat_proc_fops, }, #endif #ifdef CONFIG_JFS_DEBUG - { "TxAnchor", jfs_txanchor_read, }, - { "loglevel", loglevel_read, loglevel_write } + { "TxAnchor", &jfs_txanchor_proc_fops, }, + { "loglevel", &jfs_loglevel_proc_fops } #endif }; #define NPROCENT ARRAY_SIZE(Entries) @@ -93,13 +92,8 @@ void jfs_proc_init(void) return; base->owner = THIS_MODULE; - for (i = 0; i < NPROCENT; i++) { - struct proc_dir_entry *p; - if ((p = create_proc_entry(Entries[i].name, 0, base))) { - p->read_proc = Entries[i].read_fn; - p->write_proc = Entries[i].write_fn; - } - } + for (i = 0; i < NPROCENT; i++) + proc_create(Entries[i].name, 0, base, Entries[i].proc_fops); } void jfs_proc_clean(void) diff --git a/fs/jfs/jfs_debug.h b/fs/jfs/jfs_debug.h index 044c1e654cc0..eafd1300a00b 100644 --- a/fs/jfs/jfs_debug.h +++ b/fs/jfs/jfs_debug.h @@ -62,7 +62,7 @@ extern void jfs_proc_clean(void); extern int jfsloglevel; -extern int jfs_txanchor_read(char *, char **, off_t, int, int *, void *); +extern const struct file_operations jfs_txanchor_proc_fops; /* information message: e.g., configuration, major event */ #define jfs_info(fmt, arg...) do { \ @@ -105,10 +105,10 @@ extern int jfs_txanchor_read(char *, char **, off_t, int, int *, void *); * ---------- */ #ifdef CONFIG_JFS_STATISTICS -extern int jfs_lmstats_read(char *, char **, off_t, int, int *, void *); -extern int jfs_txstats_read(char *, char **, off_t, int, int *, void *); -extern int jfs_mpstat_read(char *, char **, off_t, int, int *, void *); -extern int jfs_xtstat_read(char *, char **, off_t, int, int *, void *); +extern const struct file_operations jfs_lmstats_proc_fops; +extern const struct file_operations jfs_txstats_proc_fops; +extern const struct file_operations jfs_mpstat_proc_fops; +extern const struct file_operations jfs_xtstat_proc_fops; #define INCREMENT(x) ((x)++) #define DECREMENT(x) ((x)--) diff --git a/fs/jfs/jfs_dtree.h b/fs/jfs/jfs_dtree.h index cdac2d5bafeb..2545bb317235 100644 --- a/fs/jfs/jfs_dtree.h +++ b/fs/jfs/jfs_dtree.h @@ -243,9 +243,6 @@ typedef union { #define JFS_REMOVE 3 #define JFS_RENAME 4 -#define DIRENTSIZ(namlen) \ - ( (sizeof(struct dirent) - 2*(JFS_NAME_MAX+1) + 2*((namlen)+1) + 3) &~ 3 ) - /* * Maximum file offset for directories. */ diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 734ec916beaf..d6363d8309d0 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -1520,7 +1520,7 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip) jfs_error(ip->i_sb, "diAlloc: can't find free bit " "in wmap"); - return EIO; + return -EIO; } /* determine the inode number within the diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index 325a9679b95a..cd2ec2988b59 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -69,6 +69,7 @@ #include <linux/freezer.h> #include <linux/delay.h> #include <linux/mutex.h> +#include <linux/seq_file.h> #include "jfs_incore.h" #include "jfs_filsys.h" #include "jfs_metapage.h" @@ -2503,13 +2504,9 @@ exit: } #ifdef CONFIG_JFS_STATISTICS -int jfs_lmstats_read(char *buffer, char **start, off_t offset, int length, - int *eof, void *data) +static int jfs_lmstats_proc_show(struct seq_file *m, void *v) { - int len = 0; - off_t begin; - - len += sprintf(buffer, + seq_printf(m, "JFS Logmgr stats\n" "================\n" "commits = %d\n" @@ -2522,19 +2519,19 @@ int jfs_lmstats_read(char *buffer, char **start, off_t offset, int length, lmStat.pagedone, lmStat.full_page, lmStat.partial_page); + return 0; +} - begin = offset; - *start = buffer + begin; - len -= begin; - - if (len > length) - len = length; - else - *eof = 1; - - if (len < 0) - len = 0; - - return len; +static int jfs_lmstats_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, jfs_lmstats_proc_show, NULL); } + +const struct file_operations jfs_lmstats_proc_fops = { + .owner = THIS_MODULE, + .open = jfs_lmstats_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif /* CONFIG_JFS_STATISTICS */ diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index d1e64f2f2fcd..854ff0ec574f 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -19,10 +19,12 @@ #include <linux/fs.h> #include <linux/mm.h> +#include <linux/module.h> #include <linux/bio.h> #include <linux/init.h> #include <linux/buffer_head.h> #include <linux/mempool.h> +#include <linux/seq_file.h> #include "jfs_incore.h" #include "jfs_superblock.h" #include "jfs_filsys.h" @@ -804,13 +806,9 @@ void __invalidate_metapages(struct inode *ip, s64 addr, int len) } #ifdef CONFIG_JFS_STATISTICS -int jfs_mpstat_read(char *buffer, char **start, off_t offset, int length, - int *eof, void *data) +static int jfs_mpstat_proc_show(struct seq_file *m, void *v) { - int len = 0; - off_t begin; - - len += sprintf(buffer, + seq_printf(m, "JFS Metapage statistics\n" "=======================\n" "page allocations = %d\n" @@ -819,19 +817,19 @@ int jfs_mpstat_read(char *buffer, char **start, off_t offset, int length, mpStat.pagealloc, mpStat.pagefree, mpStat.lockwait); + return 0; +} - begin = offset; - *start = buffer + begin; - len -= begin; - - if (len > length) - len = length; - else - *eof = 1; - - if (len < 0) - len = 0; - - return len; +static int jfs_mpstat_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, jfs_mpstat_proc_show, NULL); } + +const struct file_operations jfs_mpstat_proc_fops = { + .owner = THIS_MODULE, + .open = jfs_mpstat_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index e7c60ae6b5b2..f26e4d03ada5 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -49,6 +49,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/kthread.h> +#include <linux/seq_file.h> #include "jfs_incore.h" #include "jfs_inode.h" #include "jfs_filsys.h" @@ -3009,11 +3010,8 @@ int jfs_sync(void *arg) } #if defined(CONFIG_PROC_FS) && defined(CONFIG_JFS_DEBUG) -int jfs_txanchor_read(char *buffer, char **start, off_t offset, int length, - int *eof, void *data) +static int jfs_txanchor_proc_show(struct seq_file *m, void *v) { - int len = 0; - off_t begin; char *freewait; char *freelockwait; char *lowlockwait; @@ -3025,7 +3023,7 @@ int jfs_txanchor_read(char *buffer, char **start, off_t offset, int length, lowlockwait = waitqueue_active(&TxAnchor.lowlockwait) ? "active" : "empty"; - len += sprintf(buffer, + seq_printf(m, "JFS TxAnchor\n" "============\n" "freetid = %d\n" @@ -3044,31 +3042,27 @@ int jfs_txanchor_read(char *buffer, char **start, off_t offset, int length, TxAnchor.tlocksInUse, jfs_tlocks_low, list_empty(&TxAnchor.unlock_queue) ? "" : "not "); + return 0; +} - begin = offset; - *start = buffer + begin; - len -= begin; - - if (len > length) - len = length; - else - *eof = 1; - - if (len < 0) - len = 0; - - return len; +static int jfs_txanchor_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, jfs_txanchor_proc_show, NULL); } + +const struct file_operations jfs_txanchor_proc_fops = { + .owner = THIS_MODULE, + .open = jfs_txanchor_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif #if defined(CONFIG_PROC_FS) && defined(CONFIG_JFS_STATISTICS) -int jfs_txstats_read(char *buffer, char **start, off_t offset, int length, - int *eof, void *data) +static int jfs_txstats_proc_show(struct seq_file *m, void *v) { - int len = 0; - off_t begin; - - len += sprintf(buffer, + seq_printf(m, "JFS TxStats\n" "===========\n" "calls to txBegin = %d\n" @@ -3089,19 +3083,19 @@ int jfs_txstats_read(char *buffer, char **start, off_t offset, int length, TxStat.txBeginAnon_lockslow, TxStat.txLockAlloc, TxStat.txLockAlloc_freelock); + return 0; +} - begin = offset; - *start = buffer + begin; - len -= begin; - - if (len > length) - len = length; - else - *eof = 1; - - if (len < 0) - len = 0; - - return len; +static int jfs_txstats_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, jfs_txstats_proc_show, NULL); } + +const struct file_operations jfs_txstats_proc_fops = { + .owner = THIS_MODULE, + .open = jfs_txstats_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif diff --git a/fs/jfs/jfs_xtree.c b/fs/jfs/jfs_xtree.c index 5a61ebf2cbcc..ae3acafb447b 100644 --- a/fs/jfs/jfs_xtree.c +++ b/fs/jfs/jfs_xtree.c @@ -20,7 +20,9 @@ */ #include <linux/fs.h> +#include <linux/module.h> #include <linux/quotaops.h> +#include <linux/seq_file.h> #include "jfs_incore.h" #include "jfs_filsys.h" #include "jfs_metapage.h" @@ -4134,13 +4136,9 @@ s64 xtTruncate_pmap(tid_t tid, struct inode *ip, s64 committed_size) } #ifdef CONFIG_JFS_STATISTICS -int jfs_xtstat_read(char *buffer, char **start, off_t offset, int length, - int *eof, void *data) +static int jfs_xtstat_proc_show(struct seq_file *m, void *v) { - int len = 0; - off_t begin; - - len += sprintf(buffer, + seq_printf(m, "JFS Xtree statistics\n" "====================\n" "searches = %d\n" @@ -4149,19 +4147,19 @@ int jfs_xtstat_read(char *buffer, char **start, off_t offset, int length, xtStat.search, xtStat.fastSearch, xtStat.split); + return 0; +} - begin = offset; - *start = buffer + begin; - len -= begin; - - if (len > length) - len = length; - else - *eof = 1; - - if (len < 0) - len = 0; - - return len; +static int jfs_xtstat_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, jfs_xtstat_proc_show, NULL); } + +const struct file_operations jfs_xtstat_proc_fops = { + .owner = THIS_MODULE, + .open = jfs_xtstat_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 0ba6778edaa2..2aba82386810 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -1455,7 +1455,7 @@ static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, struc free_UCSname(&key); if (rc == -ENOENT) { d_add(dentry, NULL); - return ERR_PTR(0); + return NULL; } else if (rc) { jfs_err("jfs_lookup: dtSearch returned %d", rc); return ERR_PTR(rc); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 50ea65451732..0288e6d7936a 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -499,7 +499,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) inode = jfs_iget(sb, ROOT_I); if (IS_ERR(inode)) { ret = PTR_ERR(inode); - goto out_no_root; + goto out_no_rw; } sb->s_root = d_alloc_root(inode); if (!sb->s_root) @@ -521,9 +521,8 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) return 0; out_no_root: - jfs_err("jfs_read_super: get root inode failed"); - if (inode) - iput(inode); + jfs_err("jfs_read_super: get root dentry failed"); + iput(inode); out_no_rw: rc = jfs_umount(sb); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index c309c881bd4e..313484380a9b 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -952,6 +952,7 @@ encode_op: out: nfsd4_release_compoundargs(args); cstate_free(cstate); + dprintk("nfsv4 compound returned %d\n", ntohl(status)); return status; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8799b8708188..bf11d6879ab4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1579,8 +1579,8 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct svc_fh *cur_fh, struct nfs4_sta } /* remember the open */ filp->f_mode |= open->op_share_access; - set_bit(open->op_share_access, &stp->st_access_bmap); - set_bit(open->op_share_deny, &stp->st_deny_bmap); + __set_bit(open->op_share_access, &stp->st_access_bmap); + __set_bit(open->op_share_deny, &stp->st_deny_bmap); return nfs_ok; } @@ -3249,12 +3249,14 @@ nfs4_state_shutdown(void) nfs4_unlock_state(); } +/* + * user_recovery_dirname is protected by the nfsd_mutex since it's only + * accessed when nfsd is starting. + */ static void nfs4_set_recdir(char *recdir) { - nfs4_lock_state(); strcpy(user_recovery_dirname, recdir); - nfs4_unlock_state(); } /* @@ -3278,6 +3280,12 @@ nfs4_reset_recoverydir(char *recdir) return status; } +char * +nfs4_recoverydir(void) +{ + return user_recovery_dirname; +} + /* * Called when leasetime is changed. * @@ -3286,11 +3294,12 @@ nfs4_reset_recoverydir(char *recdir) * we start to register any changes in lease time. If the administrator * really wants to change the lease time *now*, they can go ahead and bring * nfsd down and then back up again after changing the lease time. + * + * user_lease_time is protected by nfsd_mutex since it's only really accessed + * when nfsd is starting */ void nfs4_reset_lease(time_t leasetime) { - lock_kernel(); user_lease_time = leasetime; - unlock_kernel(); } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index c513bbdf2d36..9547ab636274 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1201,7 +1201,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) *p++ = htonl((u32)((n) >> 32)); \ *p++ = htonl((u32)(n)); \ } while (0) -#define WRITEMEM(ptr,nbytes) do { \ +#define WRITEMEM(ptr,nbytes) do if (nbytes > 0) { \ *(p + XDR_QUADLEN(nbytes) -1) = 0; \ memcpy(p, ptr, nbytes); \ p += XDR_QUADLEN(nbytes); \ diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 5ac00c4fee91..2c2eb8796c10 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -450,22 +450,26 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size) int i; int rv; int len; - int npools = nfsd_nrpools(); + int npools; int *nthreads; + mutex_lock(&nfsd_mutex); + npools = nfsd_nrpools(); if (npools == 0) { /* * NFS is shut down. The admin can start it by * writing to the threads file but NOT the pool_threads * file, sorry. Report zero threads. */ + mutex_unlock(&nfsd_mutex); strcpy(buf, "0\n"); return strlen(buf); } nthreads = kcalloc(npools, sizeof(int), GFP_KERNEL); + rv = -ENOMEM; if (nthreads == NULL) - return -ENOMEM; + goto out_free; if (size > 0) { for (i = 0; i < npools; i++) { @@ -496,14 +500,16 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size) mesg += len; } + mutex_unlock(&nfsd_mutex); return (mesg-buf); out_free: kfree(nthreads); + mutex_unlock(&nfsd_mutex); return rv; } -static ssize_t write_versions(struct file *file, char *buf, size_t size) +static ssize_t __write_versions(struct file *file, char *buf, size_t size) { /* * Format: @@ -566,14 +572,23 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size) return len; } -static ssize_t write_ports(struct file *file, char *buf, size_t size) +static ssize_t write_versions(struct file *file, char *buf, size_t size) +{ + ssize_t rv; + + mutex_lock(&nfsd_mutex); + rv = __write_versions(file, buf, size); + mutex_unlock(&nfsd_mutex); + return rv; +} + +static ssize_t __write_ports(struct file *file, char *buf, size_t size) { if (size == 0) { int len = 0; - lock_kernel(); + if (nfsd_serv) len = svc_xprt_names(nfsd_serv, buf, 0); - unlock_kernel(); return len; } /* Either a single 'fd' number is written, in which @@ -603,9 +618,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) /* Decrease the count, but don't shutdown the * the service */ - lock_kernel(); nfsd_serv->sv_nrthreads--; - unlock_kernel(); } return err < 0 ? err : 0; } @@ -614,10 +627,8 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) int len = 0; if (!toclose) return -ENOMEM; - lock_kernel(); if (nfsd_serv) len = svc_sock_names(buf, nfsd_serv, toclose); - unlock_kernel(); if (len >= 0) lockd_down(); kfree(toclose); @@ -655,7 +666,6 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) if (sscanf(&buf[1], "%15s %4d", transport, &port) == 2) { if (port == 0) return -EINVAL; - lock_kernel(); if (nfsd_serv) { xprt = svc_find_xprt(nfsd_serv, transport, AF_UNSPEC, port); @@ -666,13 +676,23 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) } else err = -ENOTCONN; } - unlock_kernel(); return err < 0 ? err : 0; } } return -EINVAL; } +static ssize_t write_ports(struct file *file, char *buf, size_t size) +{ + ssize_t rv; + + mutex_lock(&nfsd_mutex); + rv = __write_ports(file, buf, size); + mutex_unlock(&nfsd_mutex); + return rv; +} + + int nfsd_max_blksize; static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) @@ -691,13 +711,13 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) if (bsize > NFSSVC_MAXBLKSIZE) bsize = NFSSVC_MAXBLKSIZE; bsize &= ~(1024-1); - lock_kernel(); + mutex_lock(&nfsd_mutex); if (nfsd_serv && nfsd_serv->sv_nrthreads) { - unlock_kernel(); + mutex_unlock(&nfsd_mutex); return -EBUSY; } nfsd_max_blksize = bsize; - unlock_kernel(); + mutex_unlock(&nfsd_mutex); } return sprintf(buf, "%d\n", nfsd_max_blksize); } @@ -705,16 +725,17 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) #ifdef CONFIG_NFSD_V4 extern time_t nfs4_leasetime(void); -static ssize_t write_leasetime(struct file *file, char *buf, size_t size) +static ssize_t __write_leasetime(struct file *file, char *buf, size_t size) { /* if size > 10 seconds, call * nfs4_reset_lease() then write out the new lease (seconds) as reply */ char *mesg = buf; - int rv; + int rv, lease; if (size > 0) { - int lease; + if (nfsd_serv) + return -EBUSY; rv = get_int(&mesg, &lease); if (rv) return rv; @@ -726,24 +747,52 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size) return strlen(buf); } -static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) +static ssize_t write_leasetime(struct file *file, char *buf, size_t size) +{ + ssize_t rv; + + mutex_lock(&nfsd_mutex); + rv = __write_leasetime(file, buf, size); + mutex_unlock(&nfsd_mutex); + return rv; +} + +extern char *nfs4_recoverydir(void); + +static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size) { char *mesg = buf; char *recdir; int len, status; - if (size == 0 || size > PATH_MAX || buf[size-1] != '\n') - return -EINVAL; - buf[size-1] = 0; + if (size > 0) { + if (nfsd_serv) + return -EBUSY; + if (size > PATH_MAX || buf[size-1] != '\n') + return -EINVAL; + buf[size-1] = 0; - recdir = mesg; - len = qword_get(&mesg, recdir, size); - if (len <= 0) - return -EINVAL; + recdir = mesg; + len = qword_get(&mesg, recdir, size); + if (len <= 0) + return -EINVAL; - status = nfs4_reset_recoverydir(recdir); + status = nfs4_reset_recoverydir(recdir); + } + sprintf(buf, "%s\n", nfs4_recoverydir()); return strlen(buf); } + +static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) +{ + ssize_t rv; + + mutex_lock(&nfsd_mutex); + rv = __write_recoverydir(file, buf, size); + mutex_unlock(&nfsd_mutex); + return rv; +} + #endif /*----------------------------------------------------------------------------*/ diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 941041f4b136..26c81149d49a 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -21,6 +21,7 @@ #include <linux/smp_lock.h> #include <linux/freezer.h> #include <linux/fs_struct.h> +#include <linux/kthread.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/stats.h> @@ -44,20 +45,39 @@ * when not handling a request. i.e. when waiting */ #define SHUTDOWN_SIGS (sigmask(SIGKILL) | sigmask(SIGHUP) | sigmask(SIGINT) | sigmask(SIGQUIT)) -/* if the last thread dies with SIGHUP, then the exports table is - * left unchanged ( like 2.4-{0-9} ). Any other signal will clear - * the exports table (like 2.2). - */ -#define SIG_NOCLEAN SIGHUP extern struct svc_program nfsd_program; -static void nfsd(struct svc_rqst *rqstp); +static int nfsd(void *vrqstp); struct timeval nfssvc_boot; - struct svc_serv *nfsd_serv; static atomic_t nfsd_busy; static unsigned long nfsd_last_call; static DEFINE_SPINLOCK(nfsd_call_lock); +/* + * nfsd_mutex protects nfsd_serv -- both the pointer itself and the members + * of the svc_serv struct. In particular, ->sv_nrthreads but also to some + * extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt + * + * If (out side the lock) nfsd_serv is non-NULL, then it must point to a + * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0. That number + * of nfsd threads must exist and each must listed in ->sp_all_threads in each + * entry of ->sv_pools[]. + * + * Transitions of the thread count between zero and non-zero are of particular + * interest since the svc_serv needs to be created and initialized at that + * point, or freed. + * + * Finally, the nfsd_mutex also protects some of the global variables that are + * accessed when nfsd starts and that are settable via the write_* routines in + * nfsctl.c. In particular: + * + * user_recovery_dirname + * user_lease_time + * nfsd_versions + */ +DEFINE_MUTEX(nfsd_mutex); +struct svc_serv *nfsd_serv; + #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; static struct svc_version * nfsd_acl_version[] = { @@ -151,7 +171,6 @@ int nfsd_nrthreads(void) return nfsd_serv->sv_nrthreads; } -static int killsig; /* signal that was used to kill last nfsd */ static void nfsd_last_thread(struct svc_serv *serv) { /* When last nfsd thread exits we need to do some clean-up */ @@ -162,11 +181,9 @@ static void nfsd_last_thread(struct svc_serv *serv) nfsd_racache_shutdown(); nfs4_state_shutdown(); - printk(KERN_WARNING "nfsd: last server has exited\n"); - if (killsig != SIG_NOCLEAN) { - printk(KERN_WARNING "nfsd: unexporting all filesystems\n"); - nfsd_export_flush(); - } + printk(KERN_WARNING "nfsd: last server has exited, flushing export " + "cache\n"); + nfsd_export_flush(); } void nfsd_reset_versions(void) @@ -190,13 +207,14 @@ void nfsd_reset_versions(void) } } + int nfsd_create_serv(void) { int err = 0; - lock_kernel(); + + WARN_ON(!mutex_is_locked(&nfsd_mutex)); if (nfsd_serv) { svc_get(nfsd_serv); - unlock_kernel(); return 0; } if (nfsd_max_blksize == 0) { @@ -217,13 +235,11 @@ int nfsd_create_serv(void) } atomic_set(&nfsd_busy, 0); - nfsd_serv = svc_create_pooled(&nfsd_program, - nfsd_max_blksize, - nfsd_last_thread, - nfsd, SIG_NOCLEAN, THIS_MODULE); + nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, + nfsd_last_thread, nfsd, THIS_MODULE); if (nfsd_serv == NULL) err = -ENOMEM; - unlock_kernel(); + do_gettimeofday(&nfssvc_boot); /* record boot time */ return err; } @@ -282,6 +298,8 @@ int nfsd_set_nrthreads(int n, int *nthreads) int tot = 0; int err = 0; + WARN_ON(!mutex_is_locked(&nfsd_mutex)); + if (nfsd_serv == NULL || n <= 0) return 0; @@ -316,7 +334,6 @@ int nfsd_set_nrthreads(int n, int *nthreads) nthreads[0] = 1; /* apply the new numbers */ - lock_kernel(); svc_get(nfsd_serv); for (i = 0; i < n; i++) { err = svc_set_num_threads(nfsd_serv, &nfsd_serv->sv_pools[i], @@ -325,7 +342,6 @@ int nfsd_set_nrthreads(int n, int *nthreads) break; } svc_destroy(nfsd_serv); - unlock_kernel(); return err; } @@ -334,8 +350,8 @@ int nfsd_svc(unsigned short port, int nrservs) { int error; - - lock_kernel(); + + mutex_lock(&nfsd_mutex); dprintk("nfsd: creating service\n"); error = -EINVAL; if (nrservs <= 0) @@ -363,7 +379,7 @@ nfsd_svc(unsigned short port, int nrservs) failure: svc_destroy(nfsd_serv); /* Release server */ out: - unlock_kernel(); + mutex_unlock(&nfsd_mutex); return error; } @@ -391,18 +407,19 @@ update_thread_usage(int busy_threads) /* * This is the NFS server kernel thread */ -static void -nfsd(struct svc_rqst *rqstp) +static int +nfsd(void *vrqstp) { + struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp; struct fs_struct *fsp; - int err; sigset_t shutdown_mask, allowed_mask; + int err, preverr = 0; + unsigned int signo; /* Lock module and set up kernel thread */ - lock_kernel(); - daemonize("nfsd"); + mutex_lock(&nfsd_mutex); - /* After daemonize() this kernel thread shares current->fs + /* At this point, the thread shares current->fs * with the init process. We need to create files with a * umask of 0 instead of init's umask. */ fsp = copy_fs_struct(current->fs); @@ -417,11 +434,17 @@ nfsd(struct svc_rqst *rqstp) siginitsetinv(&shutdown_mask, SHUTDOWN_SIGS); siginitsetinv(&allowed_mask, ALLOWED_SIGS); - nfsdstats.th_cnt++; - - rqstp->rq_task = current; + /* + * thread is spawned with all signals set to SIG_IGN, re-enable + * the ones that matter + */ + for (signo = 1; signo <= _NSIG; signo++) { + if (!sigismember(&shutdown_mask, signo)) + allow_signal(signo); + } - unlock_kernel(); + nfsdstats.th_cnt++; + mutex_unlock(&nfsd_mutex); /* * We want less throttling in balance_dirty_pages() so that nfs to @@ -444,15 +467,25 @@ nfsd(struct svc_rqst *rqstp) */ while ((err = svc_recv(rqstp, 60*60*HZ)) == -EAGAIN) ; - if (err < 0) + if (err == -EINTR) break; + else if (err < 0) { + if (err != preverr) { + printk(KERN_WARNING "%s: unexpected error " + "from svc_recv (%d)\n", __func__, -err); + preverr = err; + } + schedule_timeout_uninterruptible(HZ); + continue; + } + update_thread_usage(atomic_read(&nfsd_busy)); atomic_inc(&nfsd_busy); /* Lock the export hash tables for reading. */ exp_readlock(); - /* Process request with signals blocked. */ + /* Process request with signals blocked. */ sigprocmask(SIG_SETMASK, &allowed_mask, NULL); svc_process(rqstp); @@ -463,22 +496,10 @@ nfsd(struct svc_rqst *rqstp) atomic_dec(&nfsd_busy); } - if (err != -EINTR) { - printk(KERN_WARNING "nfsd: terminating on error %d\n", -err); - } else { - unsigned int signo; - - for (signo = 1; signo <= _NSIG; signo++) - if (sigismember(¤t->pending.signal, signo) && - !sigismember(¤t->blocked, signo)) - break; - killsig = signo; - } /* Clear signals before calling svc_exit_thread() */ flush_signals(current); - lock_kernel(); - + mutex_lock(&nfsd_mutex); nfsdstats.th_cnt --; out: @@ -486,8 +507,9 @@ out: svc_exit_thread(rqstp); /* Release module */ - unlock_kernel(); + mutex_unlock(&nfsd_mutex); module_put_and_exit(0); + return 0; } static __be32 map_new_errors(u32 vers, __be32 nfserr) diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 6149e4b58c88..efef715135d3 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -401,7 +401,7 @@ void register_disk(struct gendisk *disk) disk->dev.parent = disk->driverfs_dev; disk->dev.devt = MKDEV(disk->major, disk->first_minor); - strlcpy(disk->dev.bus_id, disk->disk_name, KOBJ_NAME_LEN); + strlcpy(disk->dev.bus_id, disk->disk_name, BUS_ID_SIZE); /* ewww... some of these buggers have / in the name... */ s = strchr(disk->dev.bus_id, '/'); if (s) diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 7e277f2ad466..c652d469dc08 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -123,6 +123,11 @@ static int uptime_read_proc(char *page, char **start, off_t off, return proc_calc_metrics(page, start, off, count, eof, len); } +int __attribute__((weak)) arch_report_meminfo(char *page) +{ + return 0; +} + static int meminfo_read_proc(char *page, char **start, off_t off, int count, int *eof, void *data) { @@ -221,6 +226,8 @@ static int meminfo_read_proc(char *page, char **start, off_t off, len += hugetlb_report_meminfo(page + len); + len += arch_report_meminfo(page + len); + return proc_calc_metrics(page, start, off, count, eof, len); #undef K } @@ -472,6 +479,13 @@ static const struct file_operations proc_vmalloc_operations = { }; #endif +#ifndef arch_irq_stat_cpu +#define arch_irq_stat_cpu(cpu) 0 +#endif +#ifndef arch_irq_stat +#define arch_irq_stat() 0 +#endif + static int show_stat(struct seq_file *p, void *v) { int i; @@ -509,7 +523,9 @@ static int show_stat(struct seq_file *p, void *v) sum += temp; per_irq_sum[j] += temp; } + sum += arch_irq_stat_cpu(i); } + sum += arch_irq_stat(); seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", (unsigned long long)cputime64_to_clock_t(user), diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index e7735f643cd1..9db95a710e92 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -18,10 +18,18 @@ #include <linux/poll.h> #include <linux/list.h> #include <linux/mutex.h> +#include <linux/limits.h> #include <asm/uaccess.h> #include "sysfs.h" +/* used in crash dumps to help with debugging */ +static char last_sysfs_file[PATH_MAX]; +void sysfs_printk_last_file(void) +{ + printk(KERN_EMERG "last sysfs file: %s\n", last_sysfs_file); +} + /* * There's one sysfs_buffer for each open file and one * sysfs_open_dirent for each sysfs_dirent with one or more open @@ -327,6 +335,11 @@ static int sysfs_open_file(struct inode *inode, struct file *file) struct sysfs_buffer *buffer; struct sysfs_ops *ops; int error = -EACCES; + char *p; + + p = d_path(&file->f_path, last_sysfs_file, sizeof(last_sysfs_file)); + if (p) + memmove(last_sysfs_file, p, strlen(p) + 1); /* need attr_sd for attr and ops, its parent for kobj */ if (!sysfs_get_active_two(attr_sd)) diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 14f0023984d7..9f328d2420e7 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -22,7 +22,7 @@ /* Random magic number */ #define SYSFS_MAGIC 0x62656572 -static struct vfsmount *sysfs_mount; +struct vfsmount *sysfs_mount; struct super_block * sysfs_sb = NULL; struct kmem_cache *sysfs_dir_cachep; diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index ce4e15f8aaeb..2915959a4499 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -91,6 +91,7 @@ struct sysfs_addrm_cxt { extern struct sysfs_dirent sysfs_root; extern struct super_block *sysfs_sb; extern struct kmem_cache *sysfs_dir_cachep; +extern struct vfsmount *sysfs_mount; /* * dir.c diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c index 9b1bb17a0501..1cd3b55ee3d2 100644 --- a/fs/xfs/linux-2.6/kmem.c +++ b/fs/xfs/linux-2.6/kmem.c @@ -90,7 +90,7 @@ kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize, } void -kmem_free(void *ptr, size_t size) +kmem_free(const void *ptr) { if (!is_vmalloc_addr(ptr)) { kfree(ptr); @@ -100,7 +100,7 @@ kmem_free(void *ptr, size_t size) } void * -kmem_realloc(void *ptr, size_t newsize, size_t oldsize, +kmem_realloc(const void *ptr, size_t newsize, size_t oldsize, unsigned int __nocast flags) { void *new; @@ -110,7 +110,7 @@ kmem_realloc(void *ptr, size_t newsize, size_t oldsize, if (new) memcpy(new, ptr, ((oldsize < newsize) ? oldsize : newsize)); - kmem_free(ptr, oldsize); + kmem_free(ptr); } return new; } diff --git a/fs/xfs/linux-2.6/kmem.h b/fs/xfs/linux-2.6/kmem.h index 5e9564902976..3c9910103c52 100644 --- a/fs/xfs/linux-2.6/kmem.h +++ b/fs/xfs/linux-2.6/kmem.h @@ -57,8 +57,8 @@ kmem_flags_convert(unsigned int __nocast flags) extern void *kmem_alloc(size_t, unsigned int __nocast); extern void *kmem_zalloc(size_t, unsigned int __nocast); extern void *kmem_zalloc_greedy(size_t *, size_t, size_t, unsigned int __nocast); -extern void *kmem_realloc(void *, size_t, size_t, unsigned int __nocast); -extern void kmem_free(void *, size_t); +extern void *kmem_realloc(const void *, size_t, size_t, unsigned int __nocast); +extern void kmem_free(const void *); /* * Zone interfaces diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index a55c3b26d840..0b211cba1909 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -409,7 +409,6 @@ xfs_start_buffer_writeback( STATIC void xfs_start_page_writeback( struct page *page, - struct writeback_control *wbc, int clear_dirty, int buffers) { @@ -858,7 +857,7 @@ xfs_convert_page( done = 1; } } - xfs_start_page_writeback(page, wbc, !page_dirty, count); + xfs_start_page_writeback(page, !page_dirty, count); } return done; @@ -1130,7 +1129,7 @@ xfs_page_state_convert( SetPageUptodate(page); if (startio) - xfs_start_page_writeback(page, wbc, 1, count); + xfs_start_page_writeback(page, 1, count); if (ioend && iomap_valid) { offset = (iomap.iomap_offset + iomap.iomap_bsize - 1) >> diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 98e0e86093b4..9cc8f0213095 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -310,8 +310,7 @@ _xfs_buf_free_pages( xfs_buf_t *bp) { if (bp->b_pages != bp->b_page_array) { - kmem_free(bp->b_pages, - bp->b_page_count * sizeof(struct page *)); + kmem_free(bp->b_pages); } } @@ -1398,7 +1397,7 @@ STATIC void xfs_free_bufhash( xfs_buftarg_t *btp) { - kmem_free(btp->bt_hash, (1<<btp->bt_hashshift) * sizeof(xfs_bufhash_t)); + kmem_free(btp->bt_hash); btp->bt_hash = NULL; } @@ -1428,13 +1427,10 @@ xfs_unregister_buftarg( void xfs_free_buftarg( - xfs_buftarg_t *btp, - int external) + xfs_buftarg_t *btp) { xfs_flush_buftarg(btp, 1); xfs_blkdev_issue_flush(btp); - if (external) - xfs_blkdev_put(btp->bt_bdev); xfs_free_bufhash(btp); iput(btp->bt_mapping->host); @@ -1444,7 +1440,7 @@ xfs_free_buftarg( xfs_unregister_buftarg(btp); kthread_stop(btp->bt_task); - kmem_free(btp, sizeof(*btp)); + kmem_free(btp); } STATIC int @@ -1575,7 +1571,7 @@ xfs_alloc_buftarg( return btp; error: - kmem_free(btp, sizeof(*btp)); + kmem_free(btp); return NULL; } diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h index f948ec7ba9a4..29d1d4adc078 100644 --- a/fs/xfs/linux-2.6/xfs_buf.h +++ b/fs/xfs/linux-2.6/xfs_buf.h @@ -429,7 +429,7 @@ static inline void xfs_bdwrite(void *mp, xfs_buf_t *bp) * Handling of buftargs. */ extern xfs_buftarg_t *xfs_alloc_buftarg(struct block_device *, int); -extern void xfs_free_buftarg(xfs_buftarg_t *, int); +extern void xfs_free_buftarg(xfs_buftarg_t *); extern void xfs_wait_buftarg(xfs_buftarg_t *); extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int); extern int xfs_flush_buftarg(xfs_buftarg_t *, int); diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c index c672b3238b14..987fe84f7b13 100644 --- a/fs/xfs/linux-2.6/xfs_export.c +++ b/fs/xfs/linux-2.6/xfs_export.c @@ -215,7 +215,7 @@ xfs_fs_get_parent( struct xfs_inode *cip; struct dentry *parent; - error = xfs_lookup(XFS_I(child->d_inode), &xfs_name_dotdot, &cip); + error = xfs_lookup(XFS_I(child->d_inode), &xfs_name_dotdot, &cip, NULL); if (unlikely(error)) return ERR_PTR(-error); diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index 2bf287ef5489..b022251114d9 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -382,7 +382,7 @@ xfs_vn_lookup( return ERR_PTR(-ENAMETOOLONG); xfs_dentry_to_name(&name, dentry); - error = xfs_lookup(XFS_I(dir), &name, &cip); + error = xfs_lookup(XFS_I(dir), &name, &cip, NULL); if (unlikely(error)) { if (unlikely(error != ENOENT)) return ERR_PTR(-error); @@ -393,6 +393,46 @@ xfs_vn_lookup( return d_splice_alias(cip->i_vnode, dentry); } +STATIC struct dentry * +xfs_vn_ci_lookup( + struct inode *dir, + struct dentry *dentry, + struct nameidata *nd) +{ + struct xfs_inode *ip; + struct xfs_name xname; + struct xfs_name ci_name; + struct qstr dname; + int error; + + if (dentry->d_name.len >= MAXNAMELEN) + return ERR_PTR(-ENAMETOOLONG); + + xfs_dentry_to_name(&xname, dentry); + error = xfs_lookup(XFS_I(dir), &xname, &ip, &ci_name); + if (unlikely(error)) { + if (unlikely(error != ENOENT)) + return ERR_PTR(-error); + /* + * call d_add(dentry, NULL) here when d_drop_negative_children + * is called in xfs_vn_mknod (ie. allow negative dentries + * with CI filesystems). + */ + return NULL; + } + + /* if exact match, just splice and exit */ + if (!ci_name.name) + return d_splice_alias(ip->i_vnode, dentry); + + /* else case-insensitive match... */ + dname.name = ci_name.name; + dname.len = ci_name.len; + dentry = d_add_ci(ip->i_vnode, dentry, &dname); + kmem_free(ci_name.name); + return dentry; +} + STATIC int xfs_vn_link( struct dentry *old_dentry, @@ -740,15 +780,11 @@ xfs_vn_setxattr( char *attr = (char *)name; attrnames_t *namesp; int xflags = 0; - int error; namesp = attr_lookup_namespace(attr, attr_namespaces, ATTR_NAMECOUNT); if (!namesp) return -EOPNOTSUPP; attr += namesp->attr_namelen; - error = namesp->attr_capable(vp, NULL); - if (error) - return error; /* Convert Linux syscall to XFS internal ATTR flags */ if (flags & XATTR_CREATE) @@ -770,15 +806,11 @@ xfs_vn_getxattr( char *attr = (char *)name; attrnames_t *namesp; int xflags = 0; - ssize_t error; namesp = attr_lookup_namespace(attr, attr_namespaces, ATTR_NAMECOUNT); if (!namesp) return -EOPNOTSUPP; attr += namesp->attr_namelen; - error = namesp->attr_capable(vp, NULL); - if (error) - return error; /* Convert Linux syscall to XFS internal ATTR flags */ if (!size) { @@ -818,15 +850,12 @@ xfs_vn_removexattr( char *attr = (char *)name; attrnames_t *namesp; int xflags = 0; - int error; namesp = attr_lookup_namespace(attr, attr_namespaces, ATTR_NAMECOUNT); if (!namesp) return -EOPNOTSUPP; attr += namesp->attr_namelen; - error = namesp->attr_capable(vp, NULL); - if (error) - return error; + xflags |= namesp->attr_flag; return namesp->attr_remove(vp, attr, xflags); } @@ -904,6 +933,25 @@ const struct inode_operations xfs_dir_inode_operations = { .removexattr = xfs_vn_removexattr, }; +const struct inode_operations xfs_dir_ci_inode_operations = { + .create = xfs_vn_create, + .lookup = xfs_vn_ci_lookup, + .link = xfs_vn_link, + .unlink = xfs_vn_unlink, + .symlink = xfs_vn_symlink, + .mkdir = xfs_vn_mkdir, + .rmdir = xfs_vn_rmdir, + .mknod = xfs_vn_mknod, + .rename = xfs_vn_rename, + .permission = xfs_vn_permission, + .getattr = xfs_vn_getattr, + .setattr = xfs_vn_setattr, + .setxattr = xfs_vn_setxattr, + .getxattr = xfs_vn_getxattr, + .listxattr = xfs_vn_listxattr, + .removexattr = xfs_vn_removexattr, +}; + const struct inode_operations xfs_symlink_inode_operations = { .readlink = generic_readlink, .follow_link = xfs_vn_follow_link, diff --git a/fs/xfs/linux-2.6/xfs_iops.h b/fs/xfs/linux-2.6/xfs_iops.h index 14d0deb7afff..3b4df5863e4a 100644 --- a/fs/xfs/linux-2.6/xfs_iops.h +++ b/fs/xfs/linux-2.6/xfs_iops.h @@ -20,6 +20,7 @@ extern const struct inode_operations xfs_inode_operations; extern const struct inode_operations xfs_dir_inode_operations; +extern const struct inode_operations xfs_dir_ci_inode_operations; extern const struct inode_operations xfs_symlink_inode_operations; extern const struct file_operations xfs_file_operations; diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h index 4edc46915b57..aded57321b12 100644 --- a/fs/xfs/linux-2.6/xfs_linux.h +++ b/fs/xfs/linux-2.6/xfs_linux.h @@ -76,6 +76,7 @@ #include <linux/log2.h> #include <linux/spinlock.h> #include <linux/random.h> +#include <linux/ctype.h> #include <asm/page.h> #include <asm/div64.h> diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 742b2c7852c1..79c11aaf5423 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -52,6 +52,7 @@ #include "xfs_version.h" #include "xfs_log_priv.h" #include "xfs_trans_priv.h" +#include "xfs_filestream.h" #include <linux/namei.h> #include <linux/init.h> @@ -74,7 +75,10 @@ xfs_args_allocate( { struct xfs_mount_args *args; - args = kmem_zalloc(sizeof(struct xfs_mount_args), KM_SLEEP); + args = kzalloc(sizeof(struct xfs_mount_args), GFP_KERNEL); + if (!args) + return NULL; + args->logbufs = args->logbufsize = -1; strncpy(args->fsname, sb->s_id, MAXNAMELEN); @@ -314,6 +318,7 @@ xfs_parseargs( args->flags |= XFSMNT_ATTR2; } else if (!strcmp(this_char, MNTOPT_NOATTR2)) { args->flags &= ~XFSMNT_ATTR2; + args->flags |= XFSMNT_NOATTR2; } else if (!strcmp(this_char, MNTOPT_FILESTREAM)) { args->flags2 |= XFSMNT2_FILESTREAMS; } else if (!strcmp(this_char, MNTOPT_NOQUOTA)) { @@ -564,7 +569,10 @@ xfs_set_inodeops( inode->i_mapping->a_ops = &xfs_address_space_operations; break; case S_IFDIR: - inode->i_op = &xfs_dir_inode_operations; + if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb)) + inode->i_op = &xfs_dir_ci_inode_operations; + else + inode->i_op = &xfs_dir_inode_operations; inode->i_fop = &xfs_dir_file_operations; break; case S_IFLNK: @@ -764,6 +772,137 @@ xfs_blkdev_issue_flush( blkdev_issue_flush(buftarg->bt_bdev, NULL); } +STATIC void +xfs_close_devices( + struct xfs_mount *mp) +{ + if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) { + xfs_free_buftarg(mp->m_logdev_targp); + xfs_blkdev_put(mp->m_logdev_targp->bt_bdev); + } + if (mp->m_rtdev_targp) { + xfs_free_buftarg(mp->m_rtdev_targp); + xfs_blkdev_put(mp->m_rtdev_targp->bt_bdev); + } + xfs_free_buftarg(mp->m_ddev_targp); +} + +/* + * The file system configurations are: + * (1) device (partition) with data and internal log + * (2) logical volume with data and log subvolumes. + * (3) logical volume with data, log, and realtime subvolumes. + * + * We only have to handle opening the log and realtime volumes here if + * they are present. The data subvolume has already been opened by + * get_sb_bdev() and is stored in sb->s_bdev. + */ +STATIC int +xfs_open_devices( + struct xfs_mount *mp, + struct xfs_mount_args *args) +{ + struct block_device *ddev = mp->m_super->s_bdev; + struct block_device *logdev = NULL, *rtdev = NULL; + int error; + + /* + * Open real time and log devices - order is important. + */ + if (args->logname[0]) { + error = xfs_blkdev_get(mp, args->logname, &logdev); + if (error) + goto out; + } + + if (args->rtname[0]) { + error = xfs_blkdev_get(mp, args->rtname, &rtdev); + if (error) + goto out_close_logdev; + + if (rtdev == ddev || rtdev == logdev) { + cmn_err(CE_WARN, + "XFS: Cannot mount filesystem with identical rtdev and ddev/logdev."); + error = EINVAL; + goto out_close_rtdev; + } + } + + /* + * Setup xfs_mount buffer target pointers + */ + error = ENOMEM; + mp->m_ddev_targp = xfs_alloc_buftarg(ddev, 0); + if (!mp->m_ddev_targp) + goto out_close_rtdev; + + if (rtdev) { + mp->m_rtdev_targp = xfs_alloc_buftarg(rtdev, 1); + if (!mp->m_rtdev_targp) + goto out_free_ddev_targ; + } + + if (logdev && logdev != ddev) { + mp->m_logdev_targp = xfs_alloc_buftarg(logdev, 1); + if (!mp->m_logdev_targp) + goto out_free_rtdev_targ; + } else { + mp->m_logdev_targp = mp->m_ddev_targp; + } + + return 0; + + out_free_rtdev_targ: + if (mp->m_rtdev_targp) + xfs_free_buftarg(mp->m_rtdev_targp); + out_free_ddev_targ: + xfs_free_buftarg(mp->m_ddev_targp); + out_close_rtdev: + if (rtdev) + xfs_blkdev_put(rtdev); + out_close_logdev: + if (logdev && logdev != ddev) + xfs_blkdev_put(logdev); + out: + return error; +} + +/* + * Setup xfs_mount buffer target pointers based on superblock + */ +STATIC int +xfs_setup_devices( + struct xfs_mount *mp) +{ + int error; + + error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_blocksize, + mp->m_sb.sb_sectsize); + if (error) + return error; + + if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) { + unsigned int log_sector_size = BBSIZE; + + if (xfs_sb_version_hassector(&mp->m_sb)) + log_sector_size = mp->m_sb.sb_logsectsize; + error = xfs_setsize_buftarg(mp->m_logdev_targp, + mp->m_sb.sb_blocksize, + log_sector_size); + if (error) + return error; + } + if (mp->m_rtdev_targp) { + error = xfs_setsize_buftarg(mp->m_rtdev_targp, + mp->m_sb.sb_blocksize, + mp->m_sb.sb_sectsize); + if (error) + return error; + } + + return 0; +} + /* * XFS AIL push thread support */ @@ -1074,7 +1213,7 @@ xfssyncd( list_del(&work->w_list); if (work == &mp->m_sync_work) continue; - kmem_free(work, sizeof(struct bhv_vfs_sync_work)); + kmem_free(work); } } @@ -1086,14 +1225,63 @@ xfs_fs_put_super( struct super_block *sb) { struct xfs_mount *mp = XFS_M(sb); + struct xfs_inode *rip = mp->m_rootip; + int unmount_event_flags = 0; int error; kthread_stop(mp->m_sync_task); xfs_sync(mp, SYNC_ATTR | SYNC_DELWRI); - error = xfs_unmount(mp, 0, NULL); - if (error) - printk("XFS: unmount got error=%d\n", error); + +#ifdef HAVE_DMAPI + if (mp->m_flags & XFS_MOUNT_DMAPI) { + unmount_event_flags = + (mp->m_dmevmask & (1 << DM_EVENT_UNMOUNT)) ? + 0 : DM_FLAGS_UNWANTED; + /* + * Ignore error from dmapi here, first unmount is not allowed + * to fail anyway, and second we wouldn't want to fail a + * unmount because of dmapi. + */ + XFS_SEND_PREUNMOUNT(mp, rip, DM_RIGHT_NULL, rip, DM_RIGHT_NULL, + NULL, NULL, 0, 0, unmount_event_flags); + } +#endif + + /* + * Blow away any referenced inode in the filestreams cache. + * This can and will cause log traffic as inodes go inactive + * here. + */ + xfs_filestream_unmount(mp); + + XFS_bflush(mp->m_ddev_targp); + error = xfs_unmount_flush(mp, 0); + WARN_ON(error); + + IRELE(rip); + + /* + * If we're forcing a shutdown, typically because of a media error, + * we want to make sure we invalidate dirty pages that belong to + * referenced vnodes as well. + */ + if (XFS_FORCED_SHUTDOWN(mp)) { + error = xfs_sync(mp, SYNC_WAIT | SYNC_CLOSE); + ASSERT(error != EFSCORRUPTED); + } + + if (mp->m_flags & XFS_MOUNT_DMAPI) { + XFS_SEND_UNMOUNT(mp, rip, DM_RIGHT_NULL, 0, 0, + unmount_event_flags); + } + + xfs_unmountfs(mp); + xfs_icsb_destroy_counters(mp); + xfs_close_devices(mp); + xfs_qmops_put(mp); + xfs_dmops_put(mp); + kfree(mp); } STATIC void @@ -1216,13 +1404,35 @@ xfs_fs_remount( char *options) { struct xfs_mount *mp = XFS_M(sb); - struct xfs_mount_args *args = xfs_args_allocate(sb, 0); + struct xfs_mount_args *args; int error; + args = xfs_args_allocate(sb, 0); + if (!args) + return -ENOMEM; + error = xfs_parseargs(mp, options, args, 1); - if (!error) - error = xfs_mntupdate(mp, flags, args); - kmem_free(args, sizeof(*args)); + if (error) + goto out_free_args; + + if (!(*flags & MS_RDONLY)) { /* rw/ro -> rw */ + if (mp->m_flags & XFS_MOUNT_RDONLY) + mp->m_flags &= ~XFS_MOUNT_RDONLY; + if (args->flags & XFSMNT_BARRIER) { + mp->m_flags |= XFS_MOUNT_BARRIER; + xfs_mountfs_check_barriers(mp); + } else { + mp->m_flags &= ~XFS_MOUNT_BARRIER; + } + } else if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { /* rw -> ro */ + xfs_filestream_flush(mp); + xfs_sync(mp, SYNC_DATA_QUIESCE); + xfs_attr_quiesce(mp); + mp->m_flags |= XFS_MOUNT_RDONLY; + } + + out_free_args: + kfree(args); return -error; } @@ -1300,6 +1510,225 @@ xfs_fs_setxquota( Q_XSETPQLIM), id, (caddr_t)fdq); } +/* + * This function fills in xfs_mount_t fields based on mount args. + * Note: the superblock has _not_ yet been read in. + */ +STATIC int +xfs_start_flags( + struct xfs_mount_args *ap, + struct xfs_mount *mp) +{ + /* Values are in BBs */ + if ((ap->flags & XFSMNT_NOALIGN) != XFSMNT_NOALIGN) { + /* + * At this point the superblock has not been read + * in, therefore we do not know the block size. + * Before the mount call ends we will convert + * these to FSBs. + */ + mp->m_dalign = ap->sunit; + mp->m_swidth = ap->swidth; + } + + if (ap->logbufs != -1 && + ap->logbufs != 0 && + (ap->logbufs < XLOG_MIN_ICLOGS || + ap->logbufs > XLOG_MAX_ICLOGS)) { + cmn_err(CE_WARN, + "XFS: invalid logbufs value: %d [not %d-%d]", + ap->logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS); + return XFS_ERROR(EINVAL); + } + mp->m_logbufs = ap->logbufs; + if (ap->logbufsize != -1 && + ap->logbufsize != 0 && + (ap->logbufsize < XLOG_MIN_RECORD_BSIZE || + ap->logbufsize > XLOG_MAX_RECORD_BSIZE || + !is_power_of_2(ap->logbufsize))) { + cmn_err(CE_WARN, + "XFS: invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]", + ap->logbufsize); + return XFS_ERROR(EINVAL); + } + mp->m_logbsize = ap->logbufsize; + mp->m_fsname_len = strlen(ap->fsname) + 1; + mp->m_fsname = kmem_alloc(mp->m_fsname_len, KM_SLEEP); + strcpy(mp->m_fsname, ap->fsname); + if (ap->rtname[0]) { + mp->m_rtname = kmem_alloc(strlen(ap->rtname) + 1, KM_SLEEP); + strcpy(mp->m_rtname, ap->rtname); + } + if (ap->logname[0]) { + mp->m_logname = kmem_alloc(strlen(ap->logname) + 1, KM_SLEEP); + strcpy(mp->m_logname, ap->logname); + } + + if (ap->flags & XFSMNT_WSYNC) + mp->m_flags |= XFS_MOUNT_WSYNC; +#if XFS_BIG_INUMS + if (ap->flags & XFSMNT_INO64) { + mp->m_flags |= XFS_MOUNT_INO64; + mp->m_inoadd = XFS_INO64_OFFSET; + } +#endif + if (ap->flags & XFSMNT_RETERR) + mp->m_flags |= XFS_MOUNT_RETERR; + if (ap->flags & XFSMNT_NOALIGN) + mp->m_flags |= XFS_MOUNT_NOALIGN; + if (ap->flags & XFSMNT_SWALLOC) + mp->m_flags |= XFS_MOUNT_SWALLOC; + if (ap->flags & XFSMNT_OSYNCISOSYNC) + mp->m_flags |= XFS_MOUNT_OSYNCISOSYNC; + if (ap->flags & XFSMNT_32BITINODES) + mp->m_flags |= XFS_MOUNT_32BITINODES; + + if (ap->flags & XFSMNT_IOSIZE) { + if (ap->iosizelog > XFS_MAX_IO_LOG || + ap->iosizelog < XFS_MIN_IO_LOG) { + cmn_err(CE_WARN, + "XFS: invalid log iosize: %d [not %d-%d]", + ap->iosizelog, XFS_MIN_IO_LOG, + XFS_MAX_IO_LOG); + return XFS_ERROR(EINVAL); + } + + mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE; + mp->m_readio_log = mp->m_writeio_log = ap->iosizelog; + } + + if (ap->flags & XFSMNT_IKEEP) + mp->m_flags |= XFS_MOUNT_IKEEP; + if (ap->flags & XFSMNT_DIRSYNC) + mp->m_flags |= XFS_MOUNT_DIRSYNC; + if (ap->flags & XFSMNT_ATTR2) + mp->m_flags |= XFS_MOUNT_ATTR2; + if (ap->flags & XFSMNT_NOATTR2) + mp->m_flags |= XFS_MOUNT_NOATTR2; + + if (ap->flags2 & XFSMNT2_COMPAT_IOSIZE) + mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE; + + /* + * no recovery flag requires a read-only mount + */ + if (ap->flags & XFSMNT_NORECOVERY) { + if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { + cmn_err(CE_WARN, + "XFS: tried to mount a FS read-write without recovery!"); + return XFS_ERROR(EINVAL); + } + mp->m_flags |= XFS_MOUNT_NORECOVERY; + } + + if (ap->flags & XFSMNT_NOUUID) + mp->m_flags |= XFS_MOUNT_NOUUID; + if (ap->flags & XFSMNT_BARRIER) + mp->m_flags |= XFS_MOUNT_BARRIER; + else + mp->m_flags &= ~XFS_MOUNT_BARRIER; + + if (ap->flags2 & XFSMNT2_FILESTREAMS) + mp->m_flags |= XFS_MOUNT_FILESTREAMS; + + if (ap->flags & XFSMNT_DMAPI) + mp->m_flags |= XFS_MOUNT_DMAPI; + return 0; +} + +/* + * This function fills in xfs_mount_t fields based on mount args. + * Note: the superblock _has_ now been read in. + */ +STATIC int +xfs_finish_flags( + struct xfs_mount_args *ap, + struct xfs_mount *mp) +{ + int ronly = (mp->m_flags & XFS_MOUNT_RDONLY); + + /* Fail a mount where the logbuf is smaller then the log stripe */ + if (xfs_sb_version_haslogv2(&mp->m_sb)) { + if ((ap->logbufsize <= 0) && + (mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE)) { + mp->m_logbsize = mp->m_sb.sb_logsunit; + } else if (ap->logbufsize > 0 && + ap->logbufsize < mp->m_sb.sb_logsunit) { + cmn_err(CE_WARN, + "XFS: logbuf size must be greater than or equal to log stripe size"); + return XFS_ERROR(EINVAL); + } + } else { + /* Fail a mount if the logbuf is larger than 32K */ + if (ap->logbufsize > XLOG_BIG_RECORD_BSIZE) { + cmn_err(CE_WARN, + "XFS: logbuf size for version 1 logs must be 16K or 32K"); + return XFS_ERROR(EINVAL); + } + } + + /* + * mkfs'ed attr2 will turn on attr2 mount unless explicitly + * told by noattr2 to turn it off + */ + if (xfs_sb_version_hasattr2(&mp->m_sb) && + !(ap->flags & XFSMNT_NOATTR2)) + mp->m_flags |= XFS_MOUNT_ATTR2; + + /* + * prohibit r/w mounts of read-only filesystems + */ + if ((mp->m_sb.sb_flags & XFS_SBF_READONLY) && !ronly) { + cmn_err(CE_WARN, + "XFS: cannot mount a read-only filesystem as read-write"); + return XFS_ERROR(EROFS); + } + + /* + * check for shared mount. + */ + if (ap->flags & XFSMNT_SHARED) { + if (!xfs_sb_version_hasshared(&mp->m_sb)) + return XFS_ERROR(EINVAL); + + /* + * For IRIX 6.5, shared mounts must have the shared + * version bit set, have the persistent readonly + * field set, must be version 0 and can only be mounted + * read-only. + */ + if (!ronly || !(mp->m_sb.sb_flags & XFS_SBF_READONLY) || + (mp->m_sb.sb_shared_vn != 0)) + return XFS_ERROR(EINVAL); + + mp->m_flags |= XFS_MOUNT_SHARED; + + /* + * Shared XFS V0 can't deal with DMI. Return EINVAL. + */ + if (mp->m_sb.sb_shared_vn == 0 && (ap->flags & XFSMNT_DMAPI)) + return XFS_ERROR(EINVAL); + } + + if (ap->flags & XFSMNT_UQUOTA) { + mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE); + if (ap->flags & XFSMNT_UQUOTAENF) + mp->m_qflags |= XFS_UQUOTA_ENFD; + } + + if (ap->flags & XFSMNT_GQUOTA) { + mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE); + if (ap->flags & XFSMNT_GQUOTAENF) + mp->m_qflags |= XFS_OQUOTA_ENFD; + } else if (ap->flags & XFSMNT_PQUOTA) { + mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE); + if (ap->flags & XFSMNT_PQUOTAENF) + mp->m_qflags |= XFS_OQUOTA_ENFD; + } + + return 0; +} + STATIC int xfs_fs_fill_super( struct super_block *sb, @@ -1308,11 +1737,21 @@ xfs_fs_fill_super( { struct inode *root; struct xfs_mount *mp = NULL; - struct xfs_mount_args *args = xfs_args_allocate(sb, silent); - int error; + struct xfs_mount_args *args; + int flags = 0, error = ENOMEM; + + args = xfs_args_allocate(sb, silent); + if (!args) + return -ENOMEM; - mp = xfs_mount_init(); + mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL); + if (!mp) + goto out_free_args; + spin_lock_init(&mp->m_sb_lock); + mutex_init(&mp->m_ilock); + mutex_init(&mp->m_growlock); + atomic_set(&mp->m_active_trans, 0); INIT_LIST_HEAD(&mp->m_sync_list); spin_lock_init(&mp->m_sync_lock); init_waitqueue_head(&mp->m_wait_single_sync_task); @@ -1325,16 +1764,59 @@ xfs_fs_fill_super( error = xfs_parseargs(mp, (char *)data, args, 0); if (error) - goto fail_vfsop; + goto out_free_mp; sb_min_blocksize(sb, BBSIZE); sb->s_export_op = &xfs_export_operations; sb->s_qcop = &xfs_quotactl_operations; sb->s_op = &xfs_super_operations; - error = xfs_mount(mp, args, NULL); + error = xfs_dmops_get(mp, args); + if (error) + goto out_free_mp; + error = xfs_qmops_get(mp, args); + if (error) + goto out_put_dmops; + + if (args->flags & XFSMNT_QUIET) + flags |= XFS_MFSI_QUIET; + + error = xfs_open_devices(mp, args); + if (error) + goto out_put_qmops; + + if (xfs_icsb_init_counters(mp)) + mp->m_flags |= XFS_MOUNT_NO_PERCPU_SB; + + /* + * Setup flags based on mount(2) options and then the superblock + */ + error = xfs_start_flags(args, mp); + if (error) + goto out_destroy_counters; + error = xfs_readsb(mp, flags); + if (error) + goto out_destroy_counters; + error = xfs_finish_flags(args, mp); + if (error) + goto out_free_sb; + + error = xfs_setup_devices(mp); + if (error) + goto out_free_sb; + + if (mp->m_flags & XFS_MOUNT_BARRIER) + xfs_mountfs_check_barriers(mp); + + error = xfs_filestream_mount(mp); + if (error) + goto out_free_sb; + + error = xfs_mountfs(mp, flags); if (error) - goto fail_vfsop; + goto out_filestream_unmount; + + XFS_SEND_MOUNT(mp, DM_RIGHT_NULL, args->mtpt, args->fsname); sb->s_dirt = 1; sb->s_magic = XFS_SB_MAGIC; @@ -1369,10 +1851,27 @@ xfs_fs_fill_super( xfs_itrace_exit(XFS_I(sb->s_root->d_inode)); - kmem_free(args, sizeof(*args)); + kfree(args); return 0; -fail_vnrele: + out_filestream_unmount: + xfs_filestream_unmount(mp); + out_free_sb: + xfs_freesb(mp); + out_destroy_counters: + xfs_icsb_destroy_counters(mp); + xfs_close_devices(mp); + out_put_qmops: + xfs_qmops_put(mp); + out_put_dmops: + xfs_dmops_put(mp); + out_free_mp: + kfree(mp); + out_free_args: + kfree(args); + return -error; + + fail_vnrele: if (sb->s_root) { dput(sb->s_root); sb->s_root = NULL; @@ -1380,12 +1879,22 @@ fail_vnrele: iput(root); } -fail_unmount: - xfs_unmount(mp, 0, NULL); + fail_unmount: + /* + * Blow away any referenced inode in the filestreams cache. + * This can and will cause log traffic as inodes go inactive + * here. + */ + xfs_filestream_unmount(mp); -fail_vfsop: - kmem_free(args, sizeof(*args)); - return -error; + XFS_bflush(mp->m_ddev_targp); + error = xfs_unmount_flush(mp, 0); + WARN_ON(error); + + IRELE(mp->m_rootip); + + xfs_unmountfs(mp); + goto out_destroy_counters; } STATIC int @@ -1396,8 +1905,17 @@ xfs_fs_get_sb( void *data, struct vfsmount *mnt) { - return get_sb_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super, + int error; + + error = get_sb_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super, mnt); + if (!error) { + xfs_mount_t *mp = XFS_M(mnt->mnt_sb); + + mp->m_vfsmount = mnt; + } + + return error; } static struct super_operations xfs_super_operations = { diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/linux-2.6/xfs_super.h index 3efb7c6d3303..212bdc7a7897 100644 --- a/fs/xfs/linux-2.6/xfs_super.h +++ b/fs/xfs/linux-2.6/xfs_super.h @@ -107,9 +107,6 @@ extern void xfs_initialize_vnode(struct xfs_mount *mp, bhv_vnode_t *vp, extern void xfs_flush_inode(struct xfs_inode *); extern void xfs_flush_device(struct xfs_inode *); -extern int xfs_blkdev_get(struct xfs_mount *, const char *, - struct block_device **); -extern void xfs_blkdev_put(struct block_device *); extern void xfs_blkdev_issue_flush(struct xfs_buftarg *); extern const struct export_operations xfs_export_operations; diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c index 85df3288efd5..fc9f3fb39b7b 100644 --- a/fs/xfs/quota/xfs_dquot.c +++ b/fs/xfs/quota/xfs_dquot.c @@ -1435,8 +1435,7 @@ xfs_dqlock2( /* ARGSUSED */ int xfs_qm_dqpurge( - xfs_dquot_t *dqp, - uint flags) + xfs_dquot_t *dqp) { xfs_dqhash_t *thishash; xfs_mount_t *mp = dqp->q_mount; diff --git a/fs/xfs/quota/xfs_dquot.h b/fs/xfs/quota/xfs_dquot.h index 5c371a92e3e2..f7393bba4e95 100644 --- a/fs/xfs/quota/xfs_dquot.h +++ b/fs/xfs/quota/xfs_dquot.h @@ -164,7 +164,7 @@ extern void xfs_qm_dqprint(xfs_dquot_t *); extern void xfs_qm_dqdestroy(xfs_dquot_t *); extern int xfs_qm_dqflush(xfs_dquot_t *, uint); -extern int xfs_qm_dqpurge(xfs_dquot_t *, uint); +extern int xfs_qm_dqpurge(xfs_dquot_t *); extern void xfs_qm_dqunpin_wait(xfs_dquot_t *); extern int xfs_qm_dqlock_nowait(xfs_dquot_t *); extern int xfs_qm_dqflock_nowait(xfs_dquot_t *); diff --git a/fs/xfs/quota/xfs_dquot_item.c b/fs/xfs/quota/xfs_dquot_item.c index 36e05ca78412..08d2fc89e6a1 100644 --- a/fs/xfs/quota/xfs_dquot_item.c +++ b/fs/xfs/quota/xfs_dquot_item.c @@ -576,8 +576,8 @@ xfs_qm_qoffend_logitem_committed( * xfs_trans_delete_ail() drops the AIL lock. */ xfs_trans_delete_ail(qfs->qql_item.li_mountp, (xfs_log_item_t *)qfs); - kmem_free(qfs, sizeof(xfs_qoff_logitem_t)); - kmem_free(qfe, sizeof(xfs_qoff_logitem_t)); + kmem_free(qfs); + kmem_free(qfe); return (xfs_lsn_t)-1; } diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c index d31cce1165c5..26370a3128f5 100644 --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -192,8 +192,8 @@ xfs_qm_destroy( xfs_qm_list_destroy(&(xqm->qm_usr_dqhtable[i])); xfs_qm_list_destroy(&(xqm->qm_grp_dqhtable[i])); } - kmem_free(xqm->qm_usr_dqhtable, hsize * sizeof(xfs_dqhash_t)); - kmem_free(xqm->qm_grp_dqhtable, hsize * sizeof(xfs_dqhash_t)); + kmem_free(xqm->qm_usr_dqhtable); + kmem_free(xqm->qm_grp_dqhtable); xqm->qm_usr_dqhtable = NULL; xqm->qm_grp_dqhtable = NULL; xqm->qm_dqhashmask = 0; @@ -201,7 +201,7 @@ xfs_qm_destroy( #ifdef DEBUG mutex_destroy(&qcheck_lock); #endif - kmem_free(xqm, sizeof(xfs_qm_t)); + kmem_free(xqm); } /* @@ -631,7 +631,7 @@ xfs_qm_dqpurge_int( * freelist in INACTIVE state. */ nextdqp = dqp->MPL_NEXT; - nmisses += xfs_qm_dqpurge(dqp, flags); + nmisses += xfs_qm_dqpurge(dqp); dqp = nextdqp; } xfs_qm_mplist_unlock(mp); @@ -1134,7 +1134,7 @@ xfs_qm_init_quotainfo( * and change the superblock accordingly. */ if ((error = xfs_qm_init_quotainos(mp))) { - kmem_free(qinf, sizeof(xfs_quotainfo_t)); + kmem_free(qinf); mp->m_quotainfo = NULL; return error; } @@ -1248,7 +1248,7 @@ xfs_qm_destroy_quotainfo( qi->qi_gquotaip = NULL; } mutex_destroy(&qi->qi_quotaofflock); - kmem_free(qi, sizeof(xfs_quotainfo_t)); + kmem_free(qi); mp->m_quotainfo = NULL; } @@ -1623,7 +1623,7 @@ xfs_qm_dqiterate( break; } while (nmaps > 0); - kmem_free(map, XFS_DQITER_MAP_SIZE * sizeof(*map)); + kmem_free(map); return error; } diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c index 768a3b27d2b6..413671523cb5 100644 --- a/fs/xfs/quota/xfs_qm_syscalls.c +++ b/fs/xfs/quota/xfs_qm_syscalls.c @@ -1449,14 +1449,14 @@ xfs_qm_internalqcheck( for (d = (xfs_dqtest_t *) h1->qh_next; d != NULL; ) { xfs_dqtest_cmp(d); e = (xfs_dqtest_t *) d->HL_NEXT; - kmem_free(d, sizeof(xfs_dqtest_t)); + kmem_free(d); d = e; } h1 = &qmtest_gdqtab[i]; for (d = (xfs_dqtest_t *) h1->qh_next; d != NULL; ) { xfs_dqtest_cmp(d); e = (xfs_dqtest_t *) d->HL_NEXT; - kmem_free(d, sizeof(xfs_dqtest_t)); + kmem_free(d); d = e; } } @@ -1467,8 +1467,8 @@ xfs_qm_internalqcheck( } else { cmn_err(CE_DEBUG, "******** quotacheck successful! ********"); } - kmem_free(qmtest_udqtab, qmtest_hashmask * sizeof(xfs_dqhash_t)); - kmem_free(qmtest_gdqtab, qmtest_hashmask * sizeof(xfs_dqhash_t)); + kmem_free(qmtest_udqtab); + kmem_free(qmtest_gdqtab); mutex_unlock(&qcheck_lock); return (qmtest_nfails); } diff --git a/fs/xfs/support/ktrace.c b/fs/xfs/support/ktrace.c index 0b75d302508f..a34ef05489b1 100644 --- a/fs/xfs/support/ktrace.c +++ b/fs/xfs/support/ktrace.c @@ -89,7 +89,7 @@ ktrace_alloc(int nentries, unsigned int __nocast sleep) if (sleep & KM_SLEEP) panic("ktrace_alloc: NULL memory on KM_SLEEP request!"); - kmem_free(ktp, sizeof(*ktp)); + kmem_free(ktp); return NULL; } @@ -126,7 +126,7 @@ ktrace_free(ktrace_t *ktp) } else { entries_size = (int)(ktp->kt_nentries * sizeof(ktrace_entry_t)); - kmem_free(ktp->kt_entries, entries_size); + kmem_free(ktp->kt_entries); } kmem_zone_free(ktrace_hdr_zone, ktp); diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c index df151a859186..557dad611de0 100644 --- a/fs/xfs/xfs_attr.c +++ b/fs/xfs/xfs_attr.c @@ -241,8 +241,7 @@ xfs_attr_set_int(xfs_inode_t *dp, struct xfs_name *name, args.firstblock = &firstblock; args.flist = &flist; args.whichfork = XFS_ATTR_FORK; - args.addname = 1; - args.oknoent = 1; + args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT; /* * Determine space new attribute will use, and if it would be @@ -974,7 +973,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) xfs_da_brelse(args->trans, bp); return(retval); } - args->rename = 1; /* an atomic rename */ + args->op_flags |= XFS_DA_OP_RENAME; /* an atomic rename */ args->blkno2 = args->blkno; /* set 2nd entry info*/ args->index2 = args->index; args->rmtblkno2 = args->rmtblkno; @@ -1054,7 +1053,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) * so that one disappears and one appears atomically. Then we * must remove the "old" attribute/value pair. */ - if (args->rename) { + if (args->op_flags & XFS_DA_OP_RENAME) { /* * In a separate transaction, set the incomplete flag on the * "old" attr and clear the incomplete flag on the "new" attr. @@ -1307,7 +1306,7 @@ restart: } else if (retval == EEXIST) { if (args->flags & ATTR_CREATE) goto out; - args->rename = 1; /* atomic rename op */ + args->op_flags |= XFS_DA_OP_RENAME; /* atomic rename op */ args->blkno2 = args->blkno; /* set 2nd entry info*/ args->index2 = args->index; args->rmtblkno2 = args->rmtblkno; @@ -1425,7 +1424,7 @@ restart: * so that one disappears and one appears atomically. Then we * must remove the "old" attribute/value pair. */ - if (args->rename) { + if (args->op_flags & XFS_DA_OP_RENAME) { /* * In a separate transaction, set the incomplete flag on the * "old" attr and clear the incomplete flag on the "new" attr. @@ -2300,23 +2299,7 @@ xfs_attr_rmtval_remove(xfs_da_args_t *args) void xfs_attr_trace_l_c(char *where, struct xfs_attr_list_context *context) { - xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_C, where, - (__psunsigned_t)context->dp, - (__psunsigned_t)context->cursor->hashval, - (__psunsigned_t)context->cursor->blkno, - (__psunsigned_t)context->cursor->offset, - (__psunsigned_t)context->alist, - (__psunsigned_t)context->bufsize, - (__psunsigned_t)context->count, - (__psunsigned_t)context->firstu, - (__psunsigned_t) - ((context->count > 0) && - !(context->flags & (ATTR_KERNAMELS|ATTR_KERNOVAL))) - ? (ATTR_ENTRY(context->alist, - context->count-1)->a_valuelen) - : 0, - (__psunsigned_t)context->dupcnt, - (__psunsigned_t)context->flags, + xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_C, where, context, (__psunsigned_t)NULL, (__psunsigned_t)NULL, (__psunsigned_t)NULL); @@ -2329,23 +2312,7 @@ void xfs_attr_trace_l_cn(char *where, struct xfs_attr_list_context *context, struct xfs_da_intnode *node) { - xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CN, where, - (__psunsigned_t)context->dp, - (__psunsigned_t)context->cursor->hashval, - (__psunsigned_t)context->cursor->blkno, - (__psunsigned_t)context->cursor->offset, - (__psunsigned_t)context->alist, - (__psunsigned_t)context->bufsize, - (__psunsigned_t)context->count, - (__psunsigned_t)context->firstu, - (__psunsigned_t) - ((context->count > 0) && - !(context->flags & (ATTR_KERNAMELS|ATTR_KERNOVAL))) - ? (ATTR_ENTRY(context->alist, - context->count-1)->a_valuelen) - : 0, - (__psunsigned_t)context->dupcnt, - (__psunsigned_t)context->flags, + xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CN, where, context, (__psunsigned_t)be16_to_cpu(node->hdr.count), (__psunsigned_t)be32_to_cpu(node->btree[0].hashval), (__psunsigned_t)be32_to_cpu(node->btree[ @@ -2359,23 +2326,7 @@ void xfs_attr_trace_l_cb(char *where, struct xfs_attr_list_context *context, struct xfs_da_node_entry *btree) { - xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CB, where, - (__psunsigned_t)context->dp, - (__psunsigned_t)context->cursor->hashval, - (__psunsigned_t)context->cursor->blkno, - (__psunsigned_t)context->cursor->offset, - (__psunsigned_t)context->alist, - (__psunsigned_t)context->bufsize, - (__psunsigned_t)context->count, - (__psunsigned_t)context->firstu, - (__psunsigned_t) - ((context->count > 0) && - !(context->flags & (ATTR_KERNAMELS|ATTR_KERNOVAL))) - ? (ATTR_ENTRY(context->alist, - context->count-1)->a_valuelen) - : 0, - (__psunsigned_t)context->dupcnt, - (__psunsigned_t)context->flags, + xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CB, where, context, (__psunsigned_t)be32_to_cpu(btree->hashval), (__psunsigned_t)be32_to_cpu(btree->before), (__psunsigned_t)NULL); @@ -2388,23 +2339,7 @@ void xfs_attr_trace_l_cl(char *where, struct xfs_attr_list_context *context, struct xfs_attr_leafblock *leaf) { - xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CL, where, - (__psunsigned_t)context->dp, - (__psunsigned_t)context->cursor->hashval, - (__psunsigned_t)context->cursor->blkno, - (__psunsigned_t)context->cursor->offset, - (__psunsigned_t)context->alist, - (__psunsigned_t)context->bufsize, - (__psunsigned_t)context->count, - (__psunsigned_t)context->firstu, - (__psunsigned_t) - ((context->count > 0) && - !(context->flags & (ATTR_KERNAMELS|ATTR_KERNOVAL))) - ? (ATTR_ENTRY(context->alist, - context->count-1)->a_valuelen) - : 0, - (__psunsigned_t)context->dupcnt, - (__psunsigned_t)context->flags, + xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CL, where, context, (__psunsigned_t)be16_to_cpu(leaf->hdr.count), (__psunsigned_t)be32_to_cpu(leaf->entries[0].hashval), (__psunsigned_t)be32_to_cpu(leaf->entries[ @@ -2417,22 +2352,30 @@ xfs_attr_trace_l_cl(char *where, struct xfs_attr_list_context *context, */ void xfs_attr_trace_enter(int type, char *where, - __psunsigned_t a2, __psunsigned_t a3, - __psunsigned_t a4, __psunsigned_t a5, - __psunsigned_t a6, __psunsigned_t a7, - __psunsigned_t a8, __psunsigned_t a9, - __psunsigned_t a10, __psunsigned_t a11, - __psunsigned_t a12, __psunsigned_t a13, - __psunsigned_t a14, __psunsigned_t a15) + struct xfs_attr_list_context *context, + __psunsigned_t a13, __psunsigned_t a14, + __psunsigned_t a15) { ASSERT(xfs_attr_trace_buf); ktrace_enter(xfs_attr_trace_buf, (void *)((__psunsigned_t)type), - (void *)where, - (void *)a2, (void *)a3, (void *)a4, - (void *)a5, (void *)a6, (void *)a7, - (void *)a8, (void *)a9, (void *)a10, - (void *)a11, (void *)a12, (void *)a13, - (void *)a14, (void *)a15); + (void *)((__psunsigned_t)where), + (void *)((__psunsigned_t)context->dp), + (void *)((__psunsigned_t)context->cursor->hashval), + (void *)((__psunsigned_t)context->cursor->blkno), + (void *)((__psunsigned_t)context->cursor->offset), + (void *)((__psunsigned_t)context->alist), + (void *)((__psunsigned_t)context->bufsize), + (void *)((__psunsigned_t)context->count), + (void *)((__psunsigned_t)context->firstu), + (void *)((__psunsigned_t) + (((context->count > 0) && + !(context->flags & (ATTR_KERNAMELS|ATTR_KERNOVAL))) + ? (ATTR_ENTRY(context->alist, + context->count-1)->a_valuelen) + : 0)), + (void *)((__psunsigned_t)context->dupcnt), + (void *)((__psunsigned_t)context->flags), + (void *)a13, (void *)a14, (void *)a15); } #endif /* XFS_ATTR_TRACE */ @@ -2622,43 +2565,6 @@ attr_lookup_namespace( return NULL; } -/* - * Some checks to prevent people abusing EAs to get over quota: - * - Don't allow modifying user EAs on devices/symlinks; - * - Don't allow modifying user EAs if sticky bit set; - */ -STATIC int -attr_user_capable( - bhv_vnode_t *vp, - cred_t *cred) -{ - struct inode *inode = vn_to_inode(vp); - - if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) - return -EPERM; - if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode) && - !capable(CAP_SYS_ADMIN)) - return -EPERM; - if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) && - (current_fsuid(cred) != inode->i_uid) && !capable(CAP_FOWNER)) - return -EPERM; - return 0; -} - -STATIC int -attr_trusted_capable( - bhv_vnode_t *vp, - cred_t *cred) -{ - struct inode *inode = vn_to_inode(vp); - - if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) - return -EPERM; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - return 0; -} - STATIC int attr_system_set( bhv_vnode_t *vp, char *name, void *data, size_t size, int xflags) @@ -2709,7 +2615,6 @@ struct attrnames attr_system = { .attr_get = attr_system_get, .attr_set = attr_system_set, .attr_remove = attr_system_remove, - .attr_capable = (attrcapable_t)fs_noerr, }; struct attrnames attr_trusted = { @@ -2719,7 +2624,6 @@ struct attrnames attr_trusted = { .attr_get = attr_generic_get, .attr_set = attr_generic_set, .attr_remove = attr_generic_remove, - .attr_capable = attr_trusted_capable, }; struct attrnames attr_secure = { @@ -2729,7 +2633,6 @@ struct attrnames attr_secure = { .attr_get = attr_generic_get, .attr_set = attr_generic_set, .attr_remove = attr_generic_remove, - .attr_capable = (attrcapable_t)fs_noerr, }; struct attrnames attr_user = { @@ -2738,7 +2641,6 @@ struct attrnames attr_user = { .attr_get = attr_generic_get, .attr_set = attr_generic_set, .attr_remove = attr_generic_remove, - .attr_capable = attr_user_capable, }; struct attrnames *attr_namespaces[] = diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h index 6cfc9384fe35..9b96d171b75c 100644 --- a/fs/xfs/xfs_attr.h +++ b/fs/xfs/xfs_attr.h @@ -42,7 +42,6 @@ typedef int (*attrset_t)(bhv_vnode_t *, char *, void *, size_t, int); typedef int (*attrget_t)(bhv_vnode_t *, char *, void *, size_t, int); typedef int (*attrremove_t)(bhv_vnode_t *, char *, int); typedef int (*attrexists_t)(bhv_vnode_t *); -typedef int (*attrcapable_t)(bhv_vnode_t *, struct cred *); typedef struct attrnames { char * attr_name; @@ -52,7 +51,6 @@ typedef struct attrnames { attrset_t attr_set; attrremove_t attr_remove; attrexists_t attr_exists; - attrcapable_t attr_capable; } attrnames_t; #define ATTR_NAMECOUNT 4 diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index 303d41e4217b..cb345e6e4850 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -369,9 +369,10 @@ xfs_attr_shortform_remove(xfs_da_args_t *args) * Fix up the start offset of the attribute fork */ totsize -= size; - if (totsize == sizeof(xfs_attr_sf_hdr_t) && !args->addname && - (mp->m_flags & XFS_MOUNT_ATTR2) && - (dp->i_d.di_format != XFS_DINODE_FMT_BTREE)) { + if (totsize == sizeof(xfs_attr_sf_hdr_t) && + !(args->op_flags & XFS_DA_OP_ADDNAME) && + (mp->m_flags & XFS_MOUNT_ATTR2) && + (dp->i_d.di_format != XFS_DINODE_FMT_BTREE)) { /* * Last attribute now removed, revert to original * inode format making all literal area available @@ -389,9 +390,10 @@ xfs_attr_shortform_remove(xfs_da_args_t *args) xfs_idata_realloc(dp, -size, XFS_ATTR_FORK); dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize); ASSERT(dp->i_d.di_forkoff); - ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) || args->addname || - !(mp->m_flags & XFS_MOUNT_ATTR2) || - dp->i_d.di_format == XFS_DINODE_FMT_BTREE); + ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) || + (args->op_flags & XFS_DA_OP_ADDNAME) || + !(mp->m_flags & XFS_MOUNT_ATTR2) || + dp->i_d.di_format == XFS_DINODE_FMT_BTREE); dp->i_afp->if_ext_max = XFS_IFORK_ASIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t); dp->i_df.if_ext_max = @@ -531,7 +533,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args) nargs.total = args->total; nargs.whichfork = XFS_ATTR_FORK; nargs.trans = args->trans; - nargs.oknoent = 1; + nargs.op_flags = XFS_DA_OP_OKNOENT; sfe = &sf->list[0]; for (i = 0; i < sf->hdr.count; i++) { @@ -555,7 +557,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args) out: if(bp) xfs_da_buf_done(bp); - kmem_free(tmpbuffer, size); + kmem_free(tmpbuffer); return(error); } @@ -676,7 +678,7 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context) XFS_ERRLEVEL_LOW, context->dp->i_mount, sfe); xfs_attr_trace_l_c("sf corrupted", context); - kmem_free(sbuf, sbsize); + kmem_free(sbuf); return XFS_ERROR(EFSCORRUPTED); } if (!xfs_attr_namesp_match_overrides(context->flags, sfe->flags)) { @@ -717,7 +719,7 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context) } } if (i == nsbuf) { - kmem_free(sbuf, sbsize); + kmem_free(sbuf); xfs_attr_trace_l_c("blk end", context); return(0); } @@ -747,7 +749,7 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context) cursor->offset++; } - kmem_free(sbuf, sbsize); + kmem_free(sbuf); xfs_attr_trace_l_c("sf E-O-F", context); return(0); } @@ -853,7 +855,7 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff) nargs.total = args->total; nargs.whichfork = XFS_ATTR_FORK; nargs.trans = args->trans; - nargs.oknoent = 1; + nargs.op_flags = XFS_DA_OP_OKNOENT; entry = &leaf->entries[0]; for (i = 0; i < be16_to_cpu(leaf->hdr.count); entry++, i++) { if (entry->flags & XFS_ATTR_INCOMPLETE) @@ -873,7 +875,7 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff) error = 0; out: - kmem_free(tmpbuffer, XFS_LBSIZE(dp->i_mount)); + kmem_free(tmpbuffer); return(error); } @@ -1155,7 +1157,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex) entry->hashval = cpu_to_be32(args->hashval); entry->flags = tmp ? XFS_ATTR_LOCAL : 0; entry->flags |= XFS_ATTR_NSP_ARGS_TO_ONDISK(args->flags); - if (args->rename) { + if (args->op_flags & XFS_DA_OP_RENAME) { entry->flags |= XFS_ATTR_INCOMPLETE; if ((args->blkno2 == args->blkno) && (args->index2 <= args->index)) { @@ -1271,7 +1273,7 @@ xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp) be16_to_cpu(hdr_s->count), mp); xfs_da_log_buf(trans, bp, 0, XFS_LBSIZE(mp) - 1); - kmem_free(tmpbuffer, XFS_LBSIZE(mp)); + kmem_free(tmpbuffer); } /* @@ -1921,7 +1923,7 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk, be16_to_cpu(drop_hdr->count), mp); } memcpy((char *)save_leaf, (char *)tmp_leaf, state->blocksize); - kmem_free(tmpbuffer, state->blocksize); + kmem_free(tmpbuffer); } xfs_da_log_buf(state->args->trans, save_blk->bp, 0, @@ -2451,7 +2453,7 @@ xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context) (int)name_rmt->namelen, valuelen, (char*)args.value); - kmem_free(args.value, valuelen); + kmem_free(args.value); } else { retval = context->put_listent(context, @@ -2954,7 +2956,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp) error = tmp; /* save only the 1st errno */ } - kmem_free((xfs_caddr_t)list, size); + kmem_free((xfs_caddr_t)list); return(error); } diff --git a/fs/xfs/xfs_attr_sf.h b/fs/xfs/xfs_attr_sf.h index f67f917803b1..ea22839caed2 100644 --- a/fs/xfs/xfs_attr_sf.h +++ b/fs/xfs/xfs_attr_sf.h @@ -97,13 +97,9 @@ void xfs_attr_trace_l_cb(char *where, struct xfs_attr_list_context *context, void xfs_attr_trace_l_cl(char *where, struct xfs_attr_list_context *context, struct xfs_attr_leafblock *leaf); void xfs_attr_trace_enter(int type, char *where, - __psunsigned_t a2, __psunsigned_t a3, - __psunsigned_t a4, __psunsigned_t a5, - __psunsigned_t a6, __psunsigned_t a7, - __psunsigned_t a8, __psunsigned_t a9, - __psunsigned_t a10, __psunsigned_t a11, - __psunsigned_t a12, __psunsigned_t a13, - __psunsigned_t a14, __psunsigned_t a15); + struct xfs_attr_list_context *context, + __psunsigned_t a13, __psunsigned_t a14, + __psunsigned_t a15); #else #define xfs_attr_trace_l_c(w,c) #define xfs_attr_trace_l_cn(w,c,n) diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 53c259f5a5af..a612a90aae4a 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -5970,7 +5970,7 @@ unlock_and_return: xfs_iunlock_map_shared(ip, lock); xfs_iunlock(ip, XFS_IOLOCK_SHARED); - kmem_free(map, subnex * sizeof(*map)); + kmem_free(map); return error; } diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 53a71c62025d..d86ca2c03a70 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -889,9 +889,9 @@ xfs_buf_item_relse( } #ifdef XFS_TRANS_DEBUG - kmem_free(bip->bli_orig, XFS_BUF_COUNT(bp)); + kmem_free(bip->bli_orig); bip->bli_orig = NULL; - kmem_free(bip->bli_logged, XFS_BUF_COUNT(bp) / NBBY); + kmem_free(bip->bli_logged); bip->bli_logged = NULL; #endif /* XFS_TRANS_DEBUG */ @@ -1138,9 +1138,9 @@ xfs_buf_iodone( xfs_trans_delete_ail(mp, (xfs_log_item_t *)bip); #ifdef XFS_TRANS_DEBUG - kmem_free(bip->bli_orig, XFS_BUF_COUNT(bp)); + kmem_free(bip->bli_orig); bip->bli_orig = NULL; - kmem_free(bip->bli_logged, XFS_BUF_COUNT(bp) / NBBY); + kmem_free(bip->bli_logged); bip->bli_logged = NULL; #endif /* XFS_TRANS_DEBUG */ diff --git a/fs/xfs/xfs_clnt.h b/fs/xfs/xfs_clnt.h index d5d1e60ee224..d2ce5dd70d87 100644 --- a/fs/xfs/xfs_clnt.h +++ b/fs/xfs/xfs_clnt.h @@ -78,6 +78,7 @@ struct xfs_mount_args { #define XFSMNT_IOSIZE 0x00002000 /* optimize for I/O size */ #define XFSMNT_OSYNCISOSYNC 0x00004000 /* o_sync is REALLY o_sync */ /* (osyncisdsync is default) */ +#define XFSMNT_NOATTR2 0x00008000 /* turn off ATTR2 EA format */ #define XFSMNT_32BITINODES 0x00200000 /* restrict inodes to 32 * bits of address space */ #define XFSMNT_GQUOTA 0x00400000 /* group quota accounting */ diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c index 021a8f7e563f..edc0aef4e51e 100644 --- a/fs/xfs/xfs_da_btree.c +++ b/fs/xfs/xfs_da_btree.c @@ -1431,7 +1431,7 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path, } if (level < 0) { *result = XFS_ERROR(ENOENT); /* we're out of our tree */ - ASSERT(args->oknoent); + ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); return(0); } @@ -1530,6 +1530,28 @@ xfs_da_hashname(const uchar_t *name, int namelen) } } +enum xfs_dacmp +xfs_da_compname( + struct xfs_da_args *args, + const char *name, + int len) +{ + return (args->namelen == len && memcmp(args->name, name, len) == 0) ? + XFS_CMP_EXACT : XFS_CMP_DIFFERENT; +} + +static xfs_dahash_t +xfs_default_hashname( + struct xfs_name *name) +{ + return xfs_da_hashname(name->name, name->len); +} + +const struct xfs_nameops xfs_default_nameops = { + .hashname = xfs_default_hashname, + .compname = xfs_da_compname +}; + /* * Add a block to the btree ahead of the file. * Return the new block number to the caller. @@ -1598,7 +1620,7 @@ xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno) args->firstblock, args->total, &mapp[mapi], &nmap, args->flist, NULL))) { - kmem_free(mapp, sizeof(*mapp) * count); + kmem_free(mapp); return error; } if (nmap < 1) @@ -1620,11 +1642,11 @@ xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno) mapp[mapi - 1].br_startoff + mapp[mapi - 1].br_blockcount != bno + count) { if (mapp != &map) - kmem_free(mapp, sizeof(*mapp) * count); + kmem_free(mapp); return XFS_ERROR(ENOSPC); } if (mapp != &map) - kmem_free(mapp, sizeof(*mapp) * count); + kmem_free(mapp); *new_blkno = (xfs_dablk_t)bno; return 0; } @@ -2090,10 +2112,10 @@ xfs_da_do_buf( } } if (bplist) { - kmem_free(bplist, sizeof(*bplist) * nmap); + kmem_free(bplist); } if (mapp != &map) { - kmem_free(mapp, sizeof(*mapp) * nfsb); + kmem_free(mapp); } if (bpp) *bpp = rbp; @@ -2102,11 +2124,11 @@ exit1: if (bplist) { for (i = 0; i < nbplist; i++) xfs_trans_brelse(trans, bplist[i]); - kmem_free(bplist, sizeof(*bplist) * nmap); + kmem_free(bplist); } exit0: if (mapp != &map) - kmem_free(mapp, sizeof(*mapp) * nfsb); + kmem_free(mapp); if (bpp) *bpp = NULL; return error; @@ -2315,7 +2337,7 @@ xfs_da_buf_done(xfs_dabuf_t *dabuf) if (dabuf->dirty) xfs_da_buf_clean(dabuf); if (dabuf->nbuf > 1) - kmem_free(dabuf->data, BBTOB(dabuf->bbcount)); + kmem_free(dabuf->data); #ifdef XFS_DABUF_DEBUG { spin_lock(&xfs_dabuf_global_lock); @@ -2332,7 +2354,7 @@ xfs_da_buf_done(xfs_dabuf_t *dabuf) if (dabuf->nbuf == 1) kmem_zone_free(xfs_dabuf_zone, dabuf); else - kmem_free(dabuf, XFS_DA_BUF_SIZE(dabuf->nbuf)); + kmem_free(dabuf); } /* @@ -2403,7 +2425,7 @@ xfs_da_brelse(xfs_trans_t *tp, xfs_dabuf_t *dabuf) for (i = 0; i < nbuf; i++) xfs_trans_brelse(tp, bplist[i]); if (bplist != &bp) - kmem_free(bplist, nbuf * sizeof(*bplist)); + kmem_free(bplist); } /* @@ -2429,7 +2451,7 @@ xfs_da_binval(xfs_trans_t *tp, xfs_dabuf_t *dabuf) for (i = 0; i < nbuf; i++) xfs_trans_binval(tp, bplist[i]); if (bplist != &bp) - kmem_free(bplist, nbuf * sizeof(*bplist)); + kmem_free(bplist); } /* diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h index 7facf86f74f9..8be0b00ede9a 100644 --- a/fs/xfs/xfs_da_btree.h +++ b/fs/xfs/xfs_da_btree.h @@ -99,6 +99,15 @@ typedef struct xfs_da_node_entry xfs_da_node_entry_t; *========================================================================*/ /* + * Search comparison results + */ +enum xfs_dacmp { + XFS_CMP_DIFFERENT, /* names are completely different */ + XFS_CMP_EXACT, /* names are exactly the same */ + XFS_CMP_CASE /* names are same but differ in case */ +}; + +/* * Structure to ease passing around component names. */ typedef struct xfs_da_args { @@ -123,13 +132,20 @@ typedef struct xfs_da_args { int index2; /* index of 2nd attr in blk */ xfs_dablk_t rmtblkno2; /* remote attr value starting blkno */ int rmtblkcnt2; /* remote attr value block count */ - unsigned char justcheck; /* T/F: check for ok with no space */ - unsigned char rename; /* T/F: this is an atomic rename op */ - unsigned char addname; /* T/F: this is an add operation */ - unsigned char oknoent; /* T/F: ok to return ENOENT, else die */ + int op_flags; /* operation flags */ + enum xfs_dacmp cmpresult; /* name compare result for lookups */ } xfs_da_args_t; /* + * Operation flags: + */ +#define XFS_DA_OP_JUSTCHECK 0x0001 /* check for ok with no space */ +#define XFS_DA_OP_RENAME 0x0002 /* this is an atomic rename op */ +#define XFS_DA_OP_ADDNAME 0x0004 /* this is an add operation */ +#define XFS_DA_OP_OKNOENT 0x0008 /* lookup/add op, ENOENT ok, else die */ +#define XFS_DA_OP_CILOOKUP 0x0010 /* lookup to return CI name if found */ + +/* * Structure to describe buffer(s) for a block. * This is needed in the directory version 2 format case, when * multiple non-contiguous fsblocks might be needed to cover one @@ -201,6 +217,14 @@ typedef struct xfs_da_state { (uint)(XFS_DA_LOGOFF(BASE, ADDR)), \ (uint)(XFS_DA_LOGOFF(BASE, ADDR)+(SIZE)-1) +/* + * Name ops for directory and/or attr name operations + */ +struct xfs_nameops { + xfs_dahash_t (*hashname)(struct xfs_name *); + enum xfs_dacmp (*compname)(struct xfs_da_args *, const char *, int); +}; + #ifdef __KERNEL__ /*======================================================================== @@ -249,6 +273,10 @@ int xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno, xfs_dabuf_t *dead_buf); uint xfs_da_hashname(const uchar_t *name_string, int name_length); +enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args, + const char *name, int len); + + xfs_da_state_t *xfs_da_state_alloc(void); void xfs_da_state_free(xfs_da_state_t *state); diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c index 5f3647cb9885..2211e885ef24 100644 --- a/fs/xfs/xfs_dfrag.c +++ b/fs/xfs/xfs_dfrag.c @@ -116,7 +116,7 @@ xfs_swapext( out_put_file: fput(file); out_free_sxp: - kmem_free(sxp, sizeof(xfs_swapext_t)); + kmem_free(sxp); out: return error; } @@ -381,6 +381,6 @@ xfs_swap_extents( xfs_iunlock(tip, lock_flags); } if (tempifp != NULL) - kmem_free(tempifp, sizeof(xfs_ifork_t)); + kmem_free(tempifp); return error; } diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c index 7cb26529766b..80e0dc51361c 100644 --- a/fs/xfs/xfs_dir2.c +++ b/fs/xfs/xfs_dir2.c @@ -46,6 +46,54 @@ struct xfs_name xfs_name_dotdot = {"..", 2}; +extern const struct xfs_nameops xfs_default_nameops; + +/* + * ASCII case-insensitive (ie. A-Z) support for directories that was + * used in IRIX. + */ +STATIC xfs_dahash_t +xfs_ascii_ci_hashname( + struct xfs_name *name) +{ + xfs_dahash_t hash; + int i; + + for (i = 0, hash = 0; i < name->len; i++) + hash = tolower(name->name[i]) ^ rol32(hash, 7); + + return hash; +} + +STATIC enum xfs_dacmp +xfs_ascii_ci_compname( + struct xfs_da_args *args, + const char *name, + int len) +{ + enum xfs_dacmp result; + int i; + + if (args->namelen != len) + return XFS_CMP_DIFFERENT; + + result = XFS_CMP_EXACT; + for (i = 0; i < len; i++) { + if (args->name[i] == name[i]) + continue; + if (tolower(args->name[i]) != tolower(name[i])) + return XFS_CMP_DIFFERENT; + result = XFS_CMP_CASE; + } + + return result; +} + +static struct xfs_nameops xfs_ascii_ci_nameops = { + .hashname = xfs_ascii_ci_hashname, + .compname = xfs_ascii_ci_compname, +}; + void xfs_dir_mount( xfs_mount_t *mp) @@ -65,6 +113,10 @@ xfs_dir_mount( (mp->m_dirblksize - (uint)sizeof(xfs_da_node_hdr_t)) / (uint)sizeof(xfs_da_node_entry_t); mp->m_dir_magicpct = (mp->m_dirblksize * 37) / 100; + if (xfs_sb_version_hasasciici(&mp->m_sb)) + mp->m_dirnameops = &xfs_ascii_ci_nameops; + else + mp->m_dirnameops = &xfs_default_nameops; } /* @@ -162,9 +214,10 @@ xfs_dir_createname( return rval; XFS_STATS_INC(xs_dir_create); + memset(&args, 0, sizeof(xfs_da_args_t)); args.name = name->name; args.namelen = name->len; - args.hashval = xfs_da_hashname(name->name, name->len); + args.hashval = dp->i_mount->m_dirnameops->hashname(name); args.inumber = inum; args.dp = dp; args.firstblock = first; @@ -172,8 +225,7 @@ xfs_dir_createname( args.total = total; args.whichfork = XFS_DATA_FORK; args.trans = tp; - args.justcheck = 0; - args.addname = args.oknoent = 1; + args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT; if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) rval = xfs_dir2_sf_addname(&args); @@ -191,14 +243,43 @@ xfs_dir_createname( } /* + * If doing a CI lookup and case-insensitive match, dup actual name into + * args.value. Return EEXIST for success (ie. name found) or an error. + */ +int +xfs_dir_cilookup_result( + struct xfs_da_args *args, + const char *name, + int len) +{ + if (args->cmpresult == XFS_CMP_DIFFERENT) + return ENOENT; + if (args->cmpresult != XFS_CMP_CASE || + !(args->op_flags & XFS_DA_OP_CILOOKUP)) + return EEXIST; + + args->value = kmem_alloc(len, KM_MAYFAIL); + if (!args->value) + return ENOMEM; + + memcpy(args->value, name, len); + args->valuelen = len; + return EEXIST; +} + +/* * Lookup a name in a directory, give back the inode number. + * If ci_name is not NULL, returns the actual name in ci_name if it differs + * to name, or ci_name->name is set to NULL for an exact match. */ + int xfs_dir_lookup( xfs_trans_t *tp, xfs_inode_t *dp, struct xfs_name *name, - xfs_ino_t *inum) /* out: inode number */ + xfs_ino_t *inum, /* out: inode number */ + struct xfs_name *ci_name) /* out: actual name if CI match */ { xfs_da_args_t args; int rval; @@ -206,15 +287,17 @@ xfs_dir_lookup( ASSERT((dp->i_d.di_mode & S_IFMT) == S_IFDIR); XFS_STATS_INC(xs_dir_lookup); - memset(&args, 0, sizeof(xfs_da_args_t)); + memset(&args, 0, sizeof(xfs_da_args_t)); args.name = name->name; args.namelen = name->len; - args.hashval = xfs_da_hashname(name->name, name->len); + args.hashval = dp->i_mount->m_dirnameops->hashname(name); args.dp = dp; args.whichfork = XFS_DATA_FORK; args.trans = tp; - args.oknoent = 1; + args.op_flags = XFS_DA_OP_OKNOENT; + if (ci_name) + args.op_flags |= XFS_DA_OP_CILOOKUP; if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) rval = xfs_dir2_sf_lookup(&args); @@ -230,8 +313,13 @@ xfs_dir_lookup( rval = xfs_dir2_node_lookup(&args); if (rval == EEXIST) rval = 0; - if (rval == 0) + if (!rval) { *inum = args.inumber; + if (ci_name) { + ci_name->name = args.value; + ci_name->len = args.valuelen; + } + } return rval; } @@ -255,9 +343,10 @@ xfs_dir_removename( ASSERT((dp->i_d.di_mode & S_IFMT) == S_IFDIR); XFS_STATS_INC(xs_dir_remove); + memset(&args, 0, sizeof(xfs_da_args_t)); args.name = name->name; args.namelen = name->len; - args.hashval = xfs_da_hashname(name->name, name->len); + args.hashval = dp->i_mount->m_dirnameops->hashname(name); args.inumber = ino; args.dp = dp; args.firstblock = first; @@ -265,7 +354,6 @@ xfs_dir_removename( args.total = total; args.whichfork = XFS_DATA_FORK; args.trans = tp; - args.justcheck = args.addname = args.oknoent = 0; if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) rval = xfs_dir2_sf_removename(&args); @@ -338,9 +426,10 @@ xfs_dir_replace( if ((rval = xfs_dir_ino_validate(tp->t_mountp, inum))) return rval; + memset(&args, 0, sizeof(xfs_da_args_t)); args.name = name->name; args.namelen = name->len; - args.hashval = xfs_da_hashname(name->name, name->len); + args.hashval = dp->i_mount->m_dirnameops->hashname(name); args.inumber = inum; args.dp = dp; args.firstblock = first; @@ -348,7 +437,6 @@ xfs_dir_replace( args.total = total; args.whichfork = XFS_DATA_FORK; args.trans = tp; - args.justcheck = args.addname = args.oknoent = 0; if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) rval = xfs_dir2_sf_replace(&args); @@ -384,15 +472,16 @@ xfs_dir_canenter( return 0; ASSERT((dp->i_d.di_mode & S_IFMT) == S_IFDIR); - memset(&args, 0, sizeof(xfs_da_args_t)); + memset(&args, 0, sizeof(xfs_da_args_t)); args.name = name->name; args.namelen = name->len; - args.hashval = xfs_da_hashname(name->name, name->len); + args.hashval = dp->i_mount->m_dirnameops->hashname(name); args.dp = dp; args.whichfork = XFS_DATA_FORK; args.trans = tp; - args.justcheck = args.addname = args.oknoent = 1; + args.op_flags = XFS_DA_OP_JUSTCHECK | XFS_DA_OP_ADDNAME | + XFS_DA_OP_OKNOENT; if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) rval = xfs_dir2_sf_addname(&args); @@ -493,7 +582,7 @@ xfs_dir2_grow_inode( args->firstblock, args->total, &mapp[mapi], &nmap, args->flist, NULL))) { - kmem_free(mapp, sizeof(*mapp) * count); + kmem_free(mapp); return error; } if (nmap < 1) @@ -525,14 +614,14 @@ xfs_dir2_grow_inode( mapp[mapi - 1].br_startoff + mapp[mapi - 1].br_blockcount != bno + count) { if (mapp != &map) - kmem_free(mapp, sizeof(*mapp) * count); + kmem_free(mapp); return XFS_ERROR(ENOSPC); } /* * Done with the temporary mapping table. */ if (mapp != &map) - kmem_free(mapp, sizeof(*mapp) * count); + kmem_free(mapp); *dbp = xfs_dir2_da_to_db(mp, (xfs_dablk_t)bno); /* * Update file's size if this is the data space and it grew. diff --git a/fs/xfs/xfs_dir2.h b/fs/xfs/xfs_dir2.h index 6392f939029f..1d9ef96f33aa 100644 --- a/fs/xfs/xfs_dir2.h +++ b/fs/xfs/xfs_dir2.h @@ -74,7 +74,8 @@ extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp, xfs_fsblock_t *first, struct xfs_bmap_free *flist, xfs_extlen_t tot); extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp, - struct xfs_name *name, xfs_ino_t *inum); + struct xfs_name *name, xfs_ino_t *inum, + struct xfs_name *ci_name); extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_name *name, xfs_ino_t ino, xfs_fsblock_t *first, @@ -99,4 +100,7 @@ extern int xfs_dir2_isleaf(struct xfs_trans *tp, struct xfs_inode *dp, extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db, struct xfs_dabuf *bp); +extern int xfs_dir_cilookup_result(struct xfs_da_args *args, const char *name, + int len); + #endif /* __XFS_DIR2_H__ */ diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c index fb5a556725b3..e2fa0a1d8e96 100644 --- a/fs/xfs/xfs_dir2_block.c +++ b/fs/xfs/xfs_dir2_block.c @@ -215,7 +215,7 @@ xfs_dir2_block_addname( /* * If this isn't a real add, we're done with the buffer. */ - if (args->justcheck) + if (args->op_flags & XFS_DA_OP_JUSTCHECK) xfs_da_brelse(tp, bp); /* * If we don't have space for the new entry & leaf ... @@ -225,7 +225,7 @@ xfs_dir2_block_addname( * Not trying to actually do anything, or don't have * a space reservation: return no-space. */ - if (args->justcheck || args->total == 0) + if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0) return XFS_ERROR(ENOSPC); /* * Convert to the next larger format. @@ -240,7 +240,7 @@ xfs_dir2_block_addname( /* * Just checking, and it would work, so say so. */ - if (args->justcheck) + if (args->op_flags & XFS_DA_OP_JUSTCHECK) return 0; needlog = needscan = 0; /* @@ -610,14 +610,15 @@ xfs_dir2_block_lookup( /* * Get the offset from the leaf entry, to point to the data. */ - dep = (xfs_dir2_data_entry_t *) - ((char *)block + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address))); + dep = (xfs_dir2_data_entry_t *)((char *)block + + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address))); /* - * Fill in inode number, release the block. + * Fill in inode number, CI name if appropriate, release the block. */ args->inumber = be64_to_cpu(dep->inumber); + error = xfs_dir_cilookup_result(args, dep->name, dep->namelen); xfs_da_brelse(args->trans, bp); - return XFS_ERROR(EEXIST); + return XFS_ERROR(error); } /* @@ -643,6 +644,7 @@ xfs_dir2_block_lookup_int( int mid; /* binary search current idx */ xfs_mount_t *mp; /* filesystem mount point */ xfs_trans_t *tp; /* transaction pointer */ + enum xfs_dacmp cmp; /* comparison result */ dp = args->dp; tp = args->trans; @@ -673,7 +675,7 @@ xfs_dir2_block_lookup_int( else high = mid - 1; if (low > high) { - ASSERT(args->oknoent); + ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); xfs_da_brelse(tp, bp); return XFS_ERROR(ENOENT); } @@ -697,20 +699,31 @@ xfs_dir2_block_lookup_int( dep = (xfs_dir2_data_entry_t *) ((char *)block + xfs_dir2_dataptr_to_off(mp, addr)); /* - * Compare, if it's right give back buffer & entry number. + * Compare name and if it's an exact match, return the index + * and buffer. If it's the first case-insensitive match, store + * the index and buffer and continue looking for an exact match. */ - if (dep->namelen == args->namelen && - dep->name[0] == args->name[0] && - memcmp(dep->name, args->name, args->namelen) == 0) { + cmp = mp->m_dirnameops->compname(args, dep->name, dep->namelen); + if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) { + args->cmpresult = cmp; *bpp = bp; *entno = mid; - return 0; + if (cmp == XFS_CMP_EXACT) + return 0; } - } while (++mid < be32_to_cpu(btp->count) && be32_to_cpu(blp[mid].hashval) == hash); + } while (++mid < be32_to_cpu(btp->count) && + be32_to_cpu(blp[mid].hashval) == hash); + + ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); + /* + * Here, we can only be doing a lookup (not a rename or replace). + * If a case-insensitive match was found earlier, return success. + */ + if (args->cmpresult == XFS_CMP_CASE) + return 0; /* * No match, release the buffer and return ENOENT. */ - ASSERT(args->oknoent); xfs_da_brelse(tp, bp); return XFS_ERROR(ENOENT); } @@ -1033,6 +1046,7 @@ xfs_dir2_sf_to_block( xfs_dir2_sf_t *sfp; /* shortform structure */ __be16 *tagp; /* end of data entry */ xfs_trans_t *tp; /* transaction pointer */ + struct xfs_name name; xfs_dir2_trace_args("sf_to_block", args); dp = args->dp; @@ -1071,7 +1085,7 @@ xfs_dir2_sf_to_block( */ error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE, &blkno); if (error) { - kmem_free(buf, buf_len); + kmem_free(buf); return error; } /* @@ -1079,7 +1093,7 @@ xfs_dir2_sf_to_block( */ error = xfs_dir2_data_init(args, blkno, &bp); if (error) { - kmem_free(buf, buf_len); + kmem_free(buf); return error; } block = bp->data; @@ -1187,8 +1201,10 @@ xfs_dir2_sf_to_block( tagp = xfs_dir2_data_entry_tag_p(dep); *tagp = cpu_to_be16((char *)dep - (char *)block); xfs_dir2_data_log_entry(tp, bp, dep); - blp[2 + i].hashval = cpu_to_be32(xfs_da_hashname( - (char *)sfep->name, sfep->namelen)); + name.name = sfep->name; + name.len = sfep->namelen; + blp[2 + i].hashval = cpu_to_be32(mp->m_dirnameops-> + hashname(&name)); blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp, (char *)dep - (char *)block)); offset = (int)((char *)(tagp + 1) - (char *)block); @@ -1198,7 +1214,7 @@ xfs_dir2_sf_to_block( sfep = xfs_dir2_sf_nextentry(sfp, sfep); } /* Done with the temporary buffer */ - kmem_free(buf, buf_len); + kmem_free(buf); /* * Sort the leaf entries by hash value. */ diff --git a/fs/xfs/xfs_dir2_data.c b/fs/xfs/xfs_dir2_data.c index fb8c9e08b23d..498f8d694330 100644 --- a/fs/xfs/xfs_dir2_data.c +++ b/fs/xfs/xfs_dir2_data.c @@ -65,6 +65,7 @@ xfs_dir2_data_check( xfs_mount_t *mp; /* filesystem mount point */ char *p; /* current data position */ int stale; /* count of stale leaves */ + struct xfs_name name; mp = dp->i_mount; d = bp->data; @@ -140,7 +141,9 @@ xfs_dir2_data_check( addr = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk, (xfs_dir2_data_aoff_t) ((char *)dep - (char *)d)); - hash = xfs_da_hashname((char *)dep->name, dep->namelen); + name.name = dep->name; + name.len = dep->namelen; + hash = mp->m_dirnameops->hashname(&name); for (i = 0; i < be32_to_cpu(btp->count); i++) { if (be32_to_cpu(lep[i].address) == addr && be32_to_cpu(lep[i].hashval) == hash) diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c index bc52b803d79b..f110242d6dfc 100644 --- a/fs/xfs/xfs_dir2_leaf.c +++ b/fs/xfs/xfs_dir2_leaf.c @@ -263,20 +263,21 @@ xfs_dir2_leaf_addname( * If we don't have enough free bytes but we can make enough * by compacting out stale entries, we'll do that. */ - if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] < needbytes && - be16_to_cpu(leaf->hdr.stale) > 1) { + if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] < + needbytes && be16_to_cpu(leaf->hdr.stale) > 1) { compact = 1; } /* * Otherwise if we don't have enough free bytes we need to * convert to node form. */ - else if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] < - needbytes) { + else if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu( + leaf->hdr.count)] < needbytes) { /* * Just checking or no space reservation, give up. */ - if (args->justcheck || args->total == 0) { + if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || + args->total == 0) { xfs_da_brelse(tp, lbp); return XFS_ERROR(ENOSPC); } @@ -301,7 +302,7 @@ xfs_dir2_leaf_addname( * If just checking, then it will fit unless we needed to allocate * a new data block. */ - if (args->justcheck) { + if (args->op_flags & XFS_DA_OP_JUSTCHECK) { xfs_da_brelse(tp, lbp); return use_block == -1 ? XFS_ERROR(ENOSPC) : 0; } @@ -1110,7 +1111,7 @@ xfs_dir2_leaf_getdents( *offset = XFS_DIR2_MAX_DATAPTR; else *offset = xfs_dir2_byte_to_dataptr(mp, curoff); - kmem_free(map, map_size * sizeof(*map)); + kmem_free(map); if (bp) xfs_da_brelse(NULL, bp); return error; @@ -1298,12 +1299,13 @@ xfs_dir2_leaf_lookup( ((char *)dbp->data + xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address))); /* - * Return the found inode number. + * Return the found inode number & CI name if appropriate */ args->inumber = be64_to_cpu(dep->inumber); + error = xfs_dir_cilookup_result(args, dep->name, dep->namelen); xfs_da_brelse(tp, dbp); xfs_da_brelse(tp, lbp); - return XFS_ERROR(EEXIST); + return XFS_ERROR(error); } /* @@ -1331,6 +1333,8 @@ xfs_dir2_leaf_lookup_int( xfs_mount_t *mp; /* filesystem mount point */ xfs_dir2_db_t newdb; /* new data block number */ xfs_trans_t *tp; /* transaction pointer */ + xfs_dabuf_t *cbp; /* case match data buffer */ + enum xfs_dacmp cmp; /* name compare result */ dp = args->dp; tp = args->trans; @@ -1354,9 +1358,11 @@ xfs_dir2_leaf_lookup_int( * Loop over all the entries with the right hash value * looking to match the name. */ + cbp = NULL; for (lep = &leaf->ents[index], dbp = NULL, curdb = -1; - index < be16_to_cpu(leaf->hdr.count) && be32_to_cpu(lep->hashval) == args->hashval; - lep++, index++) { + index < be16_to_cpu(leaf->hdr.count) && + be32_to_cpu(lep->hashval) == args->hashval; + lep++, index++) { /* * Skip over stale leaf entries. */ @@ -1371,12 +1377,12 @@ xfs_dir2_leaf_lookup_int( * need to pitch the old one and read the new one. */ if (newdb != curdb) { - if (dbp) + if (dbp != cbp) xfs_da_brelse(tp, dbp); - if ((error = - xfs_da_read_buf(tp, dp, - xfs_dir2_db_to_da(mp, newdb), -1, &dbp, - XFS_DATA_FORK))) { + error = xfs_da_read_buf(tp, dp, + xfs_dir2_db_to_da(mp, newdb), + -1, &dbp, XFS_DATA_FORK); + if (error) { xfs_da_brelse(tp, lbp); return error; } @@ -1386,24 +1392,46 @@ xfs_dir2_leaf_lookup_int( /* * Point to the data entry. */ - dep = (xfs_dir2_data_entry_t *) - ((char *)dbp->data + - xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address))); + dep = (xfs_dir2_data_entry_t *)((char *)dbp->data + + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address))); /* - * If it matches then return it. + * Compare name and if it's an exact match, return the index + * and buffer. If it's the first case-insensitive match, store + * the index and buffer and continue looking for an exact match. */ - if (dep->namelen == args->namelen && - dep->name[0] == args->name[0] && - memcmp(dep->name, args->name, args->namelen) == 0) { - *dbpp = dbp; + cmp = mp->m_dirnameops->compname(args, dep->name, dep->namelen); + if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) { + args->cmpresult = cmp; *indexp = index; - return 0; + /* + * case exact match: release the stored CI buffer if it + * exists and return the current buffer. + */ + if (cmp == XFS_CMP_EXACT) { + if (cbp && cbp != dbp) + xfs_da_brelse(tp, cbp); + *dbpp = dbp; + return 0; + } + cbp = dbp; } } + ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); + /* + * Here, we can only be doing a lookup (not a rename or replace). + * If a case-insensitive match was found earlier, release the current + * buffer and return the stored CI matching buffer. + */ + if (args->cmpresult == XFS_CMP_CASE) { + if (cbp != dbp) + xfs_da_brelse(tp, dbp); + *dbpp = cbp; + return 0; + } /* * No match found, return ENOENT. */ - ASSERT(args->oknoent); + ASSERT(cbp == NULL); if (dbp) xfs_da_brelse(tp, dbp); xfs_da_brelse(tp, lbp); diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c index 8dade711f099..1b5430223461 100644 --- a/fs/xfs/xfs_dir2_node.c +++ b/fs/xfs/xfs_dir2_node.c @@ -226,7 +226,7 @@ xfs_dir2_leafn_add( ASSERT(index == be16_to_cpu(leaf->hdr.count) || be32_to_cpu(leaf->ents[index].hashval) >= args->hashval); - if (args->justcheck) + if (args->op_flags & XFS_DA_OP_JUSTCHECK) return 0; /* @@ -387,28 +387,26 @@ xfs_dir2_leafn_lasthash( } /* - * Look up a leaf entry in a node-format leaf block. - * If this is an addname then the extrablk in state is a freespace block, - * otherwise it's a data block. + * Look up a leaf entry for space to add a name in a node-format leaf block. + * The extrablk in state is a freespace block. */ -int -xfs_dir2_leafn_lookup_int( +STATIC int +xfs_dir2_leafn_lookup_for_addname( xfs_dabuf_t *bp, /* leaf buffer */ xfs_da_args_t *args, /* operation arguments */ int *indexp, /* out: leaf entry index */ xfs_da_state_t *state) /* state to fill in */ { - xfs_dabuf_t *curbp; /* current data/free buffer */ - xfs_dir2_db_t curdb; /* current data block number */ - xfs_dir2_db_t curfdb; /* current free block number */ - xfs_dir2_data_entry_t *dep; /* data block entry */ + xfs_dabuf_t *curbp = NULL; /* current data/free buffer */ + xfs_dir2_db_t curdb = -1; /* current data block number */ + xfs_dir2_db_t curfdb = -1; /* current free block number */ xfs_inode_t *dp; /* incore directory inode */ int error; /* error return value */ int fi; /* free entry index */ - xfs_dir2_free_t *free=NULL; /* free block structure */ + xfs_dir2_free_t *free = NULL; /* free block structure */ int index; /* leaf entry index */ xfs_dir2_leaf_t *leaf; /* leaf structure */ - int length=0; /* length of new data entry */ + int length; /* length of new data entry */ xfs_dir2_leaf_entry_t *lep; /* leaf entry */ xfs_mount_t *mp; /* filesystem mount point */ xfs_dir2_db_t newdb; /* new data block number */ @@ -431,33 +429,20 @@ xfs_dir2_leafn_lookup_int( /* * Do we have a buffer coming in? */ - if (state->extravalid) + if (state->extravalid) { + /* If so, it's a free block buffer, get the block number. */ curbp = state->extrablk.bp; - else - curbp = NULL; - /* - * For addname, it's a free block buffer, get the block number. - */ - if (args->addname) { - curfdb = curbp ? state->extrablk.blkno : -1; - curdb = -1; - length = xfs_dir2_data_entsize(args->namelen); - if ((free = (curbp ? curbp->data : NULL))) - ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); - } - /* - * For others, it's a data block buffer, get the block number. - */ - else { - curfdb = -1; - curdb = curbp ? state->extrablk.blkno : -1; + curfdb = state->extrablk.blkno; + free = curbp->data; + ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); } + length = xfs_dir2_data_entsize(args->namelen); /* * Loop over leaf entries with the right hash value. */ - for (lep = &leaf->ents[index]; - index < be16_to_cpu(leaf->hdr.count) && be32_to_cpu(lep->hashval) == args->hashval; - lep++, index++) { + for (lep = &leaf->ents[index]; index < be16_to_cpu(leaf->hdr.count) && + be32_to_cpu(lep->hashval) == args->hashval; + lep++, index++) { /* * Skip stale leaf entries. */ @@ -471,158 +456,224 @@ xfs_dir2_leafn_lookup_int( * For addname, we're looking for a place to put the new entry. * We want to use a data block with an entry of equal * hash value to ours if there is one with room. + * + * If this block isn't the data block we already have + * in hand, take a look at it. */ - if (args->addname) { + if (newdb != curdb) { + curdb = newdb; /* - * If this block isn't the data block we already have - * in hand, take a look at it. + * Convert the data block to the free block + * holding its freespace information. */ - if (newdb != curdb) { - curdb = newdb; - /* - * Convert the data block to the free block - * holding its freespace information. - */ - newfdb = xfs_dir2_db_to_fdb(mp, newdb); - /* - * If it's not the one we have in hand, - * read it in. - */ - if (newfdb != curfdb) { - /* - * If we had one before, drop it. - */ - if (curbp) - xfs_da_brelse(tp, curbp); - /* - * Read the free block. - */ - if ((error = xfs_da_read_buf(tp, dp, - xfs_dir2_db_to_da(mp, - newfdb), - -1, &curbp, - XFS_DATA_FORK))) { - return error; - } - free = curbp->data; - ASSERT(be32_to_cpu(free->hdr.magic) == - XFS_DIR2_FREE_MAGIC); - ASSERT((be32_to_cpu(free->hdr.firstdb) % - XFS_DIR2_MAX_FREE_BESTS(mp)) == - 0); - ASSERT(be32_to_cpu(free->hdr.firstdb) <= curdb); - ASSERT(curdb < - be32_to_cpu(free->hdr.firstdb) + - be32_to_cpu(free->hdr.nvalid)); - } - /* - * Get the index for our entry. - */ - fi = xfs_dir2_db_to_fdindex(mp, curdb); - /* - * If it has room, return it. - */ - if (unlikely(be16_to_cpu(free->bests[fi]) == NULLDATAOFF)) { - XFS_ERROR_REPORT("xfs_dir2_leafn_lookup_int", - XFS_ERRLEVEL_LOW, mp); - if (curfdb != newfdb) - xfs_da_brelse(tp, curbp); - return XFS_ERROR(EFSCORRUPTED); - } - curfdb = newfdb; - if (be16_to_cpu(free->bests[fi]) >= length) { - *indexp = index; - state->extravalid = 1; - state->extrablk.bp = curbp; - state->extrablk.blkno = curfdb; - state->extrablk.index = fi; - state->extrablk.magic = - XFS_DIR2_FREE_MAGIC; - ASSERT(args->oknoent); - return XFS_ERROR(ENOENT); - } - } - } - /* - * Not adding a new entry, so we really want to find - * the name given to us. - */ - else { + newfdb = xfs_dir2_db_to_fdb(mp, newdb); /* - * If it's a different data block, go get it. + * If it's not the one we have in hand, read it in. */ - if (newdb != curdb) { + if (newfdb != curfdb) { /* - * If we had a block before, drop it. + * If we had one before, drop it. */ if (curbp) xfs_da_brelse(tp, curbp); /* - * Read the data block. + * Read the free block. */ - if ((error = - xfs_da_read_buf(tp, dp, - xfs_dir2_db_to_da(mp, newdb), -1, - &curbp, XFS_DATA_FORK))) { + error = xfs_da_read_buf(tp, dp, + xfs_dir2_db_to_da(mp, newfdb), + -1, &curbp, XFS_DATA_FORK); + if (error) return error; - } - xfs_dir2_data_check(dp, curbp); - curdb = newdb; + free = curbp->data; + ASSERT(be32_to_cpu(free->hdr.magic) == + XFS_DIR2_FREE_MAGIC); + ASSERT((be32_to_cpu(free->hdr.firstdb) % + XFS_DIR2_MAX_FREE_BESTS(mp)) == 0); + ASSERT(be32_to_cpu(free->hdr.firstdb) <= curdb); + ASSERT(curdb < be32_to_cpu(free->hdr.firstdb) + + be32_to_cpu(free->hdr.nvalid)); } /* - * Point to the data entry. + * Get the index for our entry. */ - dep = (xfs_dir2_data_entry_t *) - ((char *)curbp->data + - xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address))); + fi = xfs_dir2_db_to_fdindex(mp, curdb); /* - * Compare the entry, return it if it matches. + * If it has room, return it. */ - if (dep->namelen == args->namelen && - dep->name[0] == args->name[0] && - memcmp(dep->name, args->name, args->namelen) == 0) { - args->inumber = be64_to_cpu(dep->inumber); - *indexp = index; - state->extravalid = 1; - state->extrablk.bp = curbp; - state->extrablk.blkno = curdb; - state->extrablk.index = - (int)((char *)dep - - (char *)curbp->data); - state->extrablk.magic = XFS_DIR2_DATA_MAGIC; - return XFS_ERROR(EEXIST); + if (unlikely(be16_to_cpu(free->bests[fi]) == NULLDATAOFF)) { + XFS_ERROR_REPORT("xfs_dir2_leafn_lookup_int", + XFS_ERRLEVEL_LOW, mp); + if (curfdb != newfdb) + xfs_da_brelse(tp, curbp); + return XFS_ERROR(EFSCORRUPTED); } + curfdb = newfdb; + if (be16_to_cpu(free->bests[fi]) >= length) + goto out; } } + /* Didn't find any space */ + fi = -1; +out: + ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); + if (curbp) { + /* Giving back a free block. */ + state->extravalid = 1; + state->extrablk.bp = curbp; + state->extrablk.index = fi; + state->extrablk.blkno = curfdb; + state->extrablk.magic = XFS_DIR2_FREE_MAGIC; + } else { + state->extravalid = 0; + } /* - * Didn't find a match. - * If we are holding a buffer, give it back in case our caller - * finds it useful. + * Return the index, that will be the insertion point. */ - if ((state->extravalid = (curbp != NULL))) { - state->extrablk.bp = curbp; - state->extrablk.index = -1; + *indexp = index; + return XFS_ERROR(ENOENT); +} + +/* + * Look up a leaf entry in a node-format leaf block. + * The extrablk in state a data block. + */ +STATIC int +xfs_dir2_leafn_lookup_for_entry( + xfs_dabuf_t *bp, /* leaf buffer */ + xfs_da_args_t *args, /* operation arguments */ + int *indexp, /* out: leaf entry index */ + xfs_da_state_t *state) /* state to fill in */ +{ + xfs_dabuf_t *curbp = NULL; /* current data/free buffer */ + xfs_dir2_db_t curdb = -1; /* current data block number */ + xfs_dir2_data_entry_t *dep; /* data block entry */ + xfs_inode_t *dp; /* incore directory inode */ + int error; /* error return value */ + int di = -1; /* data entry index */ + int index; /* leaf entry index */ + xfs_dir2_leaf_t *leaf; /* leaf structure */ + xfs_dir2_leaf_entry_t *lep; /* leaf entry */ + xfs_mount_t *mp; /* filesystem mount point */ + xfs_dir2_db_t newdb; /* new data block number */ + xfs_trans_t *tp; /* transaction pointer */ + enum xfs_dacmp cmp; /* comparison result */ + + dp = args->dp; + tp = args->trans; + mp = dp->i_mount; + leaf = bp->data; + ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); +#ifdef __KERNEL__ + ASSERT(be16_to_cpu(leaf->hdr.count) > 0); +#endif + xfs_dir2_leafn_check(dp, bp); + /* + * Look up the hash value in the leaf entries. + */ + index = xfs_dir2_leaf_search_hash(args, bp); + /* + * Do we have a buffer coming in? + */ + if (state->extravalid) { + curbp = state->extrablk.bp; + curdb = state->extrablk.blkno; + di = state->extrablk.index; + } + /* + * Loop over leaf entries with the right hash value. + */ + for (lep = &leaf->ents[index]; index < be16_to_cpu(leaf->hdr.count) && + be32_to_cpu(lep->hashval) == args->hashval; + lep++, index++) { /* - * For addname, giving back a free block. + * Skip stale leaf entries. + */ + if (be32_to_cpu(lep->address) == XFS_DIR2_NULL_DATAPTR) + continue; + /* + * Pull the data block number from the entry. + */ + newdb = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address)); + /* + * Not adding a new entry, so we really want to find + * the name given to us. + * + * If it's a different data block, go get it. */ - if (args->addname) { - state->extrablk.blkno = curfdb; - state->extrablk.magic = XFS_DIR2_FREE_MAGIC; + if (newdb != curdb) { + /* + * If we had a block before, drop it. + */ + if (curbp) + xfs_da_brelse(tp, curbp); + /* + * Read the data block. + */ + error = xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, + newdb), -1, &curbp, XFS_DATA_FORK); + if (error) + return error; + xfs_dir2_data_check(dp, curbp); + curdb = newdb; } /* - * For other callers, giving back a data block. + * Point to the data entry. */ - else { - state->extrablk.blkno = curdb; - state->extrablk.magic = XFS_DIR2_DATA_MAGIC; + dep = (xfs_dir2_data_entry_t *)((char *)curbp->data + + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address))); + /* + * Compare the entry and if it's an exact match, return + * EEXIST immediately. If it's the first case-insensitive + * match, store the inode number and continue looking. + */ + cmp = mp->m_dirnameops->compname(args, dep->name, dep->namelen); + if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) { + args->cmpresult = cmp; + args->inumber = be64_to_cpu(dep->inumber); + di = (int)((char *)dep - (char *)curbp->data); + error = EEXIST; + if (cmp == XFS_CMP_EXACT) + goto out; } } + /* Didn't find an exact match. */ + error = ENOENT; + ASSERT(index == be16_to_cpu(leaf->hdr.count) || + (args->op_flags & XFS_DA_OP_OKNOENT)); +out: + if (curbp) { + /* Giving back a data block. */ + state->extravalid = 1; + state->extrablk.bp = curbp; + state->extrablk.index = di; + state->extrablk.blkno = curdb; + state->extrablk.magic = XFS_DIR2_DATA_MAGIC; + } else { + state->extravalid = 0; + } /* - * Return the final index, that will be the insertion point. + * Return the index, that will be the deletion point for remove/replace. */ *indexp = index; - ASSERT(index == be16_to_cpu(leaf->hdr.count) || args->oknoent); - return XFS_ERROR(ENOENT); + return XFS_ERROR(error); +} + +/* + * Look up a leaf entry in a node-format leaf block. + * If this is an addname then the extrablk in state is a freespace block, + * otherwise it's a data block. + */ +int +xfs_dir2_leafn_lookup_int( + xfs_dabuf_t *bp, /* leaf buffer */ + xfs_da_args_t *args, /* operation arguments */ + int *indexp, /* out: leaf entry index */ + xfs_da_state_t *state) /* state to fill in */ +{ + if (args->op_flags & XFS_DA_OP_ADDNAME) + return xfs_dir2_leafn_lookup_for_addname(bp, args, indexp, + state); + return xfs_dir2_leafn_lookup_for_entry(bp, args, indexp, state); } /* @@ -823,9 +874,10 @@ xfs_dir2_leafn_rebalance( */ if (!state->inleaf) blk2->index = blk1->index - be16_to_cpu(leaf1->hdr.count); - - /* - * Finally sanity check just to make sure we are not returning a negative index + + /* + * Finally sanity check just to make sure we are not returning a + * negative index */ if(blk2->index < 0) { state->inleaf = 1; @@ -1332,7 +1384,7 @@ xfs_dir2_node_addname( /* * It worked, fix the hash values up the btree. */ - if (!args->justcheck) + if (!(args->op_flags & XFS_DA_OP_JUSTCHECK)) xfs_da_fixhashpath(state, &state->path); } else { /* @@ -1515,7 +1567,8 @@ xfs_dir2_node_addname_int( /* * Not allowed to allocate, return failure. */ - if (args->justcheck || args->total == 0) { + if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || + args->total == 0) { /* * Drop the freespace buffer unless it came from our * caller. @@ -1661,7 +1714,7 @@ xfs_dir2_node_addname_int( /* * If just checking, we succeeded. */ - if (args->justcheck) { + if (args->op_flags & XFS_DA_OP_JUSTCHECK) { if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL) xfs_da_buf_done(fbp); return 0; @@ -1767,6 +1820,14 @@ xfs_dir2_node_lookup( error = xfs_da_node_lookup_int(state, &rval); if (error) rval = error; + else if (rval == ENOENT && args->cmpresult == XFS_CMP_CASE) { + /* If a CI match, dup the actual name and return EEXIST */ + xfs_dir2_data_entry_t *dep; + + dep = (xfs_dir2_data_entry_t *)((char *)state->extrablk.bp-> + data + state->extrablk.index); + rval = xfs_dir_cilookup_result(args, dep->name, dep->namelen); + } /* * Release the btree blocks and leaf block. */ @@ -1810,9 +1871,8 @@ xfs_dir2_node_removename( * Look up the entry we're deleting, set up the cursor. */ error = xfs_da_node_lookup_int(state, &rval); - if (error) { + if (error) rval = error; - } /* * Didn't find it, upper layer screwed up. */ @@ -1829,9 +1889,8 @@ xfs_dir2_node_removename( */ error = xfs_dir2_leafn_remove(args, blk->bp, blk->index, &state->extrablk, &rval); - if (error) { + if (error) return error; - } /* * Fix the hash values up the btree. */ diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c index 919d275a1cef..b46af0013ec9 100644 --- a/fs/xfs/xfs_dir2_sf.c +++ b/fs/xfs/xfs_dir2_sf.c @@ -255,7 +255,7 @@ xfs_dir2_block_to_sf( xfs_dir2_sf_check(args); out: xfs_trans_log_inode(args->trans, dp, logflags); - kmem_free(block, mp->m_dirblksize); + kmem_free(block); return error; } @@ -332,7 +332,7 @@ xfs_dir2_sf_addname( /* * Just checking or no space reservation, it doesn't fit. */ - if (args->justcheck || args->total == 0) + if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0) return XFS_ERROR(ENOSPC); /* * Convert to block form then add the name. @@ -345,7 +345,7 @@ xfs_dir2_sf_addname( /* * Just checking, it fits. */ - if (args->justcheck) + if (args->op_flags & XFS_DA_OP_JUSTCHECK) return 0; /* * Do it the easy way - just add it at the end. @@ -512,7 +512,7 @@ xfs_dir2_sf_addname_hard( sfep = xfs_dir2_sf_nextentry(sfp, sfep); memcpy(sfep, oldsfep, old_isize - nbytes); } - kmem_free(buf, old_isize); + kmem_free(buf); dp->i_d.di_size = new_isize; xfs_dir2_sf_check(args); } @@ -812,8 +812,11 @@ xfs_dir2_sf_lookup( { xfs_inode_t *dp; /* incore directory inode */ int i; /* entry index */ + int error; xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ xfs_dir2_sf_t *sfp; /* shortform structure */ + enum xfs_dacmp cmp; /* comparison result */ + xfs_dir2_sf_entry_t *ci_sfep; /* case-insens. entry */ xfs_dir2_trace_args("sf_lookup", args); xfs_dir2_sf_check(args); @@ -836,6 +839,7 @@ xfs_dir2_sf_lookup( */ if (args->namelen == 1 && args->name[0] == '.') { args->inumber = dp->i_ino; + args->cmpresult = XFS_CMP_EXACT; return XFS_ERROR(EEXIST); } /* @@ -844,28 +848,41 @@ xfs_dir2_sf_lookup( if (args->namelen == 2 && args->name[0] == '.' && args->name[1] == '.') { args->inumber = xfs_dir2_sf_get_inumber(sfp, &sfp->hdr.parent); + args->cmpresult = XFS_CMP_EXACT; return XFS_ERROR(EEXIST); } /* * Loop over all the entries trying to match ours. */ - for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); - i < sfp->hdr.count; - i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) { - if (sfep->namelen == args->namelen && - sfep->name[0] == args->name[0] && - memcmp(args->name, sfep->name, args->namelen) == 0) { - args->inumber = - xfs_dir2_sf_get_inumber(sfp, - xfs_dir2_sf_inumberp(sfep)); - return XFS_ERROR(EEXIST); + ci_sfep = NULL; + for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->hdr.count; + i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) { + /* + * Compare name and if it's an exact match, return the inode + * number. If it's the first case-insensitive match, store the + * inode number and continue looking for an exact match. + */ + cmp = dp->i_mount->m_dirnameops->compname(args, sfep->name, + sfep->namelen); + if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) { + args->cmpresult = cmp; + args->inumber = xfs_dir2_sf_get_inumber(sfp, + xfs_dir2_sf_inumberp(sfep)); + if (cmp == XFS_CMP_EXACT) + return XFS_ERROR(EEXIST); + ci_sfep = sfep; } } + ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); /* - * Didn't find it. + * Here, we can only be doing a lookup (not a rename or replace). + * If a case-insensitive match was not found, return ENOENT. */ - ASSERT(args->oknoent); - return XFS_ERROR(ENOENT); + if (!ci_sfep) + return XFS_ERROR(ENOENT); + /* otherwise process the CI match as required by the caller */ + error = xfs_dir_cilookup_result(args, ci_sfep->name, ci_sfep->namelen); + return XFS_ERROR(error); } /* @@ -904,24 +921,21 @@ xfs_dir2_sf_removename( * Loop over the old directory entries. * Find the one we're deleting. */ - for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); - i < sfp->hdr.count; - i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) { - if (sfep->namelen == args->namelen && - sfep->name[0] == args->name[0] && - memcmp(sfep->name, args->name, args->namelen) == 0) { + for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->hdr.count; + i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) { + if (xfs_da_compname(args, sfep->name, sfep->namelen) == + XFS_CMP_EXACT) { ASSERT(xfs_dir2_sf_get_inumber(sfp, - xfs_dir2_sf_inumberp(sfep)) == - args->inumber); + xfs_dir2_sf_inumberp(sfep)) == + args->inumber); break; } } /* * Didn't find it. */ - if (i == sfp->hdr.count) { + if (i == sfp->hdr.count) return XFS_ERROR(ENOENT); - } /* * Calculate sizes. */ @@ -1042,11 +1056,10 @@ xfs_dir2_sf_replace( */ else { for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); - i < sfp->hdr.count; - i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) { - if (sfep->namelen == args->namelen && - sfep->name[0] == args->name[0] && - memcmp(args->name, sfep->name, args->namelen) == 0) { + i < sfp->hdr.count; + i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) { + if (xfs_da_compname(args, sfep->name, sfep->namelen) == + XFS_CMP_EXACT) { #if XFS_BIG_INUMS || defined(DEBUG) ino = xfs_dir2_sf_get_inumber(sfp, xfs_dir2_sf_inumberp(sfep)); @@ -1061,7 +1074,7 @@ xfs_dir2_sf_replace( * Didn't find it. */ if (i == sfp->hdr.count) { - ASSERT(args->oknoent); + ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); #if XFS_BIG_INUMS if (i8elevated) xfs_dir2_sf_toino4(args); @@ -1174,7 +1187,7 @@ xfs_dir2_sf_toino4( /* * Clean up the inode. */ - kmem_free(buf, oldsize); + kmem_free(buf); dp->i_d.di_size = newsize; xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); } @@ -1251,7 +1264,7 @@ xfs_dir2_sf_toino8( /* * Clean up the inode. */ - kmem_free(buf, oldsize); + kmem_free(buf); dp->i_d.di_size = newsize; xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); } diff --git a/fs/xfs/xfs_dir2_trace.c b/fs/xfs/xfs_dir2_trace.c index f3fb2ffd6f5c..6cc7c0c681ac 100644 --- a/fs/xfs/xfs_dir2_trace.c +++ b/fs/xfs/xfs_dir2_trace.c @@ -85,7 +85,8 @@ xfs_dir2_trace_args( (void *)((unsigned long)(args->inumber >> 32)), (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)), (void *)args->dp, (void *)args->trans, - (void *)(unsigned long)args->justcheck, NULL, NULL); + (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK), + NULL, NULL); } void @@ -100,7 +101,7 @@ xfs_dir2_trace_args_b( (void *)((unsigned long)(args->inumber >> 32)), (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)), (void *)args->dp, (void *)args->trans, - (void *)(unsigned long)args->justcheck, + (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK), (void *)(bp ? bp->bps[0] : NULL), NULL); } @@ -117,7 +118,7 @@ xfs_dir2_trace_args_bb( (void *)((unsigned long)(args->inumber >> 32)), (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)), (void *)args->dp, (void *)args->trans, - (void *)(unsigned long)args->justcheck, + (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK), (void *)(lbp ? lbp->bps[0] : NULL), (void *)(dbp ? dbp->bps[0] : NULL)); } @@ -157,8 +158,8 @@ xfs_dir2_trace_args_db( (void *)((unsigned long)(args->inumber >> 32)), (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)), (void *)args->dp, (void *)args->trans, - (void *)(unsigned long)args->justcheck, (void *)(long)db, - (void *)dbp); + (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK), + (void *)(long)db, (void *)dbp); } void @@ -173,7 +174,7 @@ xfs_dir2_trace_args_i( (void *)((unsigned long)(args->inumber >> 32)), (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)), (void *)args->dp, (void *)args->trans, - (void *)(unsigned long)args->justcheck, + (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK), (void *)((unsigned long)(i >> 32)), (void *)((unsigned long)(i & 0xFFFFFFFF))); } @@ -190,7 +191,8 @@ xfs_dir2_trace_args_s( (void *)((unsigned long)(args->inumber >> 32)), (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)), (void *)args->dp, (void *)args->trans, - (void *)(unsigned long)args->justcheck, (void *)(long)s, NULL); + (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK), + (void *)(long)s, NULL); } void @@ -208,7 +210,7 @@ xfs_dir2_trace_args_sb( (void *)((unsigned long)(args->inumber >> 32)), (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)), (void *)args->dp, (void *)args->trans, - (void *)(unsigned long)args->justcheck, (void *)(long)s, - (void *)dbp); + (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK), + (void *)(long)s, (void *)dbp); } #endif /* XFS_DIR2_TRACE */ diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 05e5365d3c31..7380a00644c8 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -150,8 +150,7 @@ xfs_errortag_clearall(xfs_mount_t *mp, int loud) xfs_etest[i]); xfs_etest[i] = 0; xfs_etest_fsid[i] = 0LL; - kmem_free(xfs_etest_fsname[i], - strlen(xfs_etest_fsname[i]) + 1); + kmem_free(xfs_etest_fsname[i]); xfs_etest_fsname[i] = NULL; } } @@ -175,7 +174,7 @@ xfs_fs_vcmn_err(int level, xfs_mount_t *mp, char *fmt, va_list ap) newfmt = kmem_alloc(len, KM_SLEEP); sprintf(newfmt, "Filesystem \"%s\": %s", mp->m_fsname, fmt); icmn_err(level, newfmt, ap); - kmem_free(newfmt, len); + kmem_free(newfmt); } else { icmn_err(level, fmt, ap); } diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 132bd07b9bb8..8aa28f751b2a 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -41,8 +41,7 @@ xfs_efi_item_free(xfs_efi_log_item_t *efip) int nexts = efip->efi_format.efi_nextents; if (nexts > XFS_EFI_MAX_FAST_EXTENTS) { - kmem_free(efip, sizeof(xfs_efi_log_item_t) + - (nexts - 1) * sizeof(xfs_extent_t)); + kmem_free(efip); } else { kmem_zone_free(xfs_efi_zone, efip); } @@ -374,8 +373,7 @@ xfs_efd_item_free(xfs_efd_log_item_t *efdp) int nexts = efdp->efd_format.efd_nextents; if (nexts > XFS_EFD_MAX_FAST_EXTENTS) { - kmem_free(efdp, sizeof(xfs_efd_log_item_t) + - (nexts - 1) * sizeof(xfs_extent_t)); + kmem_free(efdp); } else { kmem_zone_free(xfs_efd_zone, efdp); } diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h index 3bed6433d050..6ca749897c58 100644 --- a/fs/xfs/xfs_fs.h +++ b/fs/xfs/xfs_fs.h @@ -239,6 +239,7 @@ typedef struct xfs_fsop_resblks { #define XFS_FSOP_GEOM_FLAGS_LOGV2 0x0100 /* log format version 2 */ #define XFS_FSOP_GEOM_FLAGS_SECTOR 0x0200 /* sector sizes >1BB */ #define XFS_FSOP_GEOM_FLAGS_ATTR2 0x0400 /* inline attributes rework */ +#define XFS_FSOP_GEOM_FLAGS_DIRV2CI 0x1000 /* ASCII only CI names */ #define XFS_FSOP_GEOM_FLAGS_LAZYSB 0x4000 /* lazy superblock counters */ diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 381ebda4f7bc..84583cf73db3 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -95,6 +95,8 @@ xfs_fs_geometry( XFS_FSOP_GEOM_FLAGS_DIRV2 : 0) | (xfs_sb_version_hassector(&mp->m_sb) ? XFS_FSOP_GEOM_FLAGS_SECTOR : 0) | + (xfs_sb_version_hasasciici(&mp->m_sb) ? + XFS_FSOP_GEOM_FLAGS_DIRV2CI : 0) | (xfs_sb_version_haslazysbcount(&mp->m_sb) ? XFS_FSOP_GEOM_FLAGS_LAZYSB : 0) | (xfs_sb_version_hasattr2(&mp->m_sb) ? @@ -625,7 +627,7 @@ xfs_fs_goingdown( xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT); thaw_bdev(sb->s_bdev, sb); } - + break; } case XFS_FSOP_GOING_FLAGS_LOGFLUSH: diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index e569bf5d6cf0..199a36ac8e2d 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1763,67 +1763,6 @@ xfs_itruncate_finish( return 0; } - -/* - * xfs_igrow_start - * - * Do the first part of growing a file: zero any data in the last - * block that is beyond the old EOF. We need to do this before - * the inode is joined to the transaction to modify the i_size. - * That way we can drop the inode lock and call into the buffer - * cache to get the buffer mapping the EOF. - */ -int -xfs_igrow_start( - xfs_inode_t *ip, - xfs_fsize_t new_size, - cred_t *credp) -{ - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL)); - ASSERT(new_size > ip->i_size); - - /* - * Zero any pages that may have been created by - * xfs_write_file() beyond the end of the file - * and any blocks between the old and new file sizes. - */ - return xfs_zero_eof(ip, new_size, ip->i_size); -} - -/* - * xfs_igrow_finish - * - * This routine is called to extend the size of a file. - * The inode must have both the iolock and the ilock locked - * for update and it must be a part of the current transaction. - * The xfs_igrow_start() function must have been called previously. - * If the change_flag is not zero, the inode change timestamp will - * be updated. - */ -void -xfs_igrow_finish( - xfs_trans_t *tp, - xfs_inode_t *ip, - xfs_fsize_t new_size, - int change_flag) -{ - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL)); - ASSERT(ip->i_transp == tp); - ASSERT(new_size > ip->i_size); - - /* - * Update the file size. Update the inode change timestamp - * if change_flag set. - */ - ip->i_d.di_size = new_size; - ip->i_size = new_size; - if (change_flag) - xfs_ichgtime(ip, XFS_ICHGTIME_CHG); - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - -} - - /* * This is called when the inode's link count goes to 0. * We place the on-disk inode on a list in the AGI. It @@ -2258,7 +2197,7 @@ xfs_ifree_cluster( xfs_trans_binval(tp, bp); } - kmem_free(ip_found, ninodes * sizeof(xfs_inode_t *)); + kmem_free(ip_found); xfs_put_perag(mp, pag); } @@ -2470,7 +2409,7 @@ xfs_iroot_realloc( (int)new_size); memcpy(np, op, new_max * (uint)sizeof(xfs_dfsbno_t)); } - kmem_free(ifp->if_broot, ifp->if_broot_bytes); + kmem_free(ifp->if_broot); ifp->if_broot = new_broot; ifp->if_broot_bytes = (int)new_size; ASSERT(ifp->if_broot_bytes <= @@ -2514,7 +2453,7 @@ xfs_idata_realloc( if (new_size == 0) { if (ifp->if_u1.if_data != ifp->if_u2.if_inline_data) { - kmem_free(ifp->if_u1.if_data, ifp->if_real_bytes); + kmem_free(ifp->if_u1.if_data); } ifp->if_u1.if_data = NULL; real_size = 0; @@ -2529,7 +2468,7 @@ xfs_idata_realloc( ASSERT(ifp->if_real_bytes != 0); memcpy(ifp->if_u2.if_inline_data, ifp->if_u1.if_data, new_size); - kmem_free(ifp->if_u1.if_data, ifp->if_real_bytes); + kmem_free(ifp->if_u1.if_data); ifp->if_u1.if_data = ifp->if_u2.if_inline_data; } real_size = 0; @@ -2636,7 +2575,7 @@ xfs_idestroy_fork( ifp = XFS_IFORK_PTR(ip, whichfork); if (ifp->if_broot != NULL) { - kmem_free(ifp->if_broot, ifp->if_broot_bytes); + kmem_free(ifp->if_broot); ifp->if_broot = NULL; } @@ -2650,7 +2589,7 @@ xfs_idestroy_fork( if ((ifp->if_u1.if_data != ifp->if_u2.if_inline_data) && (ifp->if_u1.if_data != NULL)) { ASSERT(ifp->if_real_bytes != 0); - kmem_free(ifp->if_u1.if_data, ifp->if_real_bytes); + kmem_free(ifp->if_u1.if_data); ifp->if_u1.if_data = NULL; ifp->if_real_bytes = 0; } @@ -3058,7 +2997,7 @@ xfs_iflush_cluster( out_free: read_unlock(&pag->pag_ici_lock); - kmem_free(ilist, ilist_size); + kmem_free(ilist); return 0; @@ -3102,7 +3041,7 @@ cluster_corrupt_out: * Unlocks the flush lock */ xfs_iflush_abort(iq); - kmem_free(ilist, ilist_size); + kmem_free(ilist); return XFS_ERROR(EFSCORRUPTED); } @@ -3836,7 +3775,7 @@ xfs_iext_add_indirect_multi( erp = xfs_iext_irec_new(ifp, erp_idx); } memmove(&erp->er_extbuf[i], nex2_ep, byte_diff); - kmem_free(nex2_ep, byte_diff); + kmem_free(nex2_ep); erp->er_extcount += nex2; xfs_iext_irec_update_extoffs(ifp, erp_idx + 1, nex2); } @@ -4112,7 +4051,7 @@ xfs_iext_direct_to_inline( */ memcpy(ifp->if_u2.if_inline_ext, ifp->if_u1.if_extents, nextents * sizeof(xfs_bmbt_rec_t)); - kmem_free(ifp->if_u1.if_extents, ifp->if_real_bytes); + kmem_free(ifp->if_u1.if_extents); ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext; ifp->if_real_bytes = 0; } @@ -4186,7 +4125,7 @@ xfs_iext_indirect_to_direct( ASSERT(ifp->if_real_bytes == XFS_IEXT_BUFSZ); ep = ifp->if_u1.if_ext_irec->er_extbuf; - kmem_free(ifp->if_u1.if_ext_irec, sizeof(xfs_ext_irec_t)); + kmem_free(ifp->if_u1.if_ext_irec); ifp->if_flags &= ~XFS_IFEXTIREC; ifp->if_u1.if_extents = ep; ifp->if_bytes = size; @@ -4212,7 +4151,7 @@ xfs_iext_destroy( } ifp->if_flags &= ~XFS_IFEXTIREC; } else if (ifp->if_real_bytes) { - kmem_free(ifp->if_u1.if_extents, ifp->if_real_bytes); + kmem_free(ifp->if_u1.if_extents); } else if (ifp->if_bytes) { memset(ifp->if_u2.if_inline_ext, 0, XFS_INLINE_EXTS * sizeof(xfs_bmbt_rec_t)); @@ -4483,7 +4422,7 @@ xfs_iext_irec_remove( if (erp->er_extbuf) { xfs_iext_irec_update_extoffs(ifp, erp_idx + 1, -erp->er_extcount); - kmem_free(erp->er_extbuf, XFS_IEXT_BUFSZ); + kmem_free(erp->er_extbuf); } /* Compact extent records */ erp = ifp->if_u1.if_ext_irec; @@ -4501,8 +4440,7 @@ xfs_iext_irec_remove( xfs_iext_realloc_indirect(ifp, nlists * sizeof(xfs_ext_irec_t)); } else { - kmem_free(ifp->if_u1.if_ext_irec, - sizeof(xfs_ext_irec_t)); + kmem_free(ifp->if_u1.if_ext_irec); } ifp->if_real_bytes = nlists * XFS_IEXT_BUFSZ; } @@ -4571,7 +4509,7 @@ xfs_iext_irec_compact_pages( * so er_extoffs don't get modified in * xfs_iext_irec_remove. */ - kmem_free(erp_next->er_extbuf, XFS_IEXT_BUFSZ); + kmem_free(erp_next->er_extbuf); erp_next->er_extbuf = NULL; xfs_iext_irec_remove(ifp, erp_idx + 1); nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ; @@ -4614,8 +4552,7 @@ xfs_iext_irec_compact_full( * so er_extoffs don't get modified in * xfs_iext_irec_remove. */ - kmem_free(erp_next->er_extbuf, - erp_next->er_extcount * sizeof(xfs_bmbt_rec_t)); + kmem_free(erp_next->er_extbuf); erp_next->er_extbuf = NULL; xfs_iext_irec_remove(ifp, erp_idx + 1); erp = &ifp->if_u1.if_ext_irec[erp_idx]; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 0a999fee4f03..17a04b6321ed 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -507,9 +507,6 @@ int xfs_itruncate_start(xfs_inode_t *, uint, xfs_fsize_t); int xfs_itruncate_finish(struct xfs_trans **, xfs_inode_t *, xfs_fsize_t, int, int); int xfs_iunlink(struct xfs_trans *, xfs_inode_t *); -int xfs_igrow_start(xfs_inode_t *, xfs_fsize_t, struct cred *); -void xfs_igrow_finish(struct xfs_trans *, xfs_inode_t *, - xfs_fsize_t, int); void xfs_idestroy_fork(xfs_inode_t *, int); void xfs_idestroy(xfs_inode_t *); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 167b33f15772..0eee08a32c26 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -686,7 +686,7 @@ xfs_inode_item_unlock( ASSERT(ip->i_d.di_nextents > 0); ASSERT(iip->ili_format.ilf_fields & XFS_ILOG_DEXT); ASSERT(ip->i_df.if_bytes > 0); - kmem_free(iip->ili_extents_buf, ip->i_df.if_bytes); + kmem_free(iip->ili_extents_buf); iip->ili_extents_buf = NULL; } if (iip->ili_aextents_buf != NULL) { @@ -694,7 +694,7 @@ xfs_inode_item_unlock( ASSERT(ip->i_d.di_anextents > 0); ASSERT(iip->ili_format.ilf_fields & XFS_ILOG_AEXT); ASSERT(ip->i_afp->if_bytes > 0); - kmem_free(iip->ili_aextents_buf, ip->i_afp->if_bytes); + kmem_free(iip->ili_aextents_buf); iip->ili_aextents_buf = NULL; } @@ -957,8 +957,7 @@ xfs_inode_item_destroy( { #ifdef XFS_TRANS_DEBUG if (ip->i_itemp->ili_root_size != 0) { - kmem_free(ip->i_itemp->ili_orig_root, - ip->i_itemp->ili_root_size); + kmem_free(ip->i_itemp->ili_orig_root); } #endif kmem_zone_free(xfs_ili_zone, ip->i_itemp); diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 419de15aeb43..9a3ef9dcaeb9 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -257,7 +257,7 @@ xfs_bulkstat_one( *ubused = error; out_free: - kmem_free(buf, sizeof(*buf)); + kmem_free(buf); return error; } @@ -708,7 +708,7 @@ xfs_bulkstat( /* * Done, we're either out of filesystem or space to put the data. */ - kmem_free(irbuf, irbsize); + kmem_free(irbuf); *ubcountp = ubelem; /* * Found some inodes, return them now and return the error next time. @@ -914,7 +914,7 @@ xfs_inumbers( } *lastino = XFS_AGINO_TO_INO(mp, agno, agino); } - kmem_free(buffer, bcount * sizeof(*buffer)); + kmem_free(buffer); if (cur) xfs_btree_del_cursor(cur, (error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR)); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index afaee301b0ee..2497de885b0a 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -226,20 +226,24 @@ xlog_grant_sub_space(struct log *log, int bytes) static void xlog_grant_add_space_write(struct log *log, int bytes) { - log->l_grant_write_bytes += bytes; - if (log->l_grant_write_bytes > log->l_logsize) { - log->l_grant_write_bytes -= log->l_logsize; + int tmp = log->l_logsize - log->l_grant_write_bytes; + if (tmp > bytes) + log->l_grant_write_bytes += bytes; + else { log->l_grant_write_cycle++; + log->l_grant_write_bytes = bytes - tmp; } } static void xlog_grant_add_space_reserve(struct log *log, int bytes) { - log->l_grant_reserve_bytes += bytes; - if (log->l_grant_reserve_bytes > log->l_logsize) { - log->l_grant_reserve_bytes -= log->l_logsize; + int tmp = log->l_logsize - log->l_grant_reserve_bytes; + if (tmp > bytes) + log->l_grant_reserve_bytes += bytes; + else { log->l_grant_reserve_cycle++; + log->l_grant_reserve_bytes = bytes - tmp; } } @@ -1228,7 +1232,7 @@ xlog_alloc_log(xfs_mount_t *mp, spin_lock_init(&log->l_icloglock); spin_lock_init(&log->l_grant_lock); - initnsema(&log->l_flushsema, 0, "ic-flush"); + sv_init(&log->l_flush_wait, 0, "flush_wait"); /* log record size must be multiple of BBSIZE; see xlog_rec_header_t */ ASSERT((XFS_BUF_SIZE(bp) & BBMASK) == 0); @@ -1570,10 +1574,9 @@ xlog_dealloc_log(xlog_t *log) } #endif next_iclog = iclog->ic_next; - kmem_free(iclog, sizeof(xlog_in_core_t)); + kmem_free(iclog); iclog = next_iclog; } - freesema(&log->l_flushsema); spinlock_destroy(&log->l_icloglock); spinlock_destroy(&log->l_grant_lock); @@ -1587,7 +1590,7 @@ xlog_dealloc_log(xlog_t *log) } #endif log->l_mp->m_log = NULL; - kmem_free(log, sizeof(xlog_t)); + kmem_free(log); } /* xlog_dealloc_log */ /* @@ -2097,6 +2100,7 @@ xlog_state_do_callback( int funcdidcallbacks; /* flag: function did callbacks */ int repeats; /* for issuing console warnings if * looping too many times */ + int wake = 0; spin_lock(&log->l_icloglock); first_iclog = iclog = log->l_iclog; @@ -2278,15 +2282,13 @@ xlog_state_do_callback( } #endif - flushcnt = 0; - if (log->l_iclog->ic_state & (XLOG_STATE_ACTIVE|XLOG_STATE_IOERROR)) { - flushcnt = log->l_flushcnt; - log->l_flushcnt = 0; - } + if (log->l_iclog->ic_state & (XLOG_STATE_ACTIVE|XLOG_STATE_IOERROR)) + wake = 1; spin_unlock(&log->l_icloglock); - while (flushcnt--) - vsema(&log->l_flushsema); -} /* xlog_state_do_callback */ + + if (wake) + sv_broadcast(&log->l_flush_wait); +} /* @@ -2384,16 +2386,15 @@ restart: } iclog = log->l_iclog; - if (! (iclog->ic_state == XLOG_STATE_ACTIVE)) { - log->l_flushcnt++; - spin_unlock(&log->l_icloglock); + if (iclog->ic_state != XLOG_STATE_ACTIVE) { xlog_trace_iclog(iclog, XLOG_TRACE_SLEEP_FLUSH); XFS_STATS_INC(xs_log_noiclogs); - /* Ensure that log writes happen */ - psema(&log->l_flushsema, PINOD); + + /* Wait for log writes to have flushed */ + sv_wait(&log->l_flush_wait, 0, &log->l_icloglock, 0); goto restart; } - ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE); + head = &iclog->ic_header; atomic_inc(&iclog->ic_refcnt); /* prevents sync */ diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 8952a392b5f3..6245913196b4 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -423,10 +423,8 @@ typedef struct log { int l_logBBsize; /* size of log in BB chunks */ /* The following block of fields are changed while holding icloglock */ - sema_t l_flushsema ____cacheline_aligned_in_smp; - /* iclog flushing semaphore */ - int l_flushcnt; /* # of procs waiting on this - * sema */ + sv_t l_flush_wait ____cacheline_aligned_in_smp; + /* waiting for iclog flush */ int l_covered_state;/* state of "covering disk * log entries" */ xlog_in_core_t *l_iclog; /* head log queue */ diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index e65ab4af0955..9eb722ec744e 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1715,8 +1715,7 @@ xlog_check_buffer_cancelled( } else { prevp->bc_next = bcp->bc_next; } - kmem_free(bcp, - sizeof(xfs_buf_cancel_t)); + kmem_free(bcp); } } return 1; @@ -2519,7 +2518,7 @@ write_inode_buffer: error: if (need_free) - kmem_free(in_f, sizeof(*in_f)); + kmem_free(in_f); return XFS_ERROR(error); } @@ -2830,16 +2829,14 @@ xlog_recover_free_trans( item = item->ri_next; /* Free the regions in the item. */ for (i = 0; i < free_item->ri_cnt; i++) { - kmem_free(free_item->ri_buf[i].i_addr, - free_item->ri_buf[i].i_len); + kmem_free(free_item->ri_buf[i].i_addr); } /* Free the item itself */ - kmem_free(free_item->ri_buf, - (free_item->ri_total * sizeof(xfs_log_iovec_t))); - kmem_free(free_item, sizeof(xlog_recover_item_t)); + kmem_free(free_item->ri_buf); + kmem_free(free_item); } while (first_item != item); /* Free the transaction recover structure */ - kmem_free(trans, sizeof(xlog_recover_t)); + kmem_free(trans); } STATIC int @@ -3786,8 +3783,7 @@ xlog_do_log_recovery( error = xlog_do_recovery_pass(log, head_blk, tail_blk, XLOG_RECOVER_PASS1); if (error != 0) { - kmem_free(log->l_buf_cancel_table, - XLOG_BC_TABLE_SIZE * sizeof(xfs_buf_cancel_t*)); + kmem_free(log->l_buf_cancel_table); log->l_buf_cancel_table = NULL; return error; } @@ -3806,8 +3802,7 @@ xlog_do_log_recovery( } #endif /* DEBUG */ - kmem_free(log->l_buf_cancel_table, - XLOG_BC_TABLE_SIZE * sizeof(xfs_buf_cancel_t*)); + kmem_free(log->l_buf_cancel_table); log->l_buf_cancel_table = NULL; return error; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index da3988453b71..1bfaa204f689 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -47,12 +47,10 @@ STATIC int xfs_mount_log_sb(xfs_mount_t *, __int64_t); STATIC int xfs_uuid_mount(xfs_mount_t *); -STATIC void xfs_uuid_unmount(xfs_mount_t *mp); STATIC void xfs_unmountfs_wait(xfs_mount_t *); #ifdef HAVE_PERCPU_SB -STATIC void xfs_icsb_destroy_counters(xfs_mount_t *); STATIC void xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t, int); STATIC void xfs_icsb_balance_counter_locked(xfs_mount_t *, xfs_sb_field_t, @@ -63,7 +61,6 @@ STATIC void xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t); #else -#define xfs_icsb_destroy_counters(mp) do { } while (0) #define xfs_icsb_balance_counter(mp, a, b) do { } while (0) #define xfs_icsb_balance_counter_locked(mp, a, b) do { } while (0) #define xfs_icsb_modify_counters(mp, a, b, c) do { } while (0) @@ -126,33 +123,11 @@ static const struct { }; /* - * Return a pointer to an initialized xfs_mount structure. - */ -xfs_mount_t * -xfs_mount_init(void) -{ - xfs_mount_t *mp; - - mp = kmem_zalloc(sizeof(xfs_mount_t), KM_SLEEP); - - if (xfs_icsb_init_counters(mp)) { - mp->m_flags |= XFS_MOUNT_NO_PERCPU_SB; - } - - spin_lock_init(&mp->m_sb_lock); - mutex_init(&mp->m_ilock); - mutex_init(&mp->m_growlock); - atomic_set(&mp->m_active_trans, 0); - - return mp; -} - -/* * Free up the resources associated with a mount structure. Assume that * the structure was initially zeroed, so we can tell which fields got * initialized. */ -void +STATIC void xfs_mount_free( xfs_mount_t *mp) { @@ -161,11 +136,8 @@ xfs_mount_free( for (agno = 0; agno < mp->m_maxagi; agno++) if (mp->m_perag[agno].pagb_list) - kmem_free(mp->m_perag[agno].pagb_list, - sizeof(xfs_perag_busy_t) * - XFS_PAGB_NUM_SLOTS); - kmem_free(mp->m_perag, - sizeof(xfs_perag_t) * mp->m_sb.sb_agcount); + kmem_free(mp->m_perag[agno].pagb_list); + kmem_free(mp->m_perag); } spinlock_destroy(&mp->m_ail_lock); @@ -176,13 +148,11 @@ xfs_mount_free( XFS_QM_DONE(mp); if (mp->m_fsname != NULL) - kmem_free(mp->m_fsname, mp->m_fsname_len); + kmem_free(mp->m_fsname); if (mp->m_rtname != NULL) - kmem_free(mp->m_rtname, strlen(mp->m_rtname) + 1); + kmem_free(mp->m_rtname); if (mp->m_logname != NULL) - kmem_free(mp->m_logname, strlen(mp->m_logname) + 1); - - xfs_icsb_destroy_counters(mp); + kmem_free(mp->m_logname); } /* @@ -994,9 +964,19 @@ xfs_mountfs( * Re-check for ATTR2 in case it was found in bad_features2 * slot. */ - if (xfs_sb_version_hasattr2(&mp->m_sb)) + if (xfs_sb_version_hasattr2(&mp->m_sb) && + !(mp->m_flags & XFS_MOUNT_NOATTR2)) mp->m_flags |= XFS_MOUNT_ATTR2; + } + + if (xfs_sb_version_hasattr2(&mp->m_sb) && + (mp->m_flags & XFS_MOUNT_NOATTR2)) { + xfs_sb_version_removeattr2(&mp->m_sb); + update_flags |= XFS_SB_FEATURES2; + /* update sb_versionnum for the clearing of the morebits */ + if (!sbp->sb_features2) + update_flags |= XFS_SB_VERSIONNUM; } /* @@ -1255,15 +1235,13 @@ xfs_mountfs( error2: for (agno = 0; agno < sbp->sb_agcount; agno++) if (mp->m_perag[agno].pagb_list) - kmem_free(mp->m_perag[agno].pagb_list, - sizeof(xfs_perag_busy_t) * XFS_PAGB_NUM_SLOTS); - kmem_free(mp->m_perag, sbp->sb_agcount * sizeof(xfs_perag_t)); + kmem_free(mp->m_perag[agno].pagb_list); + kmem_free(mp->m_perag); mp->m_perag = NULL; /* FALLTHROUGH */ error1: if (uuid_mounted) - xfs_uuid_unmount(mp); - xfs_freesb(mp); + uuid_table_remove(&mp->m_sb.sb_uuid); return error; } @@ -1274,7 +1252,7 @@ xfs_mountfs( * log and makes sure that incore structures are freed. */ int -xfs_unmountfs(xfs_mount_t *mp, struct cred *cr) +xfs_unmountfs(xfs_mount_t *mp) { __uint64_t resblks; int error = 0; @@ -1341,9 +1319,8 @@ xfs_unmountfs(xfs_mount_t *mp, struct cred *cr) */ ASSERT(mp->m_inodes == NULL); - xfs_unmountfs_close(mp, cr); if ((mp->m_flags & XFS_MOUNT_NOUUID) == 0) - xfs_uuid_unmount(mp); + uuid_table_remove(&mp->m_sb.sb_uuid); #if defined(DEBUG) || defined(INDUCE_IO_ERROR) xfs_errortag_clearall(mp, 0); @@ -1352,16 +1329,6 @@ xfs_unmountfs(xfs_mount_t *mp, struct cred *cr) return 0; } -void -xfs_unmountfs_close(xfs_mount_t *mp, struct cred *cr) -{ - if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) - xfs_free_buftarg(mp->m_logdev_targp, 1); - if (mp->m_rtdev_targp) - xfs_free_buftarg(mp->m_rtdev_targp, 1); - xfs_free_buftarg(mp->m_ddev_targp, 0); -} - STATIC void xfs_unmountfs_wait(xfs_mount_t *mp) { @@ -1905,16 +1872,6 @@ xfs_uuid_mount( } /* - * Remove filesystem from the UUID table. - */ -STATIC void -xfs_uuid_unmount( - xfs_mount_t *mp) -{ - uuid_table_remove(&mp->m_sb.sb_uuid); -} - -/* * Used to log changes to the superblock unit and width fields which could * be altered by the mount options, as well as any potential sb_features2 * fixup. Only the first superblock is updated. @@ -1928,7 +1885,8 @@ xfs_mount_log_sb( int error; ASSERT(fields & (XFS_SB_UNIT | XFS_SB_WIDTH | XFS_SB_UUID | - XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2)); + XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2 | + XFS_SB_VERSIONNUM)); tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT); error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0, @@ -2109,7 +2067,7 @@ xfs_icsb_reinit_counters( xfs_icsb_unlock(mp); } -STATIC void +void xfs_icsb_destroy_counters( xfs_mount_t *mp) { diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 63e0693a358a..dbba68f8c771 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -61,6 +61,7 @@ struct xfs_bmap_free; struct xfs_extdelta; struct xfs_swapext; struct xfs_mru_cache; +struct xfs_nameops; /* * Prototypes and functions for the Data Migration subsystem. @@ -210,12 +211,14 @@ typedef struct xfs_icsb_cnts { extern int xfs_icsb_init_counters(struct xfs_mount *); extern void xfs_icsb_reinit_counters(struct xfs_mount *); +extern void xfs_icsb_destroy_counters(struct xfs_mount *); extern void xfs_icsb_sync_counters(struct xfs_mount *, int); extern void xfs_icsb_sync_counters_locked(struct xfs_mount *, int); #else -#define xfs_icsb_init_counters(mp) (0) -#define xfs_icsb_reinit_counters(mp) do { } while (0) +#define xfs_icsb_init_counters(mp) (0) +#define xfs_icsb_destroy_counters(mp) do { } while (0) +#define xfs_icsb_reinit_counters(mp) do { } while (0) #define xfs_icsb_sync_counters(mp, flags) do { } while (0) #define xfs_icsb_sync_counters_locked(mp, flags) do { } while (0) #endif @@ -313,6 +316,7 @@ typedef struct xfs_mount { __uint8_t m_inode_quiesce;/* call quiesce on new inodes. field governed by m_ilock */ __uint8_t m_sectbb_log; /* sectlog - BBSHIFT */ + const struct xfs_nameops *m_dirnameops; /* vector of dir name ops */ int m_dirblksize; /* directory block sz--bytes */ int m_dirblkfsbs; /* directory block sz--fsbs */ xfs_dablk_t m_dirdatablk; /* blockno of dir data v2 */ @@ -337,6 +341,7 @@ typedef struct xfs_mount { spinlock_t m_sync_lock; /* work item list lock */ int m_sync_seq; /* sync thread generation no. */ wait_queue_head_t m_wait_single_sync_task; + struct vfsmount *m_vfsmount; } xfs_mount_t; /* @@ -378,6 +383,7 @@ typedef struct xfs_mount { counters */ #define XFS_MOUNT_FILESTREAMS (1ULL << 24) /* enable the filestreams allocator */ +#define XFS_MOUNT_NOATTR2 (1ULL << 25) /* disable use of attr2 format */ /* @@ -510,15 +516,12 @@ typedef struct xfs_mod_sb { #define XFS_MOUNT_ILOCK(mp) mutex_lock(&((mp)->m_ilock)) #define XFS_MOUNT_IUNLOCK(mp) mutex_unlock(&((mp)->m_ilock)) -extern xfs_mount_t *xfs_mount_init(void); extern void xfs_mod_sb(xfs_trans_t *, __int64_t); extern int xfs_log_sbcount(xfs_mount_t *, uint); -extern void xfs_mount_free(xfs_mount_t *mp); extern int xfs_mountfs(xfs_mount_t *mp, int); extern void xfs_mountfs_check_barriers(xfs_mount_t *mp); -extern int xfs_unmountfs(xfs_mount_t *, struct cred *); -extern void xfs_unmountfs_close(xfs_mount_t *, struct cred *); +extern int xfs_unmountfs(xfs_mount_t *); extern int xfs_unmountfs_writesb(xfs_mount_t *); extern int xfs_unmount_flush(xfs_mount_t *, int); extern int xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int); diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c index a0b2c0a2589a..26d14a1e0e14 100644 --- a/fs/xfs/xfs_mru_cache.c +++ b/fs/xfs/xfs_mru_cache.c @@ -382,9 +382,9 @@ xfs_mru_cache_create( exit: if (err && mru && mru->lists) - kmem_free(mru->lists, mru->grp_count * sizeof(*mru->lists)); + kmem_free(mru->lists); if (err && mru) - kmem_free(mru, sizeof(*mru)); + kmem_free(mru); return err; } @@ -424,8 +424,8 @@ xfs_mru_cache_destroy( xfs_mru_cache_flush(mru); - kmem_free(mru->lists, mru->grp_count * sizeof(*mru->lists)); - kmem_free(mru, sizeof(*mru)); + kmem_free(mru->lists); + kmem_free(mru); } /* diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index a0dc6e5bc5b9..bf87a5913504 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -2062,7 +2062,7 @@ xfs_growfs_rt( /* * Free the fake mp structure. */ - kmem_free(nmp, sizeof(*nmp)); + kmem_free(nmp); return error; } diff --git a/fs/xfs/xfs_sb.h b/fs/xfs/xfs_sb.h index d904efe7f871..3f8cf1587f4c 100644 --- a/fs/xfs/xfs_sb.h +++ b/fs/xfs/xfs_sb.h @@ -46,10 +46,12 @@ struct xfs_mount; #define XFS_SB_VERSION_SECTORBIT 0x0800 #define XFS_SB_VERSION_EXTFLGBIT 0x1000 #define XFS_SB_VERSION_DIRV2BIT 0x2000 +#define XFS_SB_VERSION_BORGBIT 0x4000 /* ASCII only case-insens. */ #define XFS_SB_VERSION_MOREBITSBIT 0x8000 #define XFS_SB_VERSION_OKSASHFBITS \ (XFS_SB_VERSION_EXTFLGBIT | \ - XFS_SB_VERSION_DIRV2BIT) + XFS_SB_VERSION_DIRV2BIT | \ + XFS_SB_VERSION_BORGBIT) #define XFS_SB_VERSION_OKREALFBITS \ (XFS_SB_VERSION_ATTRBIT | \ XFS_SB_VERSION_NLINKBIT | \ @@ -437,6 +439,12 @@ static inline int xfs_sb_version_hassector(xfs_sb_t *sbp) ((sbp)->sb_versionnum & XFS_SB_VERSION_SECTORBIT); } +static inline int xfs_sb_version_hasasciici(xfs_sb_t *sbp) +{ + return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \ + (sbp->sb_versionnum & XFS_SB_VERSION_BORGBIT); +} + static inline int xfs_sb_version_hasmorebits(xfs_sb_t *sbp) { return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \ @@ -473,6 +481,13 @@ static inline void xfs_sb_version_addattr2(xfs_sb_t *sbp) ((sbp)->sb_features2 | XFS_SB_VERSION2_ATTR2BIT))); } +static inline void xfs_sb_version_removeattr2(xfs_sb_t *sbp) +{ + sbp->sb_features2 &= ~XFS_SB_VERSION2_ATTR2BIT; + if (!sbp->sb_features2) + sbp->sb_versionnum &= ~XFS_SB_VERSION_MOREBITSBIT; +} + /* * end of superblock version macros */ diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 140386434aa3..e4ebddd3c500 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -889,7 +889,7 @@ shut_us_down: tp->t_commit_lsn = commit_lsn; if (nvec > XFS_TRANS_LOGVEC_COUNT) { - kmem_free(log_vector, nvec * sizeof(xfs_log_iovec_t)); + kmem_free(log_vector); } /* @@ -1265,7 +1265,7 @@ xfs_trans_committed( ASSERT(!XFS_LIC_ARE_ALL_FREE(licp)); xfs_trans_chunk_committed(licp, tp->t_lsn, abortflag); next_licp = licp->lic_next; - kmem_free(licp, sizeof(xfs_log_item_chunk_t)); + kmem_free(licp); licp = next_licp; } diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c index 4c70bf5e9985..2a1c0f071f91 100644 --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -291,7 +291,7 @@ xfs_trans_inode_broot_debug( iip = ip->i_itemp; if (iip->ili_root_size != 0) { ASSERT(iip->ili_orig_root != NULL); - kmem_free(iip->ili_orig_root, iip->ili_root_size); + kmem_free(iip->ili_orig_root); iip->ili_root_size = 0; iip->ili_orig_root = NULL; } diff --git a/fs/xfs/xfs_trans_item.c b/fs/xfs/xfs_trans_item.c index 66a09f0d894b..db5c83595526 100644 --- a/fs/xfs/xfs_trans_item.c +++ b/fs/xfs/xfs_trans_item.c @@ -161,7 +161,7 @@ xfs_trans_free_item(xfs_trans_t *tp, xfs_log_item_desc_t *lidp) licpp = &((*licpp)->lic_next); } *licpp = licp->lic_next; - kmem_free(licp, sizeof(xfs_log_item_chunk_t)); + kmem_free(licp); tp->t_items_free -= XFS_LIC_NUM_SLOTS; } } @@ -314,7 +314,7 @@ xfs_trans_free_items( ASSERT(!XFS_LIC_ARE_ALL_FREE(licp)); (void) xfs_trans_unlock_chunk(licp, 1, abort, NULLCOMMITLSN); next_licp = licp->lic_next; - kmem_free(licp, sizeof(xfs_log_item_chunk_t)); + kmem_free(licp); licp = next_licp; } @@ -363,7 +363,7 @@ xfs_trans_unlock_items(xfs_trans_t *tp, xfs_lsn_t commit_lsn) next_licp = licp->lic_next; if (XFS_LIC_ARE_ALL_FREE(licp)) { *licpp = next_licp; - kmem_free(licp, sizeof(xfs_log_item_chunk_t)); + kmem_free(licp); freed -= XFS_LIC_NUM_SLOTS; } else { licpp = &(licp->lic_next); @@ -530,7 +530,7 @@ xfs_trans_free_busy(xfs_trans_t *tp) lbcp = tp->t_busy.lbc_next; while (lbcp != NULL) { lbcq = lbcp->lbc_next; - kmem_free(lbcp, sizeof(xfs_log_busy_chunk_t)); + kmem_free(lbcp); lbcp = lbcq; } diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c index 30bacd8bb0e5..8b5a3376c2f7 100644 --- a/fs/xfs/xfs_vfsops.c +++ b/fs/xfs/xfs_vfsops.c @@ -189,455 +189,6 @@ xfs_cleanup(void) kmem_zone_destroy(xfs_log_ticket_zone); } -/* - * xfs_start_flags - * - * This function fills in xfs_mount_t fields based on mount args. - * Note: the superblock has _not_ yet been read in. - */ -STATIC int -xfs_start_flags( - struct xfs_mount_args *ap, - struct xfs_mount *mp) -{ - /* Values are in BBs */ - if ((ap->flags & XFSMNT_NOALIGN) != XFSMNT_NOALIGN) { - /* - * At this point the superblock has not been read - * in, therefore we do not know the block size. - * Before the mount call ends we will convert - * these to FSBs. - */ - mp->m_dalign = ap->sunit; - mp->m_swidth = ap->swidth; - } - - if (ap->logbufs != -1 && - ap->logbufs != 0 && - (ap->logbufs < XLOG_MIN_ICLOGS || - ap->logbufs > XLOG_MAX_ICLOGS)) { - cmn_err(CE_WARN, - "XFS: invalid logbufs value: %d [not %d-%d]", - ap->logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS); - return XFS_ERROR(EINVAL); - } - mp->m_logbufs = ap->logbufs; - if (ap->logbufsize != -1 && - ap->logbufsize != 0 && - (ap->logbufsize < XLOG_MIN_RECORD_BSIZE || - ap->logbufsize > XLOG_MAX_RECORD_BSIZE || - !is_power_of_2(ap->logbufsize))) { - cmn_err(CE_WARN, - "XFS: invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]", - ap->logbufsize); - return XFS_ERROR(EINVAL); - } - mp->m_logbsize = ap->logbufsize; - mp->m_fsname_len = strlen(ap->fsname) + 1; - mp->m_fsname = kmem_alloc(mp->m_fsname_len, KM_SLEEP); - strcpy(mp->m_fsname, ap->fsname); - if (ap->rtname[0]) { - mp->m_rtname = kmem_alloc(strlen(ap->rtname) + 1, KM_SLEEP); - strcpy(mp->m_rtname, ap->rtname); - } - if (ap->logname[0]) { - mp->m_logname = kmem_alloc(strlen(ap->logname) + 1, KM_SLEEP); - strcpy(mp->m_logname, ap->logname); - } - - if (ap->flags & XFSMNT_WSYNC) - mp->m_flags |= XFS_MOUNT_WSYNC; -#if XFS_BIG_INUMS - if (ap->flags & XFSMNT_INO64) { - mp->m_flags |= XFS_MOUNT_INO64; - mp->m_inoadd = XFS_INO64_OFFSET; - } -#endif - if (ap->flags & XFSMNT_RETERR) - mp->m_flags |= XFS_MOUNT_RETERR; - if (ap->flags & XFSMNT_NOALIGN) - mp->m_flags |= XFS_MOUNT_NOALIGN; - if (ap->flags & XFSMNT_SWALLOC) - mp->m_flags |= XFS_MOUNT_SWALLOC; - if (ap->flags & XFSMNT_OSYNCISOSYNC) - mp->m_flags |= XFS_MOUNT_OSYNCISOSYNC; - if (ap->flags & XFSMNT_32BITINODES) - mp->m_flags |= XFS_MOUNT_32BITINODES; - - if (ap->flags & XFSMNT_IOSIZE) { - if (ap->iosizelog > XFS_MAX_IO_LOG || - ap->iosizelog < XFS_MIN_IO_LOG) { - cmn_err(CE_WARN, - "XFS: invalid log iosize: %d [not %d-%d]", - ap->iosizelog, XFS_MIN_IO_LOG, - XFS_MAX_IO_LOG); - return XFS_ERROR(EINVAL); - } - - mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE; - mp->m_readio_log = mp->m_writeio_log = ap->iosizelog; - } - - if (ap->flags & XFSMNT_IKEEP) - mp->m_flags |= XFS_MOUNT_IKEEP; - if (ap->flags & XFSMNT_DIRSYNC) - mp->m_flags |= XFS_MOUNT_DIRSYNC; - if (ap->flags & XFSMNT_ATTR2) - mp->m_flags |= XFS_MOUNT_ATTR2; - - if (ap->flags2 & XFSMNT2_COMPAT_IOSIZE) - mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE; - - /* - * no recovery flag requires a read-only mount - */ - if (ap->flags & XFSMNT_NORECOVERY) { - if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { - cmn_err(CE_WARN, - "XFS: tried to mount a FS read-write without recovery!"); - return XFS_ERROR(EINVAL); - } - mp->m_flags |= XFS_MOUNT_NORECOVERY; - } - - if (ap->flags & XFSMNT_NOUUID) - mp->m_flags |= XFS_MOUNT_NOUUID; - if (ap->flags & XFSMNT_BARRIER) - mp->m_flags |= XFS_MOUNT_BARRIER; - else - mp->m_flags &= ~XFS_MOUNT_BARRIER; - - if (ap->flags2 & XFSMNT2_FILESTREAMS) - mp->m_flags |= XFS_MOUNT_FILESTREAMS; - - if (ap->flags & XFSMNT_DMAPI) - mp->m_flags |= XFS_MOUNT_DMAPI; - return 0; -} - -/* - * This function fills in xfs_mount_t fields based on mount args. - * Note: the superblock _has_ now been read in. - */ -STATIC int -xfs_finish_flags( - struct xfs_mount_args *ap, - struct xfs_mount *mp) -{ - int ronly = (mp->m_flags & XFS_MOUNT_RDONLY); - - /* Fail a mount where the logbuf is smaller then the log stripe */ - if (xfs_sb_version_haslogv2(&mp->m_sb)) { - if ((ap->logbufsize <= 0) && - (mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE)) { - mp->m_logbsize = mp->m_sb.sb_logsunit; - } else if (ap->logbufsize > 0 && - ap->logbufsize < mp->m_sb.sb_logsunit) { - cmn_err(CE_WARN, - "XFS: logbuf size must be greater than or equal to log stripe size"); - return XFS_ERROR(EINVAL); - } - } else { - /* Fail a mount if the logbuf is larger than 32K */ - if (ap->logbufsize > XLOG_BIG_RECORD_BSIZE) { - cmn_err(CE_WARN, - "XFS: logbuf size for version 1 logs must be 16K or 32K"); - return XFS_ERROR(EINVAL); - } - } - - if (xfs_sb_version_hasattr2(&mp->m_sb)) - mp->m_flags |= XFS_MOUNT_ATTR2; - - /* - * prohibit r/w mounts of read-only filesystems - */ - if ((mp->m_sb.sb_flags & XFS_SBF_READONLY) && !ronly) { - cmn_err(CE_WARN, - "XFS: cannot mount a read-only filesystem as read-write"); - return XFS_ERROR(EROFS); - } - - /* - * check for shared mount. - */ - if (ap->flags & XFSMNT_SHARED) { - if (!xfs_sb_version_hasshared(&mp->m_sb)) - return XFS_ERROR(EINVAL); - - /* - * For IRIX 6.5, shared mounts must have the shared - * version bit set, have the persistent readonly - * field set, must be version 0 and can only be mounted - * read-only. - */ - if (!ronly || !(mp->m_sb.sb_flags & XFS_SBF_READONLY) || - (mp->m_sb.sb_shared_vn != 0)) - return XFS_ERROR(EINVAL); - - mp->m_flags |= XFS_MOUNT_SHARED; - - /* - * Shared XFS V0 can't deal with DMI. Return EINVAL. - */ - if (mp->m_sb.sb_shared_vn == 0 && (ap->flags & XFSMNT_DMAPI)) - return XFS_ERROR(EINVAL); - } - - if (ap->flags & XFSMNT_UQUOTA) { - mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE); - if (ap->flags & XFSMNT_UQUOTAENF) - mp->m_qflags |= XFS_UQUOTA_ENFD; - } - - if (ap->flags & XFSMNT_GQUOTA) { - mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE); - if (ap->flags & XFSMNT_GQUOTAENF) - mp->m_qflags |= XFS_OQUOTA_ENFD; - } else if (ap->flags & XFSMNT_PQUOTA) { - mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE); - if (ap->flags & XFSMNT_PQUOTAENF) - mp->m_qflags |= XFS_OQUOTA_ENFD; - } - - return 0; -} - -/* - * xfs_mount - * - * The file system configurations are: - * (1) device (partition) with data and internal log - * (2) logical volume with data and log subvolumes. - * (3) logical volume with data, log, and realtime subvolumes. - * - * We only have to handle opening the log and realtime volumes here if - * they are present. The data subvolume has already been opened by - * get_sb_bdev() and is stored in vfsp->vfs_super->s_bdev. - */ -int -xfs_mount( - struct xfs_mount *mp, - struct xfs_mount_args *args, - cred_t *credp) -{ - struct block_device *ddev, *logdev, *rtdev; - int flags = 0, error; - - ddev = mp->m_super->s_bdev; - logdev = rtdev = NULL; - - error = xfs_dmops_get(mp, args); - if (error) - return error; - error = xfs_qmops_get(mp, args); - if (error) - return error; - - if (args->flags & XFSMNT_QUIET) - flags |= XFS_MFSI_QUIET; - - /* - * Open real time and log devices - order is important. - */ - if (args->logname[0]) { - error = xfs_blkdev_get(mp, args->logname, &logdev); - if (error) - return error; - } - if (args->rtname[0]) { - error = xfs_blkdev_get(mp, args->rtname, &rtdev); - if (error) { - xfs_blkdev_put(logdev); - return error; - } - - if (rtdev == ddev || rtdev == logdev) { - cmn_err(CE_WARN, - "XFS: Cannot mount filesystem with identical rtdev and ddev/logdev."); - xfs_blkdev_put(logdev); - xfs_blkdev_put(rtdev); - return EINVAL; - } - } - - /* - * Setup xfs_mount buffer target pointers - */ - error = ENOMEM; - mp->m_ddev_targp = xfs_alloc_buftarg(ddev, 0); - if (!mp->m_ddev_targp) { - xfs_blkdev_put(logdev); - xfs_blkdev_put(rtdev); - return error; - } - if (rtdev) { - mp->m_rtdev_targp = xfs_alloc_buftarg(rtdev, 1); - if (!mp->m_rtdev_targp) { - xfs_blkdev_put(logdev); - xfs_blkdev_put(rtdev); - goto error0; - } - } - mp->m_logdev_targp = (logdev && logdev != ddev) ? - xfs_alloc_buftarg(logdev, 1) : mp->m_ddev_targp; - if (!mp->m_logdev_targp) { - xfs_blkdev_put(logdev); - xfs_blkdev_put(rtdev); - goto error0; - } - - /* - * Setup flags based on mount(2) options and then the superblock - */ - error = xfs_start_flags(args, mp); - if (error) - goto error1; - error = xfs_readsb(mp, flags); - if (error) - goto error1; - error = xfs_finish_flags(args, mp); - if (error) - goto error2; - - /* - * Setup xfs_mount buffer target pointers based on superblock - */ - error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_blocksize, - mp->m_sb.sb_sectsize); - if (!error && logdev && logdev != ddev) { - unsigned int log_sector_size = BBSIZE; - - if (xfs_sb_version_hassector(&mp->m_sb)) - log_sector_size = mp->m_sb.sb_logsectsize; - error = xfs_setsize_buftarg(mp->m_logdev_targp, - mp->m_sb.sb_blocksize, - log_sector_size); - } - if (!error && rtdev) - error = xfs_setsize_buftarg(mp->m_rtdev_targp, - mp->m_sb.sb_blocksize, - mp->m_sb.sb_sectsize); - if (error) - goto error2; - - if (mp->m_flags & XFS_MOUNT_BARRIER) - xfs_mountfs_check_barriers(mp); - - if ((error = xfs_filestream_mount(mp))) - goto error2; - - error = xfs_mountfs(mp, flags); - if (error) - goto error2; - - XFS_SEND_MOUNT(mp, DM_RIGHT_NULL, args->mtpt, args->fsname); - - return 0; - -error2: - if (mp->m_sb_bp) - xfs_freesb(mp); -error1: - xfs_binval(mp->m_ddev_targp); - if (logdev && logdev != ddev) - xfs_binval(mp->m_logdev_targp); - if (rtdev) - xfs_binval(mp->m_rtdev_targp); -error0: - xfs_unmountfs_close(mp, credp); - xfs_qmops_put(mp); - xfs_dmops_put(mp); - return error; -} - -int -xfs_unmount( - xfs_mount_t *mp, - int flags, - cred_t *credp) -{ - xfs_inode_t *rip; - bhv_vnode_t *rvp; - int unmount_event_wanted = 0; - int unmount_event_flags = 0; - int xfs_unmountfs_needed = 0; - int error; - - rip = mp->m_rootip; - rvp = XFS_ITOV(rip); - -#ifdef HAVE_DMAPI - if (mp->m_flags & XFS_MOUNT_DMAPI) { - error = XFS_SEND_PREUNMOUNT(mp, - rip, DM_RIGHT_NULL, rip, DM_RIGHT_NULL, - NULL, NULL, 0, 0, - (mp->m_dmevmask & (1<<DM_EVENT_PREUNMOUNT))? - 0:DM_FLAGS_UNWANTED); - if (error) - return XFS_ERROR(error); - unmount_event_wanted = 1; - unmount_event_flags = (mp->m_dmevmask & (1<<DM_EVENT_UNMOUNT))? - 0 : DM_FLAGS_UNWANTED; - } -#endif - - /* - * Blow away any referenced inode in the filestreams cache. - * This can and will cause log traffic as inodes go inactive - * here. - */ - xfs_filestream_unmount(mp); - - XFS_bflush(mp->m_ddev_targp); - error = xfs_unmount_flush(mp, 0); - if (error) - goto out; - - ASSERT(vn_count(rvp) == 1); - - /* - * Drop the reference count - */ - IRELE(rip); - - /* - * If we're forcing a shutdown, typically because of a media error, - * we want to make sure we invalidate dirty pages that belong to - * referenced vnodes as well. - */ - if (XFS_FORCED_SHUTDOWN(mp)) { - error = xfs_sync(mp, SYNC_WAIT | SYNC_CLOSE); - ASSERT(error != EFSCORRUPTED); - } - xfs_unmountfs_needed = 1; - -out: - /* Send DMAPI event, if required. - * Then do xfs_unmountfs() if needed. - * Then return error (or zero). - */ - if (unmount_event_wanted) { - /* Note: mp structure must still exist for - * XFS_SEND_UNMOUNT() call. - */ - XFS_SEND_UNMOUNT(mp, error == 0 ? rip : NULL, - DM_RIGHT_NULL, 0, error, unmount_event_flags); - } - if (xfs_unmountfs_needed) { - /* - * Call common unmount function to flush to disk - * and free the super block buffer & mount structures. - */ - xfs_unmountfs(mp, credp); - xfs_qmops_put(mp); - xfs_dmops_put(mp); - kmem_free(mp, sizeof(xfs_mount_t)); - } - - return XFS_ERROR(error); -} - STATIC void xfs_quiesce_fs( xfs_mount_t *mp) @@ -694,30 +245,6 @@ xfs_attr_quiesce( xfs_unmountfs_writesb(mp); } -int -xfs_mntupdate( - struct xfs_mount *mp, - int *flags, - struct xfs_mount_args *args) -{ - if (!(*flags & MS_RDONLY)) { /* rw/ro -> rw */ - if (mp->m_flags & XFS_MOUNT_RDONLY) - mp->m_flags &= ~XFS_MOUNT_RDONLY; - if (args->flags & XFSMNT_BARRIER) { - mp->m_flags |= XFS_MOUNT_BARRIER; - xfs_mountfs_check_barriers(mp); - } else { - mp->m_flags &= ~XFS_MOUNT_BARRIER; - } - } else if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { /* rw -> ro */ - xfs_filestream_flush(mp); - xfs_sync(mp, SYNC_DATA_QUIESCE); - xfs_attr_quiesce(mp); - mp->m_flags |= XFS_MOUNT_RDONLY; - } - return 0; -} - /* * xfs_unmount_flush implements a set of flush operation on special * inodes, which are needed as a separate set of operations so that @@ -1048,7 +575,7 @@ xfs_sync_inodes( if (XFS_FORCED_SHUTDOWN(mp) && !(flags & SYNC_CLOSE)) { XFS_MOUNT_IUNLOCK(mp); - kmem_free(ipointer, sizeof(xfs_iptr_t)); + kmem_free(ipointer); return 0; } @@ -1194,7 +721,7 @@ xfs_sync_inodes( } XFS_MOUNT_IUNLOCK(mp); ASSERT(ipointer_in == B_FALSE); - kmem_free(ipointer, sizeof(xfs_iptr_t)); + kmem_free(ipointer); return XFS_ERROR(error); } @@ -1224,7 +751,7 @@ xfs_sync_inodes( ASSERT(ipointer_in == B_FALSE); - kmem_free(ipointer, sizeof(xfs_iptr_t)); + kmem_free(ipointer); return XFS_ERROR(last_error); } diff --git a/fs/xfs/xfs_vfsops.h b/fs/xfs/xfs_vfsops.h index 1688817c55ed..a74b05087da4 100644 --- a/fs/xfs/xfs_vfsops.h +++ b/fs/xfs/xfs_vfsops.h @@ -8,11 +8,6 @@ struct kstatfs; struct xfs_mount; struct xfs_mount_args; -int xfs_mount(struct xfs_mount *mp, struct xfs_mount_args *args, - struct cred *credp); -int xfs_unmount(struct xfs_mount *mp, int flags, struct cred *credp); -int xfs_mntupdate(struct xfs_mount *mp, int *flags, - struct xfs_mount_args *args); int xfs_sync(struct xfs_mount *mp, int flags); void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname, int lnnum); diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index e475e3717eb3..b6a065eb25a5 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -444,7 +444,13 @@ xfs_setattr( code = 0; if ((vap->va_size > ip->i_size) && (flags & ATTR_NOSIZETOK) == 0) { - code = xfs_igrow_start(ip, vap->va_size, credp); + /* + * Do the first part of growing a file: zero any data + * in the last block that is beyond the old EOF. We + * need to do this before the inode is joined to the + * transaction to modify the i_size. + */ + code = xfs_zero_eof(ip, vap->va_size, ip->i_size); } xfs_iunlock(ip, XFS_ILOCK_EXCL); @@ -512,8 +518,11 @@ xfs_setattr( timeflags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; if (vap->va_size > ip->i_size) { - xfs_igrow_finish(tp, ip, vap->va_size, - !(flags & ATTR_DMI)); + ip->i_d.di_size = vap->va_size; + ip->i_size = vap->va_size; + if (!(flags & ATTR_DMI)) + xfs_ichgtime(ip, XFS_ICHGTIME_CHG); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } else if ((vap->va_size <= ip->i_size) || ((vap->va_size == 0) && ip->i_d.di_nextents)) { /* @@ -1601,12 +1610,18 @@ xfs_inactive( return VN_INACTIVE_CACHE; } - +/* + * Lookups up an inode from "name". If ci_name is not NULL, then a CI match + * is allowed, otherwise it has to be an exact match. If a CI match is found, + * ci_name->name will point to a the actual name (caller must free) or + * will be set to NULL if an exact match is found. + */ int xfs_lookup( xfs_inode_t *dp, struct xfs_name *name, - xfs_inode_t **ipp) + xfs_inode_t **ipp, + struct xfs_name *ci_name) { xfs_ino_t inum; int error; @@ -1618,7 +1633,7 @@ xfs_lookup( return XFS_ERROR(EIO); lock_mode = xfs_ilock_map_shared(dp); - error = xfs_dir_lookup(NULL, dp, name, &inum); + error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name); xfs_iunlock_map_shared(dp, lock_mode); if (error) @@ -1626,12 +1641,15 @@ xfs_lookup( error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp, 0); if (error) - goto out; + goto out_free_name; xfs_itrace_ref(*ipp); return 0; - out: +out_free_name: + if (ci_name) + kmem_free(ci_name->name); +out: *ipp = NULL; return error; } diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h index 57335ba4ce53..7e9a8b241f21 100644 --- a/fs/xfs/xfs_vnodeops.h +++ b/fs/xfs/xfs_vnodeops.h @@ -22,7 +22,7 @@ int xfs_fsync(struct xfs_inode *ip); int xfs_release(struct xfs_inode *ip); int xfs_inactive(struct xfs_inode *ip); int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name, - struct xfs_inode **ipp); + struct xfs_inode **ipp, struct xfs_name *ci_name); int xfs_create(struct xfs_inode *dp, struct xfs_name *name, mode_t mode, xfs_dev_t rdev, struct xfs_inode **ipp, struct cred *credp); int xfs_remove(struct xfs_inode *dp, struct xfs_name *name, |