diff options
Diffstat (limited to 'fs')
113 files changed, 1573 insertions, 1417 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 429a0022850..781b47d2f9f 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -459,6 +459,15 @@ config OCFS2_DEBUG_MASKLOG This option will enlarge your kernel, but it allows debugging of ocfs2 filesystem issues. +config OCFS2_DEBUG_FS + bool "OCFS2 expensive checks" + depends on OCFS2_FS + default n + help + This option will enable expensive consistency checks. Enable + this option for debugging only as it is likely to decrease + performance of the filesystem. + config MINIX_FS tristate "Minix fs support" help @@ -1103,8 +1112,8 @@ config HFS_FS help If you say Y here, you will be able to mount Macintosh-formatted floppy disks and hard drive partitions with full read-write access. - Please read <file:fs/hfs/HFS.txt> to learn about the available mount - options. + Please read <file:Documentation/filesystems/hfs.txt> to learn about + the available mount options. To compile this file system support as a module, choose M here: the module will be called hfs. @@ -1296,7 +1305,7 @@ config JFFS2_COMPRESSION_OPTIONS help Enabling this option allows you to explicitly choose which compression modules, if any, are enabled in JFFS2. Removing - compressors and mean you cannot read existing file systems, + compressors can mean you cannot read existing file systems, and enabling experimental compressors can mean that you write a file system which cannot be read by a standard kernel. @@ -1161,7 +1161,12 @@ retry: ret = 0; if (to.timed_out) /* Only check after read evt */ break; - io_schedule(); + /* Try to only show up in io wait if there are ops + * in flight */ + if (ctx->reqs_active) + io_schedule(); + else + schedule(); if (signal_pending(tsk)) { ret = -EINTR; break; diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 294c41baef6..a64a71d444f 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -178,7 +178,8 @@ static void bfs_delete_inode(struct inode *inode) brelse(bh); if (bi->i_dsk_ino) { - info->si_freeb += BFS_FILEBLOCKS(bi); + if (bi->i_sblock) + info->si_freeb += bi->i_eblock + 1 - bi->i_sblock; info->si_freei++; clear_bit(ino, info->si_imap); dump_imap("delete_inode", s); diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index e176d195e7e..7596e1e94cd 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -319,7 +319,6 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs) current->mm->free_area_cache = current->mm->mmap_base; current->mm->cached_hole_size = 0; - current->mm->mmap = NULL; compute_creds(bprm); current->flags &= ~PF_FORKNOEXEC; #ifdef __sparc__ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index ba8de7ca260..f0b3171842f 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1384,7 +1384,7 @@ static void fill_prstatus(struct elf_prstatus *prstatus, prstatus->pr_sigpend = p->pending.signal.sig[0]; prstatus->pr_sighold = p->blocked.sig[0]; prstatus->pr_pid = task_pid_vnr(p); - prstatus->pr_ppid = task_pid_vnr(p->parent); + prstatus->pr_ppid = task_pid_vnr(p->real_parent); prstatus->pr_pgrp = task_pgrp_vnr(p); prstatus->pr_sid = task_session_vnr(p); if (thread_group_leader(p)) { @@ -1430,7 +1430,7 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, psinfo->pr_psargs[len] = 0; psinfo->pr_pid = task_pid_vnr(p); - psinfo->pr_ppid = task_pid_vnr(p->parent); + psinfo->pr_ppid = task_pid_vnr(p->real_parent); psinfo->pr_pgrp = task_pgrp_vnr(p); psinfo->pr_sid = task_session_vnr(p); diff --git a/fs/block_dev.c b/fs/block_dev.c index 993f78c5522..e48a630ae26 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -738,9 +738,9 @@ EXPORT_SYMBOL(bd_release); static struct kobject *bdev_get_kobj(struct block_device *bdev) { if (bdev->bd_contains != bdev) - return kobject_get(&bdev->bd_part->kobj); + return kobject_get(&bdev->bd_part->dev.kobj); else - return kobject_get(&bdev->bd_disk->kobj); + return kobject_get(&bdev->bd_disk->dev.kobj); } static struct kobject *bdev_get_holder(struct block_device *bdev) @@ -1176,7 +1176,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part) ret = -ENXIO; goto out_first; } - kobject_get(&p->kobj); + kobject_get(&p->dev.kobj); bdev->bd_part = p; bd_set_size(bdev, (loff_t) p->nr_sects << 9); } @@ -1299,7 +1299,7 @@ static int __blkdev_put(struct block_device *bdev, int for_part) module_put(owner); if (bdev->bd_contains != bdev) { - kobject_put(&bdev->bd_part->kobj); + kobject_put(&bdev->bd_part->dev.kobj); bdev->bd_part = NULL; } bdev->bd_disk = NULL; diff --git a/fs/char_dev.c b/fs/char_dev.c index c3bfa76765c..2c7a8b5b459 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -510,9 +510,8 @@ struct cdev *cdev_alloc(void) { struct cdev *p = kzalloc(sizeof(struct cdev), GFP_KERNEL); if (p) { - p->kobj.ktype = &ktype_cdev_dynamic; INIT_LIST_HEAD(&p->list); - kobject_init(&p->kobj); + kobject_init(&p->kobj, &ktype_cdev_dynamic); } return p; } @@ -529,8 +528,7 @@ void cdev_init(struct cdev *cdev, const struct file_operations *fops) { memset(cdev, 0, sizeof *cdev); INIT_LIST_HEAD(&cdev->list); - cdev->kobj.ktype = &ktype_cdev_default; - kobject_init(&cdev->kobj); + kobject_init(&cdev->kobj, &ktype_cdev_default); cdev->ops = fops; } diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index 64dd22239b2..a609599287a 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -1,6 +1,9 @@ Version 1.52 ------------ Fix oops on second mount to server when null auth is used. +Enable experimental Kerberos support. Return writebehind errors on flush +and sync so that events like out of disk space get reported properly on +cached files. Version 1.51 ------------ diff --git a/fs/cifs/README b/fs/cifs/README index b806b11b556..bf11329ac78 100644 --- a/fs/cifs/README +++ b/fs/cifs/README @@ -225,12 +225,9 @@ If no password is provided, mount.cifs will prompt for password entry Restrictions ============ -Servers must support the NTLM SMB dialect (which is the most recent, supported -by Samba and Windows NT version 4, 2000 and XP and many other SMB/CIFS servers) Servers must support either "pure-TCP" (port 445 TCP/IP CIFS connections) or RFC -1001/1002 support for "Netbios-Over-TCP/IP." Neither of these is likely to be a -problem as most servers support this. IPv6 support is planned for the future, -and is almost complete. +1001/1002 support for "Netbios-Over-TCP/IP." This is not likely to be a +problem as most servers support this. Valid filenames differ between Windows and Linux. Windows typically restricts filenames which contain certain reserved characters (e.g.the character : @@ -458,6 +455,8 @@ A partial list of the supported mount options follows: byte range locks). remount remount the share (often used to change from ro to rw mounts or vice versa) + cifsacl Report mode bits (e.g. on stat) based on the Windows ACL for + the file. (EXPERIMENTAL) servern Specify the server 's netbios name (RFC1001 name) to use when attempting to setup a session to the server. This is This is needed for mounting to some older servers (such @@ -584,8 +583,8 @@ Experimental When set to 1 used to enable certain experimental performance enhancement was disabled when signing turned on in case buffer was modified just before it was sent, also this flag will - be used to use the new experimental sessionsetup - code). + be used to use the new experimental directory change + notification code). These experimental features and tracing can be enabled by changing flags in /proc/fs/cifs (after the cifs module has been installed or built into the @@ -608,7 +607,8 @@ the start of smb requests and responses can be enabled via: Two other experimental features are under development. To test these requires enabling CONFIG_CIFS_EXPERIMENTAL - ipv6 enablement + cifsacl support needed to retrieve approximated mode bits based on + the contents on the CIFS ACL. DNOTIFY fcntl: needed for support of directory change notification and perhaps later for file leases) @@ -625,10 +625,7 @@ that they represent all for that share, not just those for which the server returned success. Also note that "cat /proc/fs/cifs/DebugData" will display information about -the active sessions and the shares that are mounted. Note: NTLMv2 enablement -will not work since its implementation is not quite complete yet. Do not alter -the ExtendedSecurity configuration value unless you are doing specific testing. -Enabling extended security works to Windows 2000 Workstations and XP but not to -Windows 2000 server or Samba since it does not usually send "raw NTLMSSP" -(instead it sends NTLMSSP encapsulated in SPNEGO/GSSAPI, which support is not -complete in the CIFS VFS yet). +the active sessions and the shares that are mounted. +Enabling Kerberos (extended security) works when CONFIG_CIFS_EXPERIMENTAL is enabled +but requires a user space helper (from the Samba project). NTLM and NTLMv2 and +LANMAN support do not require this helpr. diff --git a/fs/cifs/TODO b/fs/cifs/TODO index 29d4b271525..a8852c20072 100644 --- a/fs/cifs/TODO +++ b/fs/cifs/TODO @@ -16,7 +16,7 @@ SecurityDescriptors c) Better pam/winbind integration (e.g. to handle uid mapping better) -d) Kerberos/SPNEGO session setup support - (started) +d) Verify that Kerberos signing works e) Cleanup now unneeded SessSetup code in fs/cifs/connect.c and add back in NTLMSSP code if any servers diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index ad54a3a6e43..1529d2b12e9 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -66,20 +66,26 @@ struct key_type cifs_spnego_key_type = { .describe = user_describe, }; +#define MAX_VER_STR_LEN 9 /* length of longest version string e.g. + strlen(";ver=0xFF") */ +#define MAX_MECH_STR_LEN 13 /* length of longest security mechanism name, eg + in future could have strlen(";sec=ntlmsspi") */ +#define MAX_IPV6_ADDR_LEN 42 /* eg FEDC:BA98:7654:3210:FEDC:BA98:7654:3210/60 */ /* get a key struct with a SPNEGO security blob, suitable for session setup */ struct key * -cifs_get_spnego_key(struct cifsSesInfo *sesInfo, const char *hostname) +cifs_get_spnego_key(struct cifsSesInfo *sesInfo) { struct TCP_Server_Info *server = sesInfo->server; char *description, *dp; size_t desc_len; struct key *spnego_key; + const char *hostname = server->hostname; - - /* version + ;ip{4|6}= + address + ;host=hostname + - ;sec= + ;uid= + NULL */ - desc_len = 4 + 5 + 32 + 1 + 5 + strlen(hostname) + - strlen(";sec=krb5") + 7 + sizeof(uid_t)*2 + 1; + /* BB: come up with better scheme for determining length */ + /* length of fields (with semicolons): ver=0xyz ipv4= ipaddress host= + hostname sec=mechanism uid=0x uid */ + desc_len = MAX_VER_STR_LEN + 5 + MAX_IPV6_ADDR_LEN + 1 + 6 + + strlen(hostname) + MAX_MECH_STR_LEN + 8 + (sizeof(uid_t) * 2); spnego_key = ERR_PTR(-ENOMEM); description = kzalloc(desc_len, GFP_KERNEL); if (description == NULL) @@ -88,7 +94,7 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo, const char *hostname) dp = description; /* start with version and hostname portion of UNC string */ spnego_key = ERR_PTR(-EINVAL); - sprintf(dp, "0x%2.2x;host=%s;", CIFS_SPNEGO_UPCALL_VERSION, + sprintf(dp, "ver=0x%x;host=%s;", CIFS_SPNEGO_UPCALL_VERSION, hostname); dp = description + strlen(description); diff --git a/fs/cifs/cifs_spnego.h b/fs/cifs/cifs_spnego.h index f443f3b3513..05a34b17a1a 100644 --- a/fs/cifs/cifs_spnego.h +++ b/fs/cifs/cifs_spnego.h @@ -41,6 +41,7 @@ struct cifs_spnego_msg { #ifdef __KERNEL__ extern struct key_type cifs_spnego_key_type; +extern struct key *cifs_get_spnego_key(struct cifsSesInfo *sesInfo); #endif /* KERNEL */ #endif /* _CIFS_SPNEGO_H */ diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index dabbce00712..c312adcba4f 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -134,9 +134,10 @@ int compare_sids(const struct cifs_sid *ctsid, const struct cifs_sid *cwsid) pmode is the existing mode (we only want to overwrite part of this bits to set can be: S_IRWXU, S_IRWXG or S_IRWXO ie 00700 or 00070 or 00007 */ -static void access_flags_to_mode(__u32 ace_flags, int type, umode_t *pmode, +static void access_flags_to_mode(__le32 ace_flags, int type, umode_t *pmode, umode_t *pbits_to_set) { + __u32 flags = le32_to_cpu(ace_flags); /* the order of ACEs is important. The canonical order is to begin with DENY entries followed by ALLOW, otherwise an allow entry could be encountered first, making the subsequent deny entry like "dead code" @@ -146,17 +147,17 @@ static void access_flags_to_mode(__u32 ace_flags, int type, umode_t *pmode, /* For deny ACEs we change the mask so that subsequent allow access control entries do not turn on the bits we are denying */ if (type == ACCESS_DENIED) { - if (ace_flags & GENERIC_ALL) { + if (flags & GENERIC_ALL) { *pbits_to_set &= ~S_IRWXUGO; } - if ((ace_flags & GENERIC_WRITE) || - ((ace_flags & FILE_WRITE_RIGHTS) == FILE_WRITE_RIGHTS)) + if ((flags & GENERIC_WRITE) || + ((flags & FILE_WRITE_RIGHTS) == FILE_WRITE_RIGHTS)) *pbits_to_set &= ~S_IWUGO; - if ((ace_flags & GENERIC_READ) || - ((ace_flags & FILE_READ_RIGHTS) == FILE_READ_RIGHTS)) + if ((flags & GENERIC_READ) || + ((flags & FILE_READ_RIGHTS) == FILE_READ_RIGHTS)) *pbits_to_set &= ~S_IRUGO; - if ((ace_flags & GENERIC_EXECUTE) || - ((ace_flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS)) + if ((flags & GENERIC_EXECUTE) || + ((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS)) *pbits_to_set &= ~S_IXUGO; return; } else if (type != ACCESS_ALLOWED) { @@ -165,25 +166,25 @@ static void access_flags_to_mode(__u32 ace_flags, int type, umode_t *pmode, } /* else ACCESS_ALLOWED type */ - if (ace_flags & GENERIC_ALL) { + if (flags & GENERIC_ALL) { *pmode |= (S_IRWXUGO & (*pbits_to_set)); #ifdef CONFIG_CIFS_DEBUG2 cFYI(1, ("all perms")); #endif return; } - if ((ace_flags & GENERIC_WRITE) || - ((ace_flags & FILE_WRITE_RIGHTS) == FILE_WRITE_RIGHTS)) + if ((flags & GENERIC_WRITE) || + ((flags & FILE_WRITE_RIGHTS) == FILE_WRITE_RIGHTS)) *pmode |= (S_IWUGO & (*pbits_to_set)); - if ((ace_flags & GENERIC_READ) || - ((ace_flags & FILE_READ_RIGHTS) == FILE_READ_RIGHTS)) + if ((flags & GENERIC_READ) || + ((flags & FILE_READ_RIGHTS) == FILE_READ_RIGHTS)) *pmode |= (S_IRUGO & (*pbits_to_set)); - if ((ace_flags & GENERIC_EXECUTE) || - ((ace_flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS)) + if ((flags & GENERIC_EXECUTE) || + ((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS)) *pmode |= (S_IXUGO & (*pbits_to_set)); #ifdef CONFIG_CIFS_DEBUG2 - cFYI(1, ("access flags 0x%x mode now 0x%x", ace_flags, *pmode)); + cFYI(1, ("access flags 0x%x mode now 0x%x", flags, *pmode)); #endif return; } @@ -269,6 +270,13 @@ static void parse_dacl(struct cifs_acl *pdacl, char *end_of_acl, /* BB need to add parm so we can store the SID BB */ + if (!pdacl) { + /* no DACL in the security descriptor, set + all the permissions for user/group/other */ + inode->i_mode |= S_IRWXUGO; + return; + } + /* validate that we do not go past end of acl */ if (end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { cERROR(1, ("ACL too small to parse DACL")); @@ -286,12 +294,6 @@ static void parse_dacl(struct cifs_acl *pdacl, char *end_of_acl, user/group/other have no permissions */ inode->i_mode &= ~(S_IRWXUGO); - if (!pdacl) { - /* no DACL in the security descriptor, set - all the permissions for user/group/other */ - inode->i_mode |= S_IRWXUGO; - return; - } acl_base = (char *)pdacl; acl_size = sizeof(struct cifs_acl); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 416dc9fe896..093beaa3900 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -266,6 +266,7 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode->cifsAttrs = 0x20; /* default */ atomic_set(&cifs_inode->inUse, 0); cifs_inode->time = 0; + cifs_inode->write_behind_rc = 0; /* Until the file is open and we have gotten oplock info back from the server, can not assume caching of file data or metadata */ @@ -852,7 +853,7 @@ static int cifs_oplock_thread(void *dummyarg) struct cifsTconInfo *pTcon; struct inode *inode; __u16 netfid; - int rc; + int rc, waitrc = 0; set_freezable(); do { @@ -884,9 +885,11 @@ static int cifs_oplock_thread(void *dummyarg) filemap_fdatawrite(inode->i_mapping); if (CIFS_I(inode)->clientCanCacheRead == 0) { - filemap_fdatawait(inode->i_mapping); + waitrc = filemap_fdatawait(inode->i_mapping); invalidate_remote_inode(inode); } + if (rc == 0) + rc = waitrc; } else rc = 0; /* mutex_unlock(&inode->i_mutex);*/ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 87f51f23276..1fde2197ad7 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -110,6 +110,7 @@ struct mac_key { unsigned int len; union { char ntlm[CIFS_SESS_KEY_SIZE + 16]; + char krb5[CIFS_SESS_KEY_SIZE + 16]; /* BB: length correct? */ struct { char key[16]; struct ntlmv2_resp resp; @@ -139,6 +140,7 @@ struct TCP_Server_Info { /* 15 character server name + 0x20 16th byte indicating type = srv */ char server_RFC1001_name[SERVER_NAME_LEN_WITH_NULL]; char unicode_server_Name[SERVER_NAME_LEN_WITH_NULL * 2]; + char *hostname; /* hostname portion of UNC string */ struct socket *ssocket; union { struct sockaddr_in sockAddr; @@ -471,6 +473,17 @@ struct dir_notify_req { #define CIFS_LARGE_BUFFER 2 #define CIFS_IOVEC 4 /* array of response buffers */ +/* Type of Request to SendReceive2 */ +#define CIFS_STD_OP 0 /* normal request timeout */ +#define CIFS_LONG_OP 1 /* long op (up to 45 sec, oplock time) */ +#define CIFS_VLONG_OP 2 /* sloow op - can take up to 180 seconds */ +#define CIFS_BLOCKING_OP 4 /* operation can block */ +#define CIFS_ASYNC_OP 8 /* do not wait for response */ +#define CIFS_TIMEOUT_MASK 0x00F /* only one of 5 above set in req */ +#define CIFS_LOG_ERROR 0x010 /* log NT STATUS if non-zero */ +#define CIFS_LARGE_BUF_OP 0x020 /* large request buffer */ +#define CIFS_NO_RESP 0x040 /* no response buffer required */ + /* Security Flags: indicate type of session setup needed */ #define CIFSSEC_MAY_SIGN 0x00001 #define CIFSSEC_MAY_NTLM 0x00002 diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index dd1d7c200ee..8350eec4966 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -48,10 +48,11 @@ extern int SendReceive(const unsigned int /* xid */ , struct cifsSesInfo *, struct smb_hdr * /* input */ , struct smb_hdr * /* out */ , int * /* bytes returned */ , const int long_op); +extern int SendReceiveNoRsp(const unsigned int xid, struct cifsSesInfo *ses, + struct smb_hdr *in_buf, int flags); extern int SendReceive2(const unsigned int /* xid */ , struct cifsSesInfo *, struct kvec *, int /* nvec to send */, - int * /* type of buf returned */ , const int long_op, - const int logError /* whether to log status code*/ ); + int * /* type of buf returned */ , const int flags); extern int SendReceiveBlockingLock(const unsigned int /* xid */ , struct cifsTconInfo *, struct smb_hdr * /* input */ , @@ -76,8 +77,6 @@ extern void header_assemble(struct smb_hdr *, char /* command */ , extern int small_smb_init_no_tc(const int smb_cmd, const int wct, struct cifsSesInfo *ses, void **request_buf); -extern struct key *cifs_get_spnego_key(struct cifsSesInfo *sesInfo, - const char *hostname); extern int CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, const int stage, const struct nls_table *nls_cp); @@ -248,15 +247,15 @@ extern int CIFSSMBQueryReparseLinkInfo(const int xid, extern int CIFSSMBOpen(const int xid, struct cifsTconInfo *tcon, const char *fileName, const int disposition, const int access_flags, const int omode, - __u16 * netfid, int *pOplock, FILE_ALL_INFO *, + __u16 *netfid, int *pOplock, FILE_ALL_INFO *, const struct nls_table *nls_codepage, int remap); extern int SMBLegacyOpen(const int xid, struct cifsTconInfo *tcon, const char *fileName, const int disposition, const int access_flags, const int omode, - __u16 * netfid, int *pOplock, FILE_ALL_INFO *, + __u16 *netfid, int *pOplock, FILE_ALL_INFO *, const struct nls_table *nls_codepage, int remap); extern int CIFSPOSIXCreate(const int xid, struct cifsTconInfo *tcon, - u32 posix_flags, __u64 mode, __u16 * netfid, + u32 posix_flags, __u64 mode, __u16 *netfid, FILE_UNIX_BASIC_INFO *pRetData, __u32 *pOplock, const char *name, const struct nls_table *nls_codepage, int remap); @@ -277,7 +276,7 @@ extern int CIFSSMBWrite2(const int xid, struct cifsTconInfo *tcon, const __u64 offset, unsigned int *nbytes, struct kvec *iov, const int nvec, const int long_op); extern int CIFSGetSrvInodeNumber(const int xid, struct cifsTconInfo *tcon, - const unsigned char *searchName, __u64 * inode_number, + const unsigned char *searchName, __u64 *inode_number, const struct nls_table *nls_codepage, int remap_special_chars); extern int cifs_convertUCSpath(char *target, const __le16 *source, int maxlen, @@ -352,5 +351,5 @@ extern int CIFSSMBSetPosixACL(const int xid, struct cifsTconInfo *tcon, const char *local_acl, const int buflen, const int acl_type, const struct nls_table *nls_codepage, int remap_special_chars); extern int CIFSGetExtAttr(const int xid, struct cifsTconInfo *tcon, - const int netfid, __u64 * pExtAttrBits, __u64 *pMask); + const int netfid, __u64 *pExtAttrBits, __u64 *pMask); #endif /* _CIFSPROTO_H */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 59d7b7c037a..9e8a6bef029 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -698,9 +698,7 @@ int CIFSSMBTDis(const int xid, struct cifsTconInfo *tcon) { struct smb_hdr *smb_buffer; - struct smb_hdr *smb_buffer_response; /* BB removeme BB */ int rc = 0; - int length; cFYI(1, ("In tree disconnect")); /* @@ -737,16 +735,12 @@ CIFSSMBTDis(const int xid, struct cifsTconInfo *tcon) if (rc) { up(&tcon->tconSem); return rc; - } else { - smb_buffer_response = smb_buffer; /* BB removeme BB */ } - rc = SendReceive(xid, tcon->ses, smb_buffer, smb_buffer_response, - &length, 0); + + rc = SendReceiveNoRsp(xid, tcon->ses, smb_buffer, 0); if (rc) cFYI(1, ("Tree disconnect failed %d", rc)); - if (smb_buffer) - cifs_small_buf_release(smb_buffer); up(&tcon->tconSem); /* No need to return error on this operation if tid invalidated and @@ -760,10 +754,8 @@ CIFSSMBTDis(const int xid, struct cifsTconInfo *tcon) int CIFSSMBLogoff(const int xid, struct cifsSesInfo *ses) { - struct smb_hdr *smb_buffer_response; LOGOFF_ANDX_REQ *pSMB; int rc = 0; - int length; cFYI(1, ("In SMBLogoff for session disconnect")); if (ses) @@ -782,8 +774,6 @@ CIFSSMBLogoff(const int xid, struct cifsSesInfo *ses) return rc; } - smb_buffer_response = (struct smb_hdr *)pSMB; /* BB removeme BB */ - if (ses->server) { pSMB->hdr.Mid = GetNextMid(ses->server); @@ -795,8 +785,7 @@ CIFSSMBLogoff(const int xid, struct cifsSesInfo *ses) pSMB->hdr.Uid = ses->Suid; pSMB->AndXCommand = 0xFF; - rc = SendReceive(xid, ses, (struct smb_hdr *) pSMB, - smb_buffer_response, &length, 0); + rc = SendReceiveNoRsp(xid, ses, (struct smb_hdr *) pSMB, 0); if (ses->server) { atomic_dec(&ses->server->socketUseCount); if (atomic_read(&ses->server->socketUseCount) == 0) { @@ -807,7 +796,6 @@ CIFSSMBLogoff(const int xid, struct cifsSesInfo *ses) } } up(&ses->sesSem); - cifs_small_buf_release(pSMB); /* if session dead then we do not need to do ulogoff, since server closed smb session, no sense reporting @@ -1255,7 +1243,7 @@ OldOpenRetry: pSMB->ByteCount = cpu_to_le16(count); /* long_op set to 1 to allow for oplock break timeouts */ rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, - (struct smb_hdr *) pSMBr, &bytes_returned, 1); + (struct smb_hdr *)pSMBr, &bytes_returned, CIFS_LONG_OP); cifs_stats_inc(&tcon->num_opens); if (rc) { cFYI(1, ("Error in Open = %d", rc)); @@ -1368,7 +1356,7 @@ openRetry: pSMB->ByteCount = cpu_to_le16(count); /* long_op set to 1 to allow for oplock break timeouts */ rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, - (struct smb_hdr *) pSMBr, &bytes_returned, 1); + (struct smb_hdr *)pSMBr, &bytes_returned, CIFS_LONG_OP); cifs_stats_inc(&tcon->num_opens); if (rc) { cFYI(1, ("Error in Open = %d", rc)); @@ -1446,7 +1434,7 @@ CIFSSMBRead(const int xid, struct cifsTconInfo *tcon, const int netfid, iov[0].iov_base = (char *)pSMB; iov[0].iov_len = pSMB->hdr.smb_buf_length + 4; rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovecs */, - &resp_buf_type, 0 /* not long op */, 1 /* log err */ ); + &resp_buf_type, CIFS_STD_OP | CIFS_LOG_ERROR); cifs_stats_inc(&tcon->num_reads); pSMBr = (READ_RSP *)iov[0].iov_base; if (rc) { @@ -1665,7 +1653,7 @@ CIFSSMBWrite2(const int xid, struct cifsTconInfo *tcon, rc = SendReceive2(xid, tcon->ses, iov, n_vec + 1, &resp_buf_type, - long_op, 0 /* do not log STATUS code */ ); + long_op); cifs_stats_inc(&tcon->num_writes); if (rc) { cFYI(1, ("Send error Write2 = %d", rc)); @@ -1707,7 +1695,7 @@ CIFSSMBLock(const int xid, struct cifsTconInfo *tcon, int timeout = 0; __u16 count; - cFYI(1, ("In CIFSSMBLock - timeout %d numLock %d", waitFlag, numLock)); + cFYI(1, ("CIFSSMBLock timeout %d numLock %d", waitFlag, numLock)); rc = small_smb_init(SMB_COM_LOCKING_ANDX, 8, tcon, (void **) &pSMB); if (rc) @@ -1716,10 +1704,10 @@ CIFSSMBLock(const int xid, struct cifsTconInfo *tcon, pSMBr = (LOCK_RSP *)pSMB; /* BB removeme BB */ if (lockType == LOCKING_ANDX_OPLOCK_RELEASE) { - timeout = -1; /* no response expected */ + timeout = CIFS_ASYNC_OP; /* no response expected */ pSMB->Timeout = 0; } else if (waitFlag == TRUE) { - timeout = 3; /* blocking operation, no timeout */ + timeout = CIFS_BLOCKING_OP; /* blocking operation, no timeout */ pSMB->Timeout = cpu_to_le32(-1);/* blocking - do not time out */ } else { pSMB->Timeout = 0; @@ -1749,15 +1737,16 @@ CIFSSMBLock(const int xid, struct cifsTconInfo *tcon, if (waitFlag) { rc = SendReceiveBlockingLock(xid, tcon, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned); + cifs_small_buf_release(pSMB); } else { - rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, - (struct smb_hdr *) pSMBr, &bytes_returned, timeout); + rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *)pSMB, + timeout); + /* SMB buffer freed by function above */ } cifs_stats_inc(&tcon->num_locks); if (rc) { cFYI(1, ("Send error in Lock = %d", rc)); } - cifs_small_buf_release(pSMB); /* Note: On -EAGAIN error only caller can retry on handle based calls since file handle passed in no longer valid */ @@ -1776,7 +1765,9 @@ CIFSSMBPosixLock(const int xid, struct cifsTconInfo *tcon, int rc = 0; int timeout = 0; int bytes_returned = 0; + int resp_buf_type = 0; __u16 params, param_offset, offset, byte_count, count; + struct kvec iov[1]; cFYI(1, ("Posix Lock")); @@ -1818,7 +1809,7 @@ CIFSSMBPosixLock(const int xid, struct cifsTconInfo *tcon, parm_data->lock_type = cpu_to_le16(lock_type); if (waitFlag) { - timeout = 3; /* blocking operation, no timeout */ + timeout = CIFS_BLOCKING_OP; /* blocking operation, no timeout */ parm_data->lock_flags = cpu_to_le16(1); pSMB->Timeout = cpu_to_le32(-1); } else @@ -1838,8 +1829,13 @@ CIFSSMBPosixLock(const int xid, struct cifsTconInfo *tcon, rc = SendReceiveBlockingLock(xid, tcon, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned); } else { - rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, - (struct smb_hdr *) pSMBr, &bytes_returned, timeout); + iov[0].iov_base = (char *)pSMB; + iov[0].iov_len = pSMB->hdr.smb_buf_length + 4; + rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovecs */, + &resp_buf_type, timeout); + pSMB = NULL; /* request buf already freed by SendReceive2. Do + not try to free it twice below on exit */ + pSMBr = (struct smb_com_transaction2_sfi_rsp *)iov[0].iov_base; } if (rc) { @@ -1874,6 +1870,11 @@ plk_err_exit: if (pSMB) cifs_small_buf_release(pSMB); + if (resp_buf_type == CIFS_SMALL_BUFFER) + cifs_small_buf_release(iov[0].iov_base); + else if (resp_buf_type == CIFS_LARGE_BUFFER) + cifs_buf_release(iov[0].iov_base); + /* Note: On -EAGAIN error only caller can retry on handle based calls since file handle passed in no longer valid */ @@ -1886,8 +1887,6 @@ CIFSSMBClose(const int xid, struct cifsTconInfo *tcon, int smb_file_id) { int rc = 0; CLOSE_REQ *pSMB = NULL; - CLOSE_RSP *pSMBr = NULL; - int bytes_returned; cFYI(1, ("In CIFSSMBClose")); /* do not retry on dead session on close */ @@ -1897,13 +1896,10 @@ CIFSSMBClose(const int xid, struct cifsTconInfo *tcon, int smb_file_id) if (rc) return rc; - pSMBr = (CLOSE_RSP *)pSMB; /* BB removeme BB */ - pSMB->FileID = (__u16) smb_file_id; pSMB->LastWriteTime = 0xFFFFFFFF; pSMB->ByteCount = 0; - rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, - (struct smb_hdr *) pSMBr, &bytes_returned, 0); + rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0); cifs_stats_inc(&tcon->num_closes); if (rc) { if (rc != -EINTR) { @@ -1912,8 +1908,6 @@ CIFSSMBClose(const int xid, struct cifsTconInfo *tcon, int smb_file_id) } } - cifs_small_buf_release(pSMB); - /* Since session is dead, file will be closed on server already */ if (rc == -EAGAIN) rc = 0; @@ -3102,7 +3096,7 @@ CIFSSMBGetCIFSACL(const int xid, struct cifsTconInfo *tcon, __u16 fid, iov[0].iov_len = pSMB->hdr.smb_buf_length + 4; rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovec */, &buf_type, - 0 /* not long op */, 0 /* do not log STATUS codes */ ); + CIFS_STD_OP); cifs_stats_inc(&tcon->num_acl_get); if (rc) { cFYI(1, ("Send error in QuerySecDesc = %d", rc)); @@ -3763,8 +3757,6 @@ CIFSFindClose(const int xid, struct cifsTconInfo *tcon, { int rc = 0; FINDCLOSE_REQ *pSMB = NULL; - CLOSE_RSP *pSMBr = NULL; /* BB removeme BB */ - int bytes_returned; cFYI(1, ("In CIFSSMBFindClose")); rc = small_smb_init(SMB_COM_FIND_CLOSE2, 1, tcon, (void **)&pSMB); @@ -3776,16 +3768,13 @@ CIFSFindClose(const int xid, struct cifsTconInfo *tcon, if (rc) return rc; - pSMBr = (CLOSE_RSP *)pSMB; /* BB removeme BB */ pSMB->FileID = searchHandle; pSMB->ByteCount = 0; - rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, - (struct smb_hdr *) pSMBr, &bytes_returned, 0); + rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0); if (rc) { cERROR(1, ("Send error in FindClose = %d", rc)); } cifs_stats_inc(&tcon->num_fclose); - cifs_small_buf_release(pSMB); /* Since session is dead, search handle closed on server already */ if (rc == -EAGAIN) @@ -4707,11 +4696,9 @@ CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size, __u16 fid, __u32 pid_of_opener, int SetAllocation) { struct smb_com_transaction2_sfi_req *pSMB = NULL; - struct smb_com_transaction2_sfi_rsp *pSMBr = NULL; char *data_offset; struct file_end_of_file_info *parm_data; int rc = 0; - int bytes_returned = 0; __u16 params, param_offset, offset, byte_count, count; cFYI(1, ("SetFileSize (via SetFileInfo) %lld", @@ -4721,8 +4708,6 @@ CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size, if (rc) return rc; - pSMBr = (struct smb_com_transaction2_sfi_rsp *)pSMB; - pSMB->hdr.Pid = cpu_to_le16((__u16)pid_of_opener); pSMB->hdr.PidHigh = cpu_to_le16((__u16)(pid_of_opener >> 16)); @@ -4773,17 +4758,13 @@ CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size, pSMB->Reserved4 = 0; pSMB->hdr.smb_buf_length += byte_count; pSMB->ByteCount = cpu_to_le16(byte_count); - rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, - (struct smb_hdr *) pSMBr, &bytes_returned, 0); + rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0); if (rc) { cFYI(1, ("Send error in SetFileInfo (SetFileSize) = %d", rc)); } - if (pSMB) - cifs_small_buf_release(pSMB); - /* Note: On -EAGAIN error only caller can retry on handle based calls since file handle passed in no longer valid */ @@ -4801,10 +4782,8 @@ CIFSSMBSetFileTimes(const int xid, struct cifsTconInfo *tcon, const FILE_BASIC_INFO *data, __u16 fid) { struct smb_com_transaction2_sfi_req *pSMB = NULL; - struct smb_com_transaction2_sfi_rsp *pSMBr = NULL; char *data_offset; int rc = 0; - int bytes_returned = 0; __u16 params, param_offset, offset, byte_count, count; cFYI(1, ("Set Times (via SetFileInfo)")); @@ -4813,8 +4792,6 @@ CIFSSMBSetFileTimes(const int xid, struct cifsTconInfo *tcon, if (rc) return rc; - pSMBr = (struct smb_com_transaction2_sfi_rsp *)pSMB; - /* At this point there is no need to override the current pid with the pid of the opener, but that could change if we someday use an existing handle (rather than opening one on the fly) */ @@ -4854,14 +4831,11 @@ CIFSSMBSetFileTimes(const int xid, struct cifsTconInfo *tcon, pSMB->hdr.smb_buf_length += byte_count; pSMB->ByteCount = cpu_to_le16(byte_count); memcpy(data_offset, data, sizeof(FILE_BASIC_INFO)); - rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, - (struct smb_hdr *) pSMBr, &bytes_returned, 0); + rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0); if (rc) { cFYI(1, ("Send error in Set Time (SetFileInfo) = %d", rc)); } - cifs_small_buf_release(pSMB); - /* Note: On -EAGAIN error only caller can retry on handle based calls since file handle passed in no longer valid */ @@ -5152,7 +5126,8 @@ int CIFSSMBNotify(const int xid, struct cifsTconInfo *tcon, pSMB->ByteCount = 0; rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, - (struct smb_hdr *) pSMBr, &bytes_returned, -1); + (struct smb_hdr *)pSMBr, &bytes_returned, + CIFS_ASYNC_OP); if (rc) { cFYI(1, ("Error in Notify = %d", rc)); } else { diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index c52a76ff4bb..fd9147cdb5a 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -438,9 +438,9 @@ incomplete_rcv: csocket = server->ssocket; wake_up(&server->response_q); continue; - } else if (length < 4) { - cFYI(1, ("less than four bytes received (%d bytes)", - length)); + } else if (length < pdu_length) { + cFYI(1, ("requested %d bytes but only got %d bytes", + pdu_length, length)); pdu_length -= length; msleep(1); goto incomplete_rcv; @@ -752,6 +752,7 @@ multi_t2_fnd: } write_unlock(&GlobalSMBSeslock); + kfree(server->hostname); kfree(server); if (length > 0) mempool_resize(cifs_req_poolp, length + cifs_min_rcv, @@ -760,6 +761,34 @@ multi_t2_fnd: return 0; } +/* extract the host portion of the UNC string */ +static char * +extract_hostname(const char *unc) +{ + const char *src; + char *dst, *delim; + unsigned int len; + + /* skip double chars at beginning of string */ + /* BB: check validity of these bytes? */ + src = unc + 2; + + /* delimiter between hostname and sharename is always '\\' now */ + delim = strchr(src, '\\'); + if (!delim) + return ERR_PTR(-EINVAL); + + len = delim - src; + dst = kmalloc((len + 1), GFP_KERNEL); + if (dst == NULL) + return ERR_PTR(-ENOMEM); + + memcpy(dst, src, len); + dst[len] = '\0'; + + return dst; +} + static int cifs_parse_mount_options(char *options, const char *devname, struct smb_vol *vol) @@ -1781,11 +1810,8 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, memset(&volume_info, 0, sizeof(struct smb_vol)); if (cifs_parse_mount_options(mount_data, devname, &volume_info)) { - kfree(volume_info.UNC); - kfree(volume_info.password); - kfree(volume_info.prepath); - FreeXid(xid); - return -EINVAL; + rc = -EINVAL; + goto out; } if (volume_info.nullauth) { @@ -1798,11 +1824,8 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, cifserror("No username specified"); /* In userspace mount helper we can get user name from alternate locations such as env variables and files on disk */ - kfree(volume_info.UNC); - kfree(volume_info.password); - kfree(volume_info.prepath); - FreeXid(xid); - return -EINVAL; + rc = -EINVAL; + goto out; } if (volume_info.UNCip && volume_info.UNC) { @@ -1821,11 +1844,8 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, if (rc <= 0) { /* we failed translating address */ - kfree(volume_info.UNC); - kfree(volume_info.password); - kfree(volume_info.prepath); - FreeXid(xid); - return -EINVAL; + rc = -EINVAL; + goto out; } cFYI(1, ("UNC: %s ip: %s", volume_info.UNC, volume_info.UNCip)); @@ -1835,20 +1855,14 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, /* BB using ip addr as server name to connect to the DFS root below */ cERROR(1, ("Connecting to DFS root not implemented yet")); - kfree(volume_info.UNC); - kfree(volume_info.password); - kfree(volume_info.prepath); - FreeXid(xid); - return -EINVAL; + rc = -EINVAL; + goto out; } else /* which servers DFS root would we conect to */ { cERROR(1, ("CIFS mount error: No UNC path (e.g. -o " "unc=//192.168.1.100/public) specified")); - kfree(volume_info.UNC); - kfree(volume_info.password); - kfree(volume_info.prepath); - FreeXid(xid); - return -EINVAL; + rc = -EINVAL; + goto out; } /* this is needed for ASCII cp to Unicode converts */ @@ -1860,11 +1874,8 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, if (cifs_sb->local_nls == NULL) { cERROR(1, ("CIFS mount error: iocharset %s not found", volume_info.iocharset)); - kfree(volume_info.UNC); - kfree(volume_info.password); - kfree(volume_info.prepath); - FreeXid(xid); - return -ELIBACC; + rc = -ELIBACC; + goto out; } } @@ -1878,11 +1889,8 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, &sin_server6.sin6_addr, volume_info.username, &srvTcp); } else { - kfree(volume_info.UNC); - kfree(volume_info.password); - kfree(volume_info.prepath); - FreeXid(xid); - return -EINVAL; + rc = -EINVAL; + goto out; } if (srvTcp) { @@ -1906,22 +1914,14 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, "Aborting operation")); if (csocket != NULL) sock_release(csocket); - kfree(volume_info.UNC); - kfree(volume_info.password); - kfree(volume_info.prepath); - FreeXid(xid); - return rc; + goto out; } srvTcp = kzalloc(sizeof(struct TCP_Server_Info), GFP_KERNEL); if (!srvTcp) { rc = -ENOMEM; sock_release(csocket); - kfree(volume_info.UNC); - kfree(volume_info.password); - kfree(volume_info.prepath); - FreeXid(xid); - return rc; + goto out; } else { memcpy(&srvTcp->addr.sockAddr, &sin_server, sizeof(struct sockaddr_in)); @@ -1929,6 +1929,12 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, /* BB Add code for ipv6 case too */ srvTcp->ssocket = csocket; srvTcp->protocolType = IPV4; + srvTcp->hostname = extract_hostname(volume_info.UNC); + if (IS_ERR(srvTcp->hostname)) { + rc = PTR_ERR(srvTcp->hostname); + sock_release(csocket); + goto out; + } init_waitqueue_head(&srvTcp->response_q); init_waitqueue_head(&srvTcp->request_q); INIT_LIST_HEAD(&srvTcp->pending_mid_q); @@ -1938,16 +1944,13 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, srvTcp->tcpStatus = CifsNew; init_MUTEX(&srvTcp->tcpSem); srvTcp->tsk = kthread_run((void *)(void *)cifs_demultiplex_thread, srvTcp, "cifsd"); - if ( IS_ERR(srvTcp->tsk) ) { + if (IS_ERR(srvTcp->tsk)) { rc = PTR_ERR(srvTcp->tsk); cERROR(1, ("error %d create cifsd thread", rc)); srvTcp->tsk = NULL; sock_release(csocket); - kfree(volume_info.UNC); - kfree(volume_info.password); - kfree(volume_info.prepath); - FreeXid(xid); - return rc; + kfree(srvTcp->hostname); + goto out; } wait_for_completion(&cifsd_complete); rc = 0; @@ -1962,8 +1965,6 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, if (existingCifsSes) { pSesInfo = existingCifsSes; cFYI(1, ("Existing smb sess found")); - kfree(volume_info.password); - /* volume_info.UNC freed at end of function */ } else if (!rc) { cFYI(1, ("Existing smb sess not found")); pSesInfo = sesInfoAlloc(); @@ -1977,8 +1978,11 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, if (!rc) { /* volume_info.password freed at unmount */ - if (volume_info.password) + if (volume_info.password) { pSesInfo->password = volume_info.password; + /* set to NULL to prevent freeing on exit */ + volume_info.password = NULL; + } if (volume_info.username) strncpy(pSesInfo->userName, volume_info.username, @@ -2000,8 +2004,7 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, up(&pSesInfo->sesSem); if (!rc) atomic_inc(&srvTcp->socketUseCount); - } else - kfree(volume_info.password); + } } /* search for existing tcon to this server share */ @@ -2106,9 +2109,8 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, "", cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); - kfree(volume_info.UNC); - FreeXid(xid); - return -ENODEV; + rc = -ENODEV; + goto out; } else { /* BB Do we need to wrap sesSem around * this TCon call and Unix SetFS as @@ -2231,6 +2233,12 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, (in which case it is not needed anymore) but when new sesion is created the password ptr is put in the new session structure (in which case the password will be freed at unmount time) */ +out: + /* zero out password before freeing */ + if (volume_info.password != NULL) { + memset(volume_info.password, 0, strlen(volume_info.password)); + kfree(volume_info.password); + } kfree(volume_info.UNC); kfree(volume_info.prepath); FreeXid(xid); @@ -2374,7 +2382,7 @@ CIFSSessSetup(unsigned int xid, struct cifsSesInfo *ses, pSMB->req_no_secext.ByteCount = cpu_to_le16(count); rc = SendReceive(xid, ses, smb_buffer, smb_buffer_response, - &bytes_returned, 1); + &bytes_returned, CIFS_LONG_OP); if (rc) { /* rc = map_smb_to_linux_error(smb_buffer_response); now done in SendReceive */ } else if ((smb_buffer_response->WordCount == 3) @@ -2678,7 +2686,7 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, pSMB->req.ByteCount = cpu_to_le16(count); rc = SendReceive(xid, ses, smb_buffer, smb_buffer_response, - &bytes_returned, 1); + &bytes_returned, CIFS_LONG_OP); if (smb_buffer_response->Status.CifsError == cpu_to_le32(NT_STATUS_MORE_PROCESSING_REQUIRED)) @@ -3105,7 +3113,7 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, pSMB->req.ByteCount = cpu_to_le16(count); rc = SendReceive(xid, ses, smb_buffer, smb_buffer_response, - &bytes_returned, 1); + &bytes_returned, CIFS_LONG_OP); if (rc) { /* rc = map_smb_to_linux_error(smb_buffer_response) done in SendReceive now */ } else if ((smb_buffer_response->WordCount == 3) || @@ -3381,7 +3389,8 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses, pSMB->hdr.smb_buf_length += count; pSMB->ByteCount = cpu_to_le16(count); - rc = SendReceive(xid, ses, smb_buffer, smb_buffer_response, &length, 0); + rc = SendReceive(xid, ses, smb_buffer, smb_buffer_response, &length, + CIFS_STD_OP); /* if (rc) rc = map_smb_to_linux_error(smb_buffer_response); */ /* above now done in SendReceive */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 68ad4ca0cfa..dd26e2759b1 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -130,7 +130,9 @@ static inline int cifs_open_inode_helper(struct inode *inode, struct file *file, if (file->f_path.dentry->d_inode->i_mapping) { /* BB no need to lock inode until after invalidate since namei code should already have it locked? */ - filemap_write_and_wait(file->f_path.dentry->d_inode->i_mapping); + rc = filemap_write_and_wait(file->f_path.dentry->d_inode->i_mapping); + if (rc != 0) + CIFS_I(file->f_path.dentry->d_inode)->write_behind_rc = rc; } cFYI(1, ("invalidating remote inode since open detected it " "changed")); @@ -425,7 +427,9 @@ reopen_error_exit: pCifsInode = CIFS_I(inode); if (pCifsInode) { if (can_flush) { - filemap_write_and_wait(inode->i_mapping); + rc = filemap_write_and_wait(inode->i_mapping); + if (rc != 0) + CIFS_I(inode)->write_behind_rc = rc; /* temporarily disable caching while we go to server to get inode info */ pCifsInode->clientCanCacheAll = FALSE; @@ -835,9 +839,9 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data, xid = GetXid(); if (*poffset > file->f_path.dentry->d_inode->i_size) - long_op = 2; /* writes past end of file can take a long time */ + long_op = CIFS_VLONG_OP; /* writes past EOF take long time */ else - long_op = 1; + long_op = CIFS_LONG_OP; for (total_written = 0; write_size > total_written; total_written += bytes_written) { @@ -884,7 +888,7 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data, } } else *poffset += bytes_written; - long_op = FALSE; /* subsequent writes fast - + long_op = CIFS_STD_OP; /* subsequent writes fast - 15 seconds is plenty */ } @@ -934,9 +938,9 @@ static ssize_t cifs_write(struct file *file, const char *write_data, xid = GetXid(); if (*poffset > file->f_path.dentry->d_inode->i_size) - long_op = 2; /* writes past end of file can take a long time */ + long_op = CIFS_VLONG_OP; /* writes past EOF can be slow */ else - long_op = 1; + long_op = CIFS_LONG_OP; for (total_written = 0; write_size > total_written; total_written += bytes_written) { @@ -1002,7 +1006,7 @@ static ssize_t cifs_write(struct file *file, const char *write_data, } } else *poffset += bytes_written; - long_op = FALSE; /* subsequent writes fast - + long_op = CIFS_STD_OP; /* subsequent writes fast - 15 seconds is plenty */ } @@ -1087,11 +1091,11 @@ refind_writable: read_unlock(&GlobalSMBSeslock); return open_file; } - + read_unlock(&GlobalSMBSeslock); /* Had to unlock since following call can block */ rc = cifs_reopen_file(open_file->pfile, FALSE); - if (!rc) { + if (!rc) { if (!open_file->closePend) return open_file; else { /* start over in case this was deleted */ @@ -1114,7 +1118,7 @@ refind_writable: /* can not use this handle, no write pending on this one after all */ atomic_dec(&open_file->wrtPending); - + if (open_file->closePend) /* list could have changed */ goto refind_writable; /* else we simply continue to the next entry. Thus @@ -1360,14 +1364,17 @@ retry: open_file->netfid, bytes_to_write, offset, &bytes_written, iov, n_iov, - 1); + CIFS_LONG_OP); atomic_dec(&open_file->wrtPending); if (rc || bytes_written < bytes_to_write) { cERROR(1, ("Write2 ret %d, wrote %d", rc, bytes_written)); /* BB what if continued retry is requested via mount flags? */ - set_bit(AS_EIO, &mapping->flags); + if (rc == -ENOSPC) + set_bit(AS_ENOSPC, &mapping->flags); + else + set_bit(AS_EIO, &mapping->flags); } else { cifs_stats_bytes_written(cifs_sb->tcon, bytes_written); @@ -1499,9 +1506,11 @@ int cifs_fsync(struct file *file, struct dentry *dentry, int datasync) cFYI(1, ("Sync file - name: %s datasync: 0x%x", dentry->d_name.name, datasync)); - rc = filemap_fdatawrite(inode->i_mapping); - if (rc == 0) + rc = filemap_write_and_wait(inode->i_mapping); + if (rc == 0) { + rc = CIFS_I(inode)->write_behind_rc; CIFS_I(inode)->write_behind_rc = 0; + } FreeXid(xid); return rc; } @@ -1553,8 +1562,11 @@ int cifs_flush(struct file *file, fl_owner_t id) filemapfdatawrite appears easier for the time being */ rc = filemap_fdatawrite(inode->i_mapping); - if (!rc) /* reset wb rc if we were able to write out dirty pages */ + /* reset wb rc if we were able to write out dirty pages */ + if (!rc) { + rc = CIFS_I(inode)->write_behind_rc; CIFS_I(inode)->write_behind_rc = 0; + } cFYI(1, ("Flush inode %p file %p rc %d", inode, file, rc)); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 7d907e84e03..e915eb1d2e6 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1233,7 +1233,7 @@ cifs_rename_exit: int cifs_revalidate(struct dentry *direntry) { int xid; - int rc = 0; + int rc = 0, wbrc = 0; char *full_path; struct cifs_sb_info *cifs_sb; struct cifsInodeInfo *cifsInode; @@ -1333,7 +1333,9 @@ int cifs_revalidate(struct dentry *direntry) if (direntry->d_inode->i_mapping) { /* do we need to lock inode until after invalidate completes below? */ - filemap_fdatawrite(direntry->d_inode->i_mapping); + wbrc = filemap_fdatawrite(direntry->d_inode->i_mapping); + if (wbrc) + CIFS_I(direntry->d_inode)->write_behind_rc = wbrc; } if (invalidate_inode) { /* shrink_dcache not necessary now that cifs dentry ops @@ -1342,7 +1344,9 @@ int cifs_revalidate(struct dentry *direntry) shrink_dcache_parent(direntry); */ if (S_ISREG(direntry->d_inode->i_mode)) { if (direntry->d_inode->i_mapping) - filemap_fdatawait(direntry->d_inode->i_mapping); + wbrc = filemap_fdatawait(direntry->d_inode->i_mapping); + if (wbrc) + CIFS_I(direntry->d_inode)->write_behind_rc = wbrc; /* may eventually have to do this for open files too */ if (list_empty(&(cifsInode->openFileList))) { /* changed on server - flush read ahead pages */ @@ -1485,10 +1489,20 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) /* BB check if we need to refresh inode from server now ? BB */ - /* need to flush data before changing file size on server */ - filemap_write_and_wait(direntry->d_inode->i_mapping); - if (attrs->ia_valid & ATTR_SIZE) { + /* + Flush data before changing file size on server. If the + flush returns error, store it to report later and continue. + BB: This should be smarter. Why bother flushing pages that + will be truncated anyway? Also, should we error out here if + the flush returns error? + */ + rc = filemap_write_and_wait(direntry->d_inode->i_mapping); + if (rc != 0) { + CIFS_I(direntry->d_inode)->write_behind_rc = rc; + rc = 0; + } + /* To avoid spurious oplock breaks from server, in the case of inodes that we already have open, avoid doing path based setting of file size if we can do it by handle. diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 899dc6078d9..d0cb469daab 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -29,6 +29,7 @@ #include "ntlmssp.h" #include "nterr.h" #include <linux/utsname.h> +#include "cifs_spnego.h" extern void SMBNTencrypt(unsigned char *passwd, unsigned char *c8, unsigned char *p24); @@ -340,11 +341,12 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, int first_time, SESSION_SETUP_ANDX *pSMB; __u32 capabilities; int count; - int resp_buf_type = 0; - struct kvec iov[2]; + int resp_buf_type; + struct kvec iov[3]; enum securityEnum type; __u16 action; int bytes_remaining; + struct key *spnego_key = NULL; if (ses == NULL) return -EINVAL; @@ -377,24 +379,32 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, int first_time, capabilities = cifs_ssetup_hdr(ses, pSMB); - /* we will send the SMB in two pieces, - a fixed length beginning part, and a - second part which will include the strings - and rest of bcc area, in order to avoid having - to do a large buffer 17K allocation */ + /* we will send the SMB in three pieces: + a fixed length beginning part, an optional + SPNEGO blob (which can be zero length), and a + last part which will include the strings + and rest of bcc area. This allows us to avoid + a large buffer 17K allocation */ iov[0].iov_base = (char *)pSMB; iov[0].iov_len = smb_buf->smb_buf_length + 4; + /* setting this here allows the code at the end of the function + to free the request buffer if there's an error */ + resp_buf_type = CIFS_SMALL_BUFFER; + /* 2000 big enough to fit max user, domain, NOS name etc. */ str_area = kmalloc(2000, GFP_KERNEL); if (str_area == NULL) { - cifs_small_buf_release(smb_buf); - return -ENOMEM; + rc = -ENOMEM; + goto ssetup_exit; } bcc_ptr = str_area; ses->flags &= ~CIFS_SES_LANMAN; + iov[1].iov_base = NULL; + iov[1].iov_len = 0; + if (type == LANMAN) { #ifdef CONFIG_CIFS_WEAK_PW_HASH char lnm_session_key[CIFS_SESS_KEY_SIZE]; @@ -463,8 +473,8 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, int first_time, struct ntlmv2_resp */ if (v2_sess_key == NULL) { - cifs_small_buf_release(smb_buf); - return -ENOMEM; + rc = -ENOMEM; + goto ssetup_exit; } pSMB->req_no_secext.Capabilities = cpu_to_le32(capabilities); @@ -499,22 +509,67 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, int first_time, unicode_ssetup_strings(&bcc_ptr, ses, nls_cp); } else ascii_ssetup_strings(&bcc_ptr, ses, nls_cp); - } else /* NTLMSSP or SPNEGO */ { + } else if (type == Kerberos) { +#ifdef CONFIG_CIFS_UPCALL + struct cifs_spnego_msg *msg; + spnego_key = cifs_get_spnego_key(ses); + if (IS_ERR(spnego_key)) { + rc = PTR_ERR(spnego_key); + spnego_key = NULL; + goto ssetup_exit; + } + + msg = spnego_key->payload.data; + /* bail out if key is too long */ + if (msg->sesskey_len > + sizeof(ses->server->mac_signing_key.data.krb5)) { + cERROR(1, ("Kerberos signing key too long (%u bytes)", + msg->sesskey_len)); + rc = -EOVERFLOW; + goto ssetup_exit; + } + ses->server->mac_signing_key.len = msg->sesskey_len; + memcpy(ses->server->mac_signing_key.data.krb5, msg->data, + msg->sesskey_len); pSMB->req.hdr.Flags2 |= SMBFLG2_EXT_SEC; capabilities |= CAP_EXTENDED_SECURITY; pSMB->req.Capabilities = cpu_to_le32(capabilities); - /* BB set password lengths */ + iov[1].iov_base = msg->data + msg->sesskey_len; + iov[1].iov_len = msg->secblob_len; + pSMB->req.SecurityBlobLength = cpu_to_le16(iov[1].iov_len); + + if (ses->capabilities & CAP_UNICODE) { + /* unicode strings must be word aligned */ + if (iov[0].iov_len % 2) { + *bcc_ptr = 0; + bcc_ptr++; + } + unicode_oslm_strings(&bcc_ptr, nls_cp); + unicode_domain_string(&bcc_ptr, ses, nls_cp); + } else + /* BB: is this right? */ + ascii_ssetup_strings(&bcc_ptr, ses, nls_cp); +#else /* ! CONFIG_CIFS_UPCALL */ + cERROR(1, ("Kerberos negotiated but upcall support disabled!")); + rc = -ENOSYS; + goto ssetup_exit; +#endif /* CONFIG_CIFS_UPCALL */ + } else { + cERROR(1, ("secType %d not supported!", type)); + rc = -ENOSYS; + goto ssetup_exit; } - count = (long) bcc_ptr - (long) str_area; + iov[2].iov_base = str_area; + iov[2].iov_len = (long) bcc_ptr - (long) str_area; + + count = iov[1].iov_len + iov[2].iov_len; smb_buf->smb_buf_length += count; BCC_LE(smb_buf) = cpu_to_le16(count); - iov[1].iov_base = str_area; - iov[1].iov_len = count; - rc = SendReceive2(xid, ses, iov, 2 /* num_iovecs */, &resp_buf_type, - 0 /* not long op */, 1 /* log NT STATUS if any */ ); + rc = SendReceive2(xid, ses, iov, 3 /* num_iovecs */, &resp_buf_type, + CIFS_STD_OP /* not long */ | CIFS_LOG_ERROR); /* SMB request buf freed in SendReceive2 */ cFYI(1, ("ssetup rc from sendrecv2 is %d", rc)); @@ -560,6 +615,8 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, int first_time, ses, nls_cp); ssetup_exit: + if (spnego_key) + key_put(spnego_key); kfree(str_area); if (resp_buf_type == CIFS_SMALL_BUFFER) { cFYI(1, ("ssetup freeing small buf %p", iov[0].iov_base)); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 7ed32b3cb78..50b623ad932 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -308,7 +308,7 @@ smb_send2(struct socket *ssocket, struct kvec *iov, int n_vec, static int wait_for_free_request(struct cifsSesInfo *ses, const int long_op) { - if (long_op == -1) { + if (long_op == CIFS_ASYNC_OP) { /* oplock breaks must not be held up */ atomic_inc(&ses->server->inFlight); } else { @@ -337,7 +337,7 @@ static int wait_for_free_request(struct cifsSesInfo *ses, const int long_op) as they are allowed to block on server */ /* update # of requests on the wire to server */ - if (long_op < 3) + if (long_op != CIFS_BLOCKING_OP) atomic_inc(&ses->server->inFlight); spin_unlock(&GlobalMid_Lock); break; @@ -415,17 +415,48 @@ static int wait_for_response(struct cifsSesInfo *ses, } } + +/* + * + * Send an SMB Request. No response info (other than return code) + * needs to be parsed. + * + * flags indicate the type of request buffer and how long to wait + * and whether to log NT STATUS code (error) before mapping it to POSIX error + * + */ +int +SendReceiveNoRsp(const unsigned int xid, struct cifsSesInfo *ses, + struct smb_hdr *in_buf, int flags) +{ + int rc; + struct kvec iov[1]; + int resp_buf_type; + + iov[0].iov_base = (char *)in_buf; + iov[0].iov_len = in_buf->smb_buf_length + 4; + flags |= CIFS_NO_RESP; + rc = SendReceive2(xid, ses, iov, 1, &resp_buf_type, flags); +#ifdef CONFIG_CIFS_DEBUG2 + cFYI(1, ("SendRcvNoR flags %d rc %d", flags, rc)); +#endif + return rc; +} + int SendReceive2(const unsigned int xid, struct cifsSesInfo *ses, struct kvec *iov, int n_vec, int *pRespBufType /* ret */, - const int long_op, const int logError) + const int flags) { int rc = 0; + int long_op; unsigned int receive_len; unsigned long timeout; struct mid_q_entry *midQ; struct smb_hdr *in_buf = iov[0].iov_base; + long_op = flags & CIFS_TIMEOUT_MASK; + *pRespBufType = CIFS_NO_BUFFER; /* no response buf yet */ if ((ses == NULL) || (ses->server == NULL)) { @@ -483,15 +514,22 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses, if (rc < 0) goto out; - if (long_op == -1) - goto out; - else if (long_op == 2) /* writes past end of file can take loong time */ + if (long_op == CIFS_STD_OP) + timeout = 15 * HZ; + else if (long_op == CIFS_VLONG_OP) /* e.g. slow writes past EOF */ timeout = 180 * HZ; - else if (long_op == 1) + else if (long_op == CIFS_LONG_OP) timeout = 45 * HZ; /* should be greater than servers oplock break timeout (about 43 seconds) */ - else - timeout = 15 * HZ; + else if (long_op == CIFS_ASYNC_OP) + goto out; + else if (long_op == CIFS_BLOCKING_OP) + timeout = 0x7FFFFFFF; /* large, but not so large as to wrap */ + else { + cERROR(1, ("unknown timeout flag %d", long_op)); + rc = -EIO; + goto out; + } /* wait for 15 seconds or until woken up due to response arriving or due to last connection to this server being unmounted */ @@ -566,7 +604,8 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses, } /* BB special case reconnect tid and uid here? */ - rc = map_smb_to_linux_error(midQ->resp_buf, logError); + rc = map_smb_to_linux_error(midQ->resp_buf, + flags & CIFS_LOG_ERROR); /* convert ByteCount if necessary */ if (receive_len >= sizeof(struct smb_hdr) - 4 @@ -574,8 +613,10 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses, (2 * midQ->resp_buf->WordCount) + 2 /* bcc */ ) BCC(midQ->resp_buf) = le16_to_cpu(BCC_LE(midQ->resp_buf)); - midQ->resp_buf = NULL; /* mark it so will not be freed - by DeleteMidQEntry */ + if ((flags & CIFS_NO_RESP) == 0) + midQ->resp_buf = NULL; /* mark it so buf will + not be freed by + DeleteMidQEntry */ } else { rc = -EIO; cFYI(1, ("Bad MID state?")); @@ -663,17 +704,25 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses, if (rc < 0) goto out; - if (long_op == -1) + if (long_op == CIFS_STD_OP) + timeout = 15 * HZ; + /* wait for 15 seconds or until woken up due to response arriving or + due to last connection to this server being unmounted */ + else if (long_op == CIFS_ASYNC_OP) goto out; - else if (long_op == 2) /* writes past end of file can take loong time */ + else if (long_op == CIFS_VLONG_OP) /* writes past EOF can be slow */ timeout = 180 * HZ; - else if (long_op == 1) + else if (long_op == CIFS_LONG_OP) timeout = 45 * HZ; /* should be greater than servers oplock break timeout (about 43 seconds) */ - else - timeout = 15 * HZ; - /* wait for 15 seconds or until woken up due to response arriving or - due to last connection to this server being unmounted */ + else if (long_op == CIFS_BLOCKING_OP) + timeout = 0x7FFFFFFF; /* large but no so large as to wrap */ + else { + cERROR(1, ("unknown timeout flag %d", long_op)); + rc = -EIO; + goto out; + } + if (signal_pending(current)) { /* if signal pending do not hold up user for full smb timeout but we still give response a chance to complete */ @@ -812,7 +861,7 @@ send_lock_cancel(const unsigned int xid, struct cifsTconInfo *tcon, pSMB->hdr.Mid = GetNextMid(ses->server); return SendReceive(xid, ses, in_buf, out_buf, - &bytes_returned, 0); + &bytes_returned, CIFS_STD_OP); } int @@ -844,7 +893,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon, to the same server. We may make this configurable later or use ses->maxReq */ - rc = wait_for_free_request(ses, 3); + rc = wait_for_free_request(ses, CIFS_BLOCKING_OP); if (rc) return rc; diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index dcc6aead70f..e3eb3556622 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -362,8 +362,8 @@ static int init_coda_psdev(void) goto out_chrdev; } for (i = 0; i < MAX_CODADEVS; i++) - class_device_create(coda_psdev_class, NULL, - MKDEV(CODA_PSDEV_MAJOR,i), NULL, "cfs%d", i); + device_create(coda_psdev_class, NULL, + MKDEV(CODA_PSDEV_MAJOR,i), "cfs%d", i); coda_sysctl_init(); goto out; @@ -405,7 +405,7 @@ static int __init init_coda(void) return 0; out: for (i = 0; i < MAX_CODADEVS; i++) - class_device_destroy(coda_psdev_class, MKDEV(CODA_PSDEV_MAJOR, i)); + device_destroy(coda_psdev_class, MKDEV(CODA_PSDEV_MAJOR, i)); class_destroy(coda_psdev_class); unregister_chrdev(CODA_PSDEV_MAJOR, "coda"); coda_sysctl_clean(); @@ -424,7 +424,7 @@ static void __exit exit_coda(void) printk("coda: failed to unregister filesystem\n"); } for (i = 0; i < MAX_CODADEVS; i++) - class_device_destroy(coda_psdev_class, MKDEV(CODA_PSDEV_MAJOR, i)); + device_destroy(coda_psdev_class, MKDEV(CODA_PSDEV_MAJOR, i)); class_destroy(coda_psdev_class); unregister_chrdev(CODA_PSDEV_MAJOR, "coda"); coda_sysctl_clean(); diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index bd26e4cbb99..da8cb3b3592 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -10,6 +10,8 @@ * ioctls. */ +#include <linux/joystick.h> + #include <linux/types.h> #include <linux/compat.h> #include <linux/kernel.h> @@ -1954,6 +1956,12 @@ ULONG_IOCTL(TIOCSCTTY) COMPATIBLE_IOCTL(TIOCGPTN) COMPATIBLE_IOCTL(TIOCSPTLCK) COMPATIBLE_IOCTL(TIOCSERGETLSR) +#ifdef TCGETS2 +COMPATIBLE_IOCTL(TCGETS2) +COMPATIBLE_IOCTL(TCSETS2) +COMPATIBLE_IOCTL(TCSETSW2) +COMPATIBLE_IOCTL(TCSETSF2) +#endif /* Little f */ COMPATIBLE_IOCTL(FIOCLEX) COMPATIBLE_IOCTL(FIONCLEX) @@ -2636,6 +2644,12 @@ COMPATIBLE_IOCTL(VIDEO_SET_ATTRIBUTES) COMPATIBLE_IOCTL(VIDEO_GET_SIZE) COMPATIBLE_IOCTL(VIDEO_GET_FRAME_RATE) +/* joystick */ +COMPATIBLE_IOCTL(JSIOCGVERSION) +COMPATIBLE_IOCTL(JSIOCGAXES) +COMPATIBLE_IOCTL(JSIOCGBUTTONS) +COMPATIBLE_IOCTL(JSIOCGNAME(0)) + /* now things that need handlers */ HANDLE_IOCTL(MEMREADOOB32, mtd_rw_oob) HANDLE_IOCTL(MEMWRITEOOB32, mtd_rw_oob) diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 3bf0278ea84..de3b31d0a37 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -128,7 +128,7 @@ void configfs_release_fs(void) } -static decl_subsys(config, NULL, NULL); +static struct kobject *config_kobj; static int __init configfs_init(void) { @@ -140,9 +140,8 @@ static int __init configfs_init(void) if (!configfs_dir_cachep) goto out; - kobj_set_kset_s(&config_subsys, kernel_subsys); - err = subsystem_register(&config_subsys); - if (err) { + config_kobj = kobject_create_and_add("config", kernel_kobj); + if (!config_kobj) { kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; goto out; @@ -151,7 +150,7 @@ static int __init configfs_init(void) err = register_filesystem(&configfs_fs_type); if (err) { printk(KERN_ERR "configfs: Unable to register filesystem!\n"); - subsystem_unregister(&config_subsys); + kobject_put(config_kobj); kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; goto out; @@ -160,7 +159,7 @@ static int __init configfs_init(void) err = configfs_inode_init(); if (err) { unregister_filesystem(&configfs_fs_type); - subsystem_unregister(&config_subsys); + kobject_put(config_kobj); kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; } @@ -171,7 +170,7 @@ out: static void __exit configfs_exit(void) { unregister_filesystem(&configfs_fs_type); - subsystem_unregister(&config_subsys); + kobject_put(config_kobj); kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; configfs_inode_exit(); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 6a713b33992..d26e2826ba5 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -426,20 +426,19 @@ exit: } EXPORT_SYMBOL_GPL(debugfs_rename); -static decl_subsys(debug, NULL, NULL); +static struct kobject *debug_kobj; static int __init debugfs_init(void) { int retval; - kobj_set_kset_s(&debug_subsys, kernel_subsys); - retval = subsystem_register(&debug_subsys); - if (retval) - return retval; + debug_kobj = kobject_create_and_add("debug", kernel_kobj); + if (!debug_kobj) + return -EINVAL; retval = register_filesystem(&debug_fs_type); if (retval) - subsystem_unregister(&debug_subsys); + kobject_put(debug_kobj); return retval; } @@ -447,7 +446,7 @@ static void __exit debugfs_exit(void) { simple_release_fs(&debugfs_mount, &debugfs_mount_count); unregister_filesystem(&debug_fs_type); - subsystem_unregister(&debug_subsys); + kobject_put(debug_kobj); } core_initcall(debugfs_init); diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 6353a838452..5c108c49cb8 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -166,26 +166,7 @@ static struct kobj_type dlm_ktype = { .release = lockspace_kobj_release, }; -static struct kset dlm_kset = { - .ktype = &dlm_ktype, -}; - -static int kobject_setup(struct dlm_ls *ls) -{ - char lsname[DLM_LOCKSPACE_LEN]; - int error; - - memset(lsname, 0, DLM_LOCKSPACE_LEN); - snprintf(lsname, DLM_LOCKSPACE_LEN, "%s", ls->ls_name); - - error = kobject_set_name(&ls->ls_kobj, "%s", lsname); - if (error) - return error; - - ls->ls_kobj.kset = &dlm_kset; - ls->ls_kobj.ktype = &dlm_ktype; - return 0; -} +static struct kset *dlm_kset; static int do_uevent(struct dlm_ls *ls, int in) { @@ -220,24 +201,22 @@ static int do_uevent(struct dlm_ls *ls, int in) int dlm_lockspace_init(void) { - int error; - ls_count = 0; mutex_init(&ls_lock); INIT_LIST_HEAD(&lslist); spin_lock_init(&lslist_lock); - kobject_set_name(&dlm_kset.kobj, "dlm"); - kobj_set_kset_s(&dlm_kset, kernel_subsys); - error = kset_register(&dlm_kset); - if (error) - printk("dlm_lockspace_init: cannot register kset %d\n", error); - return error; + dlm_kset = kset_create_and_add("dlm", NULL, kernel_kobj); + if (!dlm_kset) { + printk(KERN_WARNING "%s: can not create kset\n", __FUNCTION__); + return -ENOMEM; + } + return 0; } void dlm_lockspace_exit(void) { - kset_unregister(&dlm_kset); + kset_unregister(dlm_kset); } static int dlm_scand(void *data) @@ -549,13 +528,12 @@ static int new_lockspace(char *name, int namelen, void **lockspace, goto out_delist; } - error = kobject_setup(ls); - if (error) - goto out_stop; - - error = kobject_register(&ls->ls_kobj); + ls->ls_kobj.kset = dlm_kset; + error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL, + "%s", ls->ls_name); if (error) goto out_stop; + kobject_uevent(&ls->ls_kobj, KOBJ_ADD); /* let kobject handle freeing of ls if there's an error */ do_unreg = 1; @@ -601,7 +579,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace, kfree(ls->ls_rsbtbl); out_lsfree: if (do_unreg) - kobject_unregister(&ls->ls_kobj); + kobject_put(&ls->ls_kobj); else kfree(ls); out: @@ -750,7 +728,7 @@ static int release_lockspace(struct dlm_ls *ls, int force) dlm_clear_members(ls); dlm_clear_members_gone(ls); kfree(ls->ls_node_array); - kobject_unregister(&ls->ls_kobj); + kobject_put(&ls->ls_kobj); /* The ls structure will be freed when the kobject is done with */ mutex_lock(&ls_lock); diff --git a/fs/dquot.c b/fs/dquot.c index 2809768d9c4..cee7c6f428f 100644 --- a/fs/dquot.c +++ b/fs/dquot.c @@ -827,6 +827,18 @@ static inline void dquot_decr_space(struct dquot *dquot, qsize_t number) clear_bit(DQ_BLKS_B, &dquot->dq_flags); } +static int warning_issued(struct dquot *dquot, const int warntype) +{ + int flag = (warntype == QUOTA_NL_BHARDWARN || + warntype == QUOTA_NL_BSOFTLONGWARN) ? DQ_BLKS_B : + ((warntype == QUOTA_NL_IHARDWARN || + warntype == QUOTA_NL_ISOFTLONGWARN) ? DQ_INODES_B : 0); + + if (!flag) + return 0; + return test_and_set_bit(flag, &dquot->dq_flags); +} + #ifdef CONFIG_PRINT_QUOTA_WARNING static int flag_print_warnings = 1; @@ -845,16 +857,12 @@ static inline int need_print_warning(struct dquot *dquot) } /* Print warning to user which exceeded quota */ -static void print_warning(struct dquot *dquot, const char warntype) +static void print_warning(struct dquot *dquot, const int warntype) { char *msg = NULL; struct tty_struct *tty; - int flag = (warntype == QUOTA_NL_BHARDWARN || - warntype == QUOTA_NL_BSOFTLONGWARN) ? DQ_BLKS_B : - ((warntype == QUOTA_NL_IHARDWARN || - warntype == QUOTA_NL_ISOFTLONGWARN) ? DQ_INODES_B : 0); - if (!need_print_warning(dquot) || (flag && test_and_set_bit(flag, &dquot->dq_flags))) + if (!need_print_warning(dquot)) return; mutex_lock(&tty_mutex); @@ -895,9 +903,6 @@ out_lock: #ifdef CONFIG_QUOTA_NETLINK_INTERFACE -/* Size of quota netlink message - actually an upperbound for buffer size */ -#define QUOTA_NL_MSG_SIZE 32 - /* Netlink family structure for quota */ static struct genl_family quota_genl_family = { .id = GENL_ID_GENERATE, @@ -914,11 +919,13 @@ static void send_warning(const struct dquot *dquot, const char warntype) struct sk_buff *skb; void *msg_head; int ret; + int msg_size = 4 * nla_total_size(sizeof(u32)) + + 2 * nla_total_size(sizeof(u64)); /* We have to allocate using GFP_NOFS as we are called from a * filesystem performing write and thus further recursion into * the fs to free some data could cause deadlocks. */ - skb = genlmsg_new(QUOTA_NL_MSG_SIZE, GFP_NOFS); + skb = genlmsg_new(msg_size, GFP_NOFS); if (!skb) { printk(KERN_ERR "VFS: Not enough memory to send quota warning.\n"); @@ -959,18 +966,19 @@ static void send_warning(const struct dquot *dquot, const char warntype) "VFS: Failed to send notification message: %d\n", ret); return; attr_err_out: - printk(KERN_ERR "VFS: Failed to compose quota message: %d\n", ret); + printk(KERN_ERR "VFS: Not enough space to compose quota message!\n"); err_out: kfree_skb(skb); } #endif -static inline void flush_warnings(struct dquot **dquots, char *warntype) +static inline void flush_warnings(struct dquot * const *dquots, char *warntype) { int i; for (i = 0; i < MAXQUOTAS; i++) - if (dquots[i] != NODQUOT && warntype[i] != QUOTA_NL_NOWARN) { + if (dquots[i] != NODQUOT && warntype[i] != QUOTA_NL_NOWARN && + !warning_issued(dquots[i], warntype[i])) { #ifdef CONFIG_PRINT_QUOTA_WARNING print_warning(dquots[i], warntype[i]); #endif @@ -1216,7 +1224,7 @@ warn_put_all: for (cnt = 0; cnt < MAXQUOTAS; cnt++) if (inode->i_dquot[cnt]) mark_dquot_dirty(inode->i_dquot[cnt]); - flush_warnings((struct dquot **)inode->i_dquot, warntype); + flush_warnings(inode->i_dquot, warntype); up_read(&sb_dqopt(inode->i_sb)->dqptr_sem); return ret; } diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index bbed2fd40fd..f8ef0af919e 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -799,7 +799,7 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat) rc = ecryptfs_crypto_api_algify_cipher_name(&full_alg_name, crypt_stat->cipher, "cbc"); if (rc) - goto out; + goto out_unlock; crypt_stat->tfm = crypto_alloc_blkcipher(full_alg_name, 0, CRYPTO_ALG_ASYNC); kfree(full_alg_name); @@ -808,12 +808,12 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat) ecryptfs_printk(KERN_ERR, "cryptfs: init_crypt_ctx(): " "Error initializing cipher [%s]\n", crypt_stat->cipher); - mutex_unlock(&crypt_stat->cs_tfm_mutex); - goto out; + goto out_unlock; } crypto_blkcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY); - mutex_unlock(&crypt_stat->cs_tfm_mutex); rc = 0; +out_unlock: + mutex_unlock(&crypt_stat->cs_tfm_mutex); out: return rc; } @@ -1847,6 +1847,7 @@ ecryptfs_add_new_key_tfm(struct ecryptfs_key_tfm **key_tfm, char *cipher_name, mutex_init(&tmp_tfm->key_tfm_mutex); strncpy(tmp_tfm->cipher_name, cipher_name, ECRYPTFS_MAX_CIPHER_NAME_SIZE); + tmp_tfm->cipher_name[ECRYPTFS_MAX_CIPHER_NAME_SIZE] = '\0'; tmp_tfm->key_size = key_size; rc = ecryptfs_process_key_cipher(&tmp_tfm->key_tfm, tmp_tfm->cipher_name, diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 0b1ab016fa2..5a719180983 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -120,22 +120,9 @@ ecryptfs_do_create(struct inode *directory_inode, rc = ecryptfs_create_underlying_file(lower_dir_dentry->d_inode, ecryptfs_dentry, mode, nd); if (rc) { - struct inode *ecryptfs_inode = ecryptfs_dentry->d_inode; - struct ecryptfs_inode_info *inode_info = - ecryptfs_inode_to_private(ecryptfs_inode); - - printk(KERN_WARNING "%s: Error creating underlying file; " - "rc = [%d]; checking for existing\n", __FUNCTION__, rc); - if (inode_info) { - mutex_lock(&inode_info->lower_file_mutex); - if (!inode_info->lower_file) { - mutex_unlock(&inode_info->lower_file_mutex); - printk(KERN_ERR "%s: Failure to set underlying " - "file; rc = [%d]\n", __FUNCTION__, rc); - goto out_lock; - } - mutex_unlock(&inode_info->lower_file_mutex); - } + printk(KERN_ERR "%s: Failure to create dentry in lower fs; " + "rc = [%d]\n", __FUNCTION__, rc); + goto out_lock; } rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry, directory_inode->i_sb, 0); @@ -451,6 +438,7 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry) dentry->d_inode->i_nlink = ecryptfs_inode_to_lower(dentry->d_inode)->i_nlink; dentry->d_inode->i_ctime = dir->i_ctime; + d_drop(dentry); out_unlock: unlock_parent(lower_dentry); return rc; diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 263fed88c0c..f458c1f3556 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -1860,7 +1860,7 @@ ecryptfs_add_global_auth_tok(struct ecryptfs_mount_crypt_stat *mount_crypt_stat, struct ecryptfs_global_auth_tok *new_auth_tok; int rc = 0; - new_auth_tok = kmem_cache_alloc(ecryptfs_global_auth_tok_cache, + new_auth_tok = kmem_cache_zalloc(ecryptfs_global_auth_tok_cache, GFP_KERNEL); if (!new_auth_tok) { rc = -ENOMEM; diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index b83a512b7e0..0249aa4ae18 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -138,11 +138,14 @@ int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry) inode_info->lower_file = dentry_open(lower_dentry, lower_mnt, (O_RDWR | O_LARGEFILE)); - if (IS_ERR(inode_info->lower_file)) + if (IS_ERR(inode_info->lower_file)) { + dget(lower_dentry); + mntget(lower_mnt); inode_info->lower_file = dentry_open(lower_dentry, lower_mnt, (O_RDONLY | O_LARGEFILE)); + } if (IS_ERR(inode_info->lower_file)) { printk(KERN_ERR "Error opening lower persistent file " "for lower_dentry [0x%p] and lower_mnt [0x%p]\n", @@ -523,6 +526,7 @@ static int ecryptfs_read_super(struct super_block *sb, const char *dev_name) lower_mnt = nd.mnt; ecryptfs_set_superblock_lower(sb, lower_root->d_sb); sb->s_maxbytes = lower_root->d_sb->s_maxbytes; + sb->s_blocksize = lower_root->d_sb->s_blocksize; ecryptfs_set_dentry_lower(sb->s_root, lower_root); ecryptfs_set_dentry_lower_mnt(sb->s_root, lower_mnt); rc = ecryptfs_interpose(lower_root, sb->s_root, sb, 0); @@ -730,127 +734,40 @@ static int ecryptfs_init_kmem_caches(void) return 0; } -struct ecryptfs_obj { - char *name; - struct list_head slot_list; - struct kobject kobj; -}; - -struct ecryptfs_attribute { - struct attribute attr; - ssize_t(*show) (struct ecryptfs_obj *, char *); - ssize_t(*store) (struct ecryptfs_obj *, const char *, size_t); -}; - -static ssize_t -ecryptfs_attr_store(struct kobject *kobj, - struct attribute *attr, const char *buf, size_t len) -{ - struct ecryptfs_obj *obj = container_of(kobj, struct ecryptfs_obj, - kobj); - struct ecryptfs_attribute *attribute = - container_of(attr, struct ecryptfs_attribute, attr); - - return (attribute->store ? attribute->store(obj, buf, len) : 0); -} +static struct kobject *ecryptfs_kobj; -static ssize_t -ecryptfs_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) +static ssize_t version_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buff) { - struct ecryptfs_obj *obj = container_of(kobj, struct ecryptfs_obj, - kobj); - struct ecryptfs_attribute *attribute = - container_of(attr, struct ecryptfs_attribute, attr); - - return (attribute->show ? attribute->show(obj, buf) : 0); + return snprintf(buff, PAGE_SIZE, "%d\n", ECRYPTFS_VERSIONING_MASK); } -static struct sysfs_ops ecryptfs_sysfs_ops = { - .show = ecryptfs_attr_show, - .store = ecryptfs_attr_store -}; +static struct kobj_attribute version_attr = __ATTR_RO(version); -static struct kobj_type ecryptfs_ktype = { - .sysfs_ops = &ecryptfs_sysfs_ops +static struct attribute *attributes[] = { + &version_attr.attr, + NULL, }; -static decl_subsys(ecryptfs, &ecryptfs_ktype, NULL); - -static ssize_t version_show(struct ecryptfs_obj *obj, char *buff) -{ - return snprintf(buff, PAGE_SIZE, "%d\n", ECRYPTFS_VERSIONING_MASK); -} - -static struct ecryptfs_attribute sysfs_attr_version = __ATTR_RO(version); - -static struct ecryptfs_version_str_map_elem { - u32 flag; - char *str; -} ecryptfs_version_str_map[] = { - {ECRYPTFS_VERSIONING_PASSPHRASE, "passphrase"}, - {ECRYPTFS_VERSIONING_PUBKEY, "pubkey"}, - {ECRYPTFS_VERSIONING_PLAINTEXT_PASSTHROUGH, "plaintext passthrough"}, - {ECRYPTFS_VERSIONING_POLICY, "policy"}, - {ECRYPTFS_VERSIONING_XATTR, "metadata in extended attribute"}, - {ECRYPTFS_VERSIONING_MULTKEY, "multiple keys per file"} +static struct attribute_group attr_group = { + .attrs = attributes, }; -static ssize_t version_str_show(struct ecryptfs_obj *obj, char *buff) -{ - int i; - int remaining = PAGE_SIZE; - int total_written = 0; - - buff[0] = '\0'; - for (i = 0; i < ARRAY_SIZE(ecryptfs_version_str_map); i++) { - int entry_size; - - if (!(ECRYPTFS_VERSIONING_MASK - & ecryptfs_version_str_map[i].flag)) - continue; - entry_size = strlen(ecryptfs_version_str_map[i].str); - if ((entry_size + 2) > remaining) - goto out; - memcpy(buff, ecryptfs_version_str_map[i].str, entry_size); - buff[entry_size++] = '\n'; - buff[entry_size] = '\0'; - buff += entry_size; - total_written += entry_size; - remaining -= entry_size; - } -out: - return total_written; -} - -static struct ecryptfs_attribute sysfs_attr_version_str = __ATTR_RO(version_str); - static int do_sysfs_registration(void) { int rc; - rc = subsystem_register(&ecryptfs_subsys); - if (rc) { - printk(KERN_ERR - "Unable to register ecryptfs sysfs subsystem\n"); - goto out; - } - rc = sysfs_create_file(&ecryptfs_subsys.kobj, - &sysfs_attr_version.attr); - if (rc) { - printk(KERN_ERR - "Unable to create ecryptfs version attribute\n"); - subsystem_unregister(&ecryptfs_subsys); + ecryptfs_kobj = kobject_create_and_add("ecryptfs", fs_kobj); + if (!ecryptfs_kobj) { + printk(KERN_ERR "Unable to create ecryptfs kset\n"); + rc = -ENOMEM; goto out; } - rc = sysfs_create_file(&ecryptfs_subsys.kobj, - &sysfs_attr_version_str.attr); + rc = sysfs_create_group(ecryptfs_kobj, &attr_group); if (rc) { printk(KERN_ERR - "Unable to create ecryptfs version_str attribute\n"); - sysfs_remove_file(&ecryptfs_subsys.kobj, - &sysfs_attr_version.attr); - subsystem_unregister(&ecryptfs_subsys); - goto out; + "Unable to create ecryptfs version attributes\n"); + kobject_put(ecryptfs_kobj); } out: return rc; @@ -858,11 +775,8 @@ out: static void do_sysfs_unregistration(void) { - sysfs_remove_file(&ecryptfs_subsys.kobj, - &sysfs_attr_version.attr); - sysfs_remove_file(&ecryptfs_subsys.kobj, - &sysfs_attr_version_str.attr); - subsystem_unregister(&ecryptfs_subsys); + sysfs_remove_group(ecryptfs_kobj, &attr_group); + kobject_put(ecryptfs_kobj); } static int __init ecryptfs_init(void) @@ -890,7 +804,6 @@ static int __init ecryptfs_init(void) printk(KERN_ERR "Failed to register filesystem\n"); goto out_free_kmem_caches; } - kobj_set_kset_s(&ecryptfs_subsys, fs_subsys); rc = do_sysfs_registration(); if (rc) { printk(KERN_ERR "sysfs registration failed\n"); diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index a96d341d154..9cc2aec27b0 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -427,6 +427,7 @@ int ecryptfs_init_messaging(unsigned int transport) if (!ecryptfs_daemon_id_hash) { rc = -ENOMEM; ecryptfs_printk(KERN_ERR, "Failed to allocate memory\n"); + mutex_unlock(&ecryptfs_daemon_id_hash_mux); goto out; } for (i = 0; i < ecryptfs_hash_buckets; i++) diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 16a7a555f39..32c5711d79a 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -263,14 +263,13 @@ out: return 0; } +/* This function must zero any hole we create */ static int ecryptfs_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to) { int rc = 0; + loff_t prev_page_end_size; - if (from == 0 && to == PAGE_CACHE_SIZE) - goto out; /* If we are writing a full page, it will be - up to date. */ if (!PageUptodate(page)) { rc = ecryptfs_read_lower_page_segment(page, page->index, 0, PAGE_CACHE_SIZE, @@ -283,22 +282,32 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page, } else SetPageUptodate(page); } - if (page->index != 0) { - loff_t end_of_prev_pg_pos = - (((loff_t)page->index << PAGE_CACHE_SHIFT) - 1); - if (end_of_prev_pg_pos > i_size_read(page->mapping->host)) { + prev_page_end_size = ((loff_t)page->index << PAGE_CACHE_SHIFT); + + /* + * If creating a page or more of holes, zero them out via truncate. + * Note, this will increase i_size. + */ + if (page->index != 0) { + if (prev_page_end_size > i_size_read(page->mapping->host)) { rc = ecryptfs_truncate(file->f_path.dentry, - end_of_prev_pg_pos); + prev_page_end_size); if (rc) { printk(KERN_ERR "Error on attempt to " "truncate to (higher) offset [%lld];" - " rc = [%d]\n", end_of_prev_pg_pos, rc); + " rc = [%d]\n", prev_page_end_size, rc); goto out; } } - if (end_of_prev_pg_pos + 1 > i_size_read(page->mapping->host)) - zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0); + } + /* + * Writing to a new page, and creating a small hole from start of page? + * Zero it out. + */ + if ((i_size_read(page->mapping->host) == prev_page_end_size) && + (from != 0)) { + zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0); } out: return rc; diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c index 6b7474a4336..948f57624c0 100644 --- a/fs/ecryptfs/read_write.c +++ b/fs/ecryptfs/read_write.c @@ -124,6 +124,10 @@ int ecryptfs_write(struct file *ecryptfs_file, char *data, loff_t offset, loff_t pos; int rc = 0; + /* + * if we are writing beyond current size, then start pos + * at the current size - we'll fill in zeros from there. + */ if (offset > ecryptfs_file_size) pos = ecryptfs_file_size; else @@ -137,6 +141,7 @@ int ecryptfs_write(struct file *ecryptfs_file, char *data, loff_t offset, if (num_bytes > total_remaining_bytes) num_bytes = total_remaining_bytes; if (pos < offset) { + /* remaining zeros to write, up to destination offset */ size_t total_remaining_zeros = (offset - pos); if (num_bytes > total_remaining_zeros) @@ -167,17 +172,27 @@ int ecryptfs_write(struct file *ecryptfs_file, char *data, loff_t offset, } } ecryptfs_page_virt = kmap_atomic(ecryptfs_page, KM_USER0); + + /* + * pos: where we're now writing, offset: where the request was + * If current pos is before request, we are filling zeros + * If we are at or beyond request, we are writing the *data* + * If we're in a fresh page beyond eof, zero it in either case + */ + if (pos < offset || !start_offset_in_page) { + /* We are extending past the previous end of the file. + * Fill in zero values to the end of the page */ + memset(((char *)ecryptfs_page_virt + + start_offset_in_page), 0, + PAGE_CACHE_SIZE - start_offset_in_page); + } + + /* pos >= offset, we are now writing the data request */ if (pos >= offset) { memcpy(((char *)ecryptfs_page_virt + start_offset_in_page), (data + data_offset), num_bytes); data_offset += num_bytes; - } else { - /* We are extending past the previous end of the file. - * Fill in zero values up to the start of where we - * will be writing data. */ - memset(((char *)ecryptfs_page_virt - + start_offset_in_page), 0, num_bytes); } kunmap_atomic(ecryptfs_page_virt, KM_USER0); flush_dcache_page(ecryptfs_page); diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index f8cdab2bee3..4859c4eecd6 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -86,7 +86,6 @@ static void ecryptfs_destroy_inode(struct inode *inode) fput(inode_info->lower_file); inode_info->lower_file = NULL; d_drop(lower_dentry); - d_delete(lower_dentry); } } mutex_unlock(&inode_info->lower_file_mutex); diff --git a/fs/exec.c b/fs/exec.c index 4ccaaa4b13b..282240afe99 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1780,6 +1780,12 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) but keep the previous behaviour for now. */ if (!ispipe && !S_ISREG(inode->i_mode)) goto close_fail; + /* + * Dont allow local users get cute and trick others to coredump + * into their pre-created files: + */ + if (inode->i_uid != current->fsuid) + goto close_fail; if (!file->f_op) goto close_fail; if (!file->f_op->write) diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 7730388c493..c87ae29c19c 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -178,3 +178,10 @@ extern const struct inode_operations ext2_special_inode_operations; /* symlink.c */ extern const struct inode_operations ext2_fast_symlink_inode_operations; extern const struct inode_operations ext2_symlink_inode_operations; + +static inline ext2_fsblk_t +ext2_group_first_block_no(struct super_block *sb, unsigned long group_no) +{ + return group_no * (ext2_fsblk_t)EXT2_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(EXT2_SB(sb)->s_es->s_first_data_block); +} diff --git a/fs/ext3/super.c b/fs/ext3/super.c index de55da9e28b..cb14de1502c 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1676,7 +1676,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); - if (EXT3_INODE_SIZE(sb) == 0) + if (EXT3_INODE_SIZE(sb) == 0 || EXT3_INODES_PER_GROUP(sb) == 0) goto cantfind_ext3; sbi->s_inodes_per_block = blocksize / EXT3_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8031dc0e24e..1ca0f546c46 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1797,7 +1797,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) sbi->s_desc_size = EXT4_MIN_DESC_SIZE; sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); - if (EXT4_INODE_SIZE(sb) == 0) + if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0) goto cantfind_ext4; sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0) diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 2c1b73fb82a..5fb366992b7 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -590,21 +590,49 @@ error: EXPORT_SYMBOL_GPL(fat_free_clusters); +/* 128kb is the whole sectors for FAT12 and FAT16 */ +#define FAT_READA_SIZE (128 * 1024) + +static void fat_ent_reada(struct super_block *sb, struct fat_entry *fatent, + unsigned long reada_blocks) +{ + struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; + sector_t blocknr; + int i, offset; + + ops->ent_blocknr(sb, fatent->entry, &offset, &blocknr); + + for (i = 0; i < reada_blocks; i++) + sb_breadahead(sb, blocknr + i); +} + int fat_count_free_clusters(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); struct fatent_operations *ops = sbi->fatent_ops; struct fat_entry fatent; + unsigned long reada_blocks, reada_mask, cur_block; int err = 0, free; lock_fat(sbi); if (sbi->free_clusters != -1) goto out; + reada_blocks = FAT_READA_SIZE >> sb->s_blocksize_bits; + reada_mask = reada_blocks - 1; + cur_block = 0; + free = 0; fatent_init(&fatent); fatent_set_entry(&fatent, FAT_START_ENT); while (fatent.entry < sbi->max_cluster) { + /* readahead of fat blocks */ + if ((cur_block & reada_mask) == 0) { + unsigned long rest = sbi->fat_length - cur_block; + fat_ent_reada(sb, &fatent, min(reada_blocks, rest)); + } + cur_block++; + err = fat_ent_read_block(sb, &fatent); if (err) goto out; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 0fca82021d7..300324bd563 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -482,8 +482,6 @@ sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc) if (wbc->nr_to_write <= 0) break; } - if (!list_empty(&sb->s_more_io)) - wbc->more_io = 1; return; /* Leave any unwritten inodes on s_io */ } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 3763757f9fe..80d2f5292cf 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -132,6 +132,21 @@ static void fuse_lookup_init(struct fuse_req *req, struct inode *dir, req->out.args[0].value = outarg; } +static u64 fuse_get_attr_version(struct fuse_conn *fc) +{ + u64 curr_version; + + /* + * The spin lock isn't actually needed on 64bit archs, but we + * don't yet care too much about such optimizations. + */ + spin_lock(&fc->lock); + curr_version = fc->attr_version; + spin_unlock(&fc->lock); + + return curr_version; +} + /* * Check whether the dentry is still valid * @@ -171,9 +186,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) return 0; } - spin_lock(&fc->lock); - attr_version = fc->attr_version; - spin_unlock(&fc->lock); + attr_version = fuse_get_attr_version(fc); parent = dget_parent(entry); fuse_lookup_init(req, parent->d_inode, entry, &outarg); @@ -264,9 +277,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, return ERR_PTR(PTR_ERR(forget_req)); } - spin_lock(&fc->lock); - attr_version = fc->attr_version; - spin_unlock(&fc->lock); + attr_version = fuse_get_attr_version(fc); fuse_lookup_init(req, dir, entry, &outarg); request_send(fc, req); @@ -646,6 +657,9 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent, err = req->out.h.error; fuse_put_request(fc, req); if (!err) { + /* ctime changes */ + fuse_invalidate_attr(oldent->d_inode); + fuse_invalidate_attr(olddir); if (olddir != newdir) fuse_invalidate_attr(newdir); @@ -733,9 +747,7 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat, if (IS_ERR(req)) return PTR_ERR(req); - spin_lock(&fc->lock); - attr_version = fc->attr_version; - spin_unlock(&fc->lock); + attr_version = fuse_get_attr_version(fc); memset(&inarg, 0, sizeof(inarg)); memset(&outarg, 0, sizeof(outarg)); @@ -775,6 +787,31 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat, return err; } +int fuse_update_attributes(struct inode *inode, struct kstat *stat, + struct file *file, bool *refreshed) +{ + struct fuse_inode *fi = get_fuse_inode(inode); + int err; + bool r; + + if (fi->i_time < get_jiffies_64()) { + r = true; + err = fuse_do_getattr(inode, stat, file); + } else { + r = false; + err = 0; + if (stat) { + generic_fillattr(inode, stat); + stat->mode = fi->orig_i_mode; + } + } + + if (refreshed != NULL) + *refreshed = r; + + return err; +} + /* * Calling into a user-controlled filesystem gives the filesystem * daemon ptrace-like capabilities over the requester process. This @@ -862,14 +899,9 @@ static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd) */ if ((fc->flags & FUSE_DEFAULT_PERMISSIONS) || ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) { - struct fuse_inode *fi = get_fuse_inode(inode); - if (fi->i_time < get_jiffies_64()) { - err = fuse_do_getattr(inode, NULL, NULL); - if (err) - return err; - - refreshed = true; - } + err = fuse_update_attributes(inode, NULL, NULL, &refreshed); + if (err) + return err; } if (fc->flags & FUSE_DEFAULT_PERMISSIONS) { @@ -935,7 +967,6 @@ static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir) struct page *page; struct inode *inode = file->f_path.dentry->d_inode; struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_file *ff = file->private_data; struct fuse_req *req; if (is_bad_inode(inode)) @@ -952,7 +983,7 @@ static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir) } req->num_pages = 1; req->pages[0] = page; - fuse_read_fill(req, ff, inode, file->f_pos, PAGE_SIZE, FUSE_READDIR); + fuse_read_fill(req, file, inode, file->f_pos, PAGE_SIZE, FUSE_READDIR); request_send(fc, req); nbytes = req->out.args[0].size; err = req->out.h.error; @@ -1173,22 +1204,12 @@ static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry, struct kstat *stat) { struct inode *inode = entry->d_inode; - struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_conn *fc = get_fuse_conn(inode); - int err; if (!fuse_allow_task(fc, current)) return -EACCES; - if (fi->i_time < get_jiffies_64()) - err = fuse_do_getattr(inode, stat, NULL); - else { - err = 0; - generic_fillattr(inode, stat); - stat->mode = fi->orig_i_mode; - } - - return err; + return fuse_update_attributes(inode, stat, NULL, NULL); } static int fuse_setxattr(struct dentry *entry, const char *name, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 535b3739900..bb05d227cf3 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -289,14 +289,16 @@ static int fuse_fsync(struct file *file, struct dentry *de, int datasync) return fuse_fsync_common(file, de, datasync, 0); } -void fuse_read_fill(struct fuse_req *req, struct fuse_file *ff, +void fuse_read_fill(struct fuse_req *req, struct file *file, struct inode *inode, loff_t pos, size_t count, int opcode) { struct fuse_read_in *inarg = &req->misc.read_in; + struct fuse_file *ff = file->private_data; inarg->fh = ff->fh; inarg->offset = pos; inarg->size = count; + inarg->flags = file->f_flags; req->in.h.opcode = opcode; req->in.h.nodeid = get_node_id(inode); req->in.numargs = 1; @@ -313,9 +315,8 @@ static size_t fuse_send_read(struct fuse_req *req, struct file *file, fl_owner_t owner) { struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_file *ff = file->private_data; - fuse_read_fill(req, ff, inode, pos, count, FUSE_READ); + fuse_read_fill(req, file, inode, pos, count, FUSE_READ); if (owner != NULL) { struct fuse_read_in *inarg = &req->misc.read_in; @@ -376,15 +377,16 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req) fuse_put_request(fc, req); } -static void fuse_send_readpages(struct fuse_req *req, struct fuse_file *ff, +static void fuse_send_readpages(struct fuse_req *req, struct file *file, struct inode *inode) { struct fuse_conn *fc = get_fuse_conn(inode); loff_t pos = page_offset(req->pages[0]); size_t count = req->num_pages << PAGE_CACHE_SHIFT; req->out.page_zeroing = 1; - fuse_read_fill(req, ff, inode, pos, count, FUSE_READ); + fuse_read_fill(req, file, inode, pos, count, FUSE_READ); if (fc->async_read) { + struct fuse_file *ff = file->private_data; req->ff = fuse_file_get(ff); req->end = fuse_readpages_end; request_send_background(fc, req); @@ -396,7 +398,7 @@ static void fuse_send_readpages(struct fuse_req *req, struct fuse_file *ff, struct fuse_fill_data { struct fuse_req *req; - struct fuse_file *ff; + struct file *file; struct inode *inode; }; @@ -411,7 +413,7 @@ static int fuse_readpages_fill(void *_data, struct page *page) (req->num_pages == FUSE_MAX_PAGES_PER_REQ || (req->num_pages + 1) * PAGE_CACHE_SIZE > fc->max_read || req->pages[req->num_pages - 1]->index + 1 != page->index)) { - fuse_send_readpages(req, data->ff, inode); + fuse_send_readpages(req, data->file, inode); data->req = req = fuse_get_req(fc); if (IS_ERR(req)) { unlock_page(page); @@ -435,7 +437,7 @@ static int fuse_readpages(struct file *file, struct address_space *mapping, if (is_bad_inode(inode)) goto out; - data.ff = file->private_data; + data.file = file; data.inode = inode; data.req = fuse_get_req(fc); err = PTR_ERR(data.req); @@ -445,7 +447,7 @@ static int fuse_readpages(struct file *file, struct address_space *mapping, err = read_cache_pages(mapping, pages, fuse_readpages_fill, &data); if (!err) { if (data.req->num_pages) - fuse_send_readpages(data.req, data.ff, inode); + fuse_send_readpages(data.req, file, inode); else fuse_put_request(fc, data.req); } @@ -453,11 +455,31 @@ out: return err; } -static void fuse_write_fill(struct fuse_req *req, struct fuse_file *ff, +static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + struct inode *inode = iocb->ki_filp->f_mapping->host; + + if (pos + iov_length(iov, nr_segs) > i_size_read(inode)) { + int err; + /* + * If trying to read past EOF, make sure the i_size + * attribute is up-to-date. + */ + err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL); + if (err) + return err; + } + + return generic_file_aio_read(iocb, iov, nr_segs, pos); +} + +static void fuse_write_fill(struct fuse_req *req, struct file *file, struct inode *inode, loff_t pos, size_t count, int writepage) { struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_file *ff = file->private_data; struct fuse_write_in *inarg = &req->misc.write.in; struct fuse_write_out *outarg = &req->misc.write.out; @@ -466,6 +488,7 @@ static void fuse_write_fill(struct fuse_req *req, struct fuse_file *ff, inarg->offset = pos; inarg->size = count; inarg->write_flags = writepage ? FUSE_WRITE_CACHE : 0; + inarg->flags = file->f_flags; req->in.h.opcode = FUSE_WRITE; req->in.h.nodeid = get_node_id(inode); req->in.argpages = 1; @@ -486,7 +509,7 @@ static size_t fuse_send_write(struct fuse_req *req, struct file *file, fl_owner_t owner) { struct fuse_conn *fc = get_fuse_conn(inode); - fuse_write_fill(req, file->private_data, inode, pos, count, 0); + fuse_write_fill(req, file, inode, pos, count, 0); if (owner != NULL) { struct fuse_write_in *inarg = &req->misc.write.in; inarg->write_flags |= FUSE_WRITE_LOCKOWNER; @@ -887,7 +910,7 @@ static sector_t fuse_bmap(struct address_space *mapping, sector_t block) static const struct file_operations fuse_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, - .aio_read = generic_file_aio_read, + .aio_read = fuse_file_aio_read, .write = do_sync_write, .aio_write = generic_file_aio_write, .mmap = fuse_file_mmap, diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 6c5461de1a5..3ab8a3048e8 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -447,7 +447,7 @@ void fuse_send_forget(struct fuse_conn *fc, struct fuse_req *req, /** * Initialize READ or READDIR request */ -void fuse_read_fill(struct fuse_req *req, struct fuse_file *ff, +void fuse_read_fill(struct fuse_req *req, struct file *file, struct inode *inode, loff_t pos, size_t count, int opcode); /** @@ -593,3 +593,6 @@ int fuse_valid_type(int m); int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task); u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id); + +int fuse_update_attributes(struct inode *inode, struct kstat *stat, + struct file *file, bool *refreshed); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 9a68d697084..e5e80d1a468 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -56,6 +56,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) fi->i_time = 0; fi->nodeid = 0; fi->nlookup = 0; + fi->attr_version = 0; INIT_LIST_HEAD(&fi->write_files); fi->forget_req = fuse_request_alloc(); if (!fi->forget_req) { @@ -562,8 +563,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) arg->major = FUSE_KERNEL_VERSION; arg->minor = FUSE_KERNEL_MINOR_VERSION; arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE; - arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_FILE_OPS | - FUSE_ATOMIC_O_TRUNC; + arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); @@ -744,9 +744,6 @@ static inline void unregister_fuseblk(void) } #endif -static decl_subsys(fuse, NULL, NULL); -static decl_subsys(connections, NULL, NULL); - static void fuse_inode_init_once(struct kmem_cache *cachep, void *foo) { struct inode * inode = foo; @@ -791,32 +788,37 @@ static void fuse_fs_cleanup(void) kmem_cache_destroy(fuse_inode_cachep); } +static struct kobject *fuse_kobj; +static struct kobject *connections_kobj; + static int fuse_sysfs_init(void) { int err; - kobj_set_kset_s(&fuse_subsys, fs_subsys); - err = subsystem_register(&fuse_subsys); - if (err) + fuse_kobj = kobject_create_and_add("fuse", fs_kobj); + if (!fuse_kobj) { + err = -ENOMEM; goto out_err; + } - kobj_set_kset_s(&connections_subsys, fuse_subsys); - err = subsystem_register(&connections_subsys); - if (err) + connections_kobj = kobject_create_and_add("connections", fuse_kobj); + if (!connections_kobj) { + err = -ENOMEM; goto out_fuse_unregister; + } return 0; out_fuse_unregister: - subsystem_unregister(&fuse_subsys); + kobject_put(fuse_kobj); out_err: return err; } static void fuse_sysfs_cleanup(void) { - subsystem_unregister(&connections_subsys); - subsystem_unregister(&fuse_subsys); + kobject_put(connections_kobj); + kobject_put(fuse_kobj); } static int __init fuse_init(void) diff --git a/fs/gfs2/locking/dlm/sysfs.c b/fs/gfs2/locking/dlm/sysfs.c index ae9e6a25fe2..a87b0983976 100644 --- a/fs/gfs2/locking/dlm/sysfs.c +++ b/fs/gfs2/locking/dlm/sysfs.c @@ -189,51 +189,39 @@ static struct kobj_type gdlm_ktype = { .sysfs_ops = &gdlm_attr_ops, }; -static struct kset gdlm_kset = { - .ktype = &gdlm_ktype, -}; +static struct kset *gdlm_kset; int gdlm_kobject_setup(struct gdlm_ls *ls, struct kobject *fskobj) { int error; - error = kobject_set_name(&ls->kobj, "%s", "lock_module"); - if (error) { - log_error("can't set kobj name %d", error); - return error; - } - - ls->kobj.kset = &gdlm_kset; - ls->kobj.ktype = &gdlm_ktype; - ls->kobj.parent = fskobj; - - error = kobject_register(&ls->kobj); + ls->kobj.kset = gdlm_kset; + error = kobject_init_and_add(&ls->kobj, &gdlm_ktype, fskobj, + "lock_module"); if (error) log_error("can't register kobj %d", error); + kobject_uevent(&ls->kobj, KOBJ_ADD); return error; } void gdlm_kobject_release(struct gdlm_ls *ls) { - kobject_unregister(&ls->kobj); + kobject_put(&ls->kobj); } int gdlm_sysfs_init(void) { - int error; - - kobject_set_name(&gdlm_kset.kobj, "lock_dlm"); - kobj_set_kset_s(&gdlm_kset, kernel_subsys); - error = kset_register(&gdlm_kset); - if (error) - printk("lock_dlm: cannot register kset %d\n", error); - - return error; + gdlm_kset = kset_create_and_add("lock_dlm", NULL, kernel_kobj); + if (!gdlm_kset) { + printk(KERN_WARNING "%s: can not create kset\n", __FUNCTION__); + return -ENOMEM; + } + return 0; } void gdlm_sysfs_exit(void) { - kset_unregister(&gdlm_kset); + kset_unregister(gdlm_kset); } diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 06e0b7768d9..3a3176b846f 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -221,9 +221,7 @@ static struct kobj_type gfs2_ktype = { .sysfs_ops = &gfs2_attr_ops, }; -static struct kset gfs2_kset = { - .ktype = &gfs2_ktype, -}; +static struct kset *gfs2_kset; /* * display struct lm_lockstruct fields @@ -495,14 +493,9 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) { int error; - sdp->sd_kobj.kset = &gfs2_kset; - sdp->sd_kobj.ktype = &gfs2_ktype; - - error = kobject_set_name(&sdp->sd_kobj, "%s", sdp->sd_table_name); - if (error) - goto fail; - - error = kobject_register(&sdp->sd_kobj); + sdp->sd_kobj.kset = gfs2_kset; + error = kobject_init_and_add(&sdp->sd_kobj, &gfs2_ktype, NULL, + "%s", sdp->sd_table_name); if (error) goto fail; @@ -522,6 +515,7 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) if (error) goto fail_args; + kobject_uevent(&sdp->sd_kobj, KOBJ_ADD); return 0; fail_args: @@ -531,7 +525,7 @@ fail_counters: fail_lockstruct: sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group); fail_reg: - kobject_unregister(&sdp->sd_kobj); + kobject_put(&sdp->sd_kobj); fail: fs_err(sdp, "error %d adding sysfs files", error); return error; @@ -543,21 +537,22 @@ void gfs2_sys_fs_del(struct gfs2_sbd *sdp) sysfs_remove_group(&sdp->sd_kobj, &args_group); sysfs_remove_group(&sdp->sd_kobj, &counters_group); sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group); - kobject_unregister(&sdp->sd_kobj); + kobject_put(&sdp->sd_kobj); } int gfs2_sys_init(void) { gfs2_sys_margs = NULL; spin_lock_init(&gfs2_sys_margs_lock); - kobject_set_name(&gfs2_kset.kobj, "gfs2"); - kobj_set_kset_s(&gfs2_kset, fs_subsys); - return kset_register(&gfs2_kset); + gfs2_kset = kset_create_and_add("gfs2", NULL, fs_kobj); + if (!gfs2_kset) + return -ENOMEM; + return 0; } void gfs2_sys_uninit(void) { kfree(gfs2_sys_margs); - kset_unregister(&gfs2_kset); + kset_unregister(gfs2_kset); } diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index f13f1494d4f..f8452a0eab5 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -52,6 +52,10 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) rec = (e + b) / 2; len = hfs_brec_lenoff(bnode, rec, &off); keylen = hfs_brec_keylen(bnode, rec); + if (keylen == HFS_BAD_KEYLEN) { + res = -EINVAL; + goto done; + } hfs_bnode_read(bnode, fd->key, off, keylen); cmpval = bnode->tree->keycmp(fd->key, fd->search_key); if (!cmpval) { @@ -67,6 +71,10 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) if (rec != e && e >= 0) { len = hfs_brec_lenoff(bnode, e, &off); keylen = hfs_brec_keylen(bnode, e); + if (keylen == HFS_BAD_KEYLEN) { + res = -EINVAL; + goto done; + } hfs_bnode_read(bnode, fd->key, off, keylen); } done: @@ -198,6 +206,10 @@ int hfs_brec_goto(struct hfs_find_data *fd, int cnt) len = hfs_brec_lenoff(bnode, fd->record, &off); keylen = hfs_brec_keylen(bnode, fd->record); + if (keylen == HFS_BAD_KEYLEN) { + res = -EINVAL; + goto out; + } fd->keyoffset = off; fd->keylength = keylen; fd->entryoffset = off + keylen; diff --git a/fs/hfs/brec.c b/fs/hfs/brec.c index 5c87cf4801f..8626ee375ea 100644 --- a/fs/hfs/brec.c +++ b/fs/hfs/brec.c @@ -44,10 +44,21 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec) recoff = hfs_bnode_read_u16(node, node->tree->node_size - (rec + 1) * 2); if (!recoff) return 0; - if (node->tree->attributes & HFS_TREE_BIGKEYS) + if (node->tree->attributes & HFS_TREE_BIGKEYS) { retval = hfs_bnode_read_u16(node, recoff) + 2; - else + if (retval > node->tree->max_key_len + 2) { + printk(KERN_ERR "hfs: keylen %d too large\n", + retval); + retval = HFS_BAD_KEYLEN; + } + } else { retval = (hfs_bnode_read_u8(node, recoff) | 1) + 1; + if (retval > node->tree->max_key_len + 1) { + printk(KERN_ERR "hfs: keylen %d too large\n", + retval); + retval = HFS_BAD_KEYLEN; + } + } } return retval; } diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 8a3a650abc8..110dd3515dc 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -61,7 +61,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke mapping = tree->inode->i_mapping; page = read_mapping_page(mapping, 0, NULL); if (IS_ERR(page)) - goto free_tree; + goto free_inode; /* Load the header */ head = (struct hfs_btree_header_rec *)(kmap(page) + sizeof(struct hfs_bnode_desc)); @@ -81,6 +81,17 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke goto fail_page; if (!tree->node_count) goto fail_page; + if ((id == HFS_EXT_CNID) && (tree->max_key_len != HFS_MAX_EXT_KEYLEN)) { + printk(KERN_ERR "hfs: invalid extent max_key_len %d\n", + tree->max_key_len); + goto fail_page; + } + if ((id == HFS_CAT_CNID) && (tree->max_key_len != HFS_MAX_CAT_KEYLEN)) { + printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n", + tree->max_key_len); + goto fail_page; + } + tree->node_size_shift = ffs(size) - 1; tree->pages_per_bnode = (tree->node_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; @@ -88,11 +99,12 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke page_cache_release(page); return tree; - fail_page: - tree->inode->i_mapping->a_ops = &hfs_aops; +fail_page: page_cache_release(page); - free_tree: +free_inode: + tree->inode->i_mapping->a_ops = &hfs_aops; iput(tree->inode); +free_tree: kfree(tree); return NULL; } diff --git a/fs/hfs/hfs.h b/fs/hfs/hfs.h index 1445e3a56ed..c6aae61adfe 100644 --- a/fs/hfs/hfs.h +++ b/fs/hfs/hfs.h @@ -28,6 +28,8 @@ #define HFS_MAX_NAMELEN 128 #define HFS_MAX_VALENCE 32767U +#define HFS_BAD_KEYLEN 0xFF + /* Meanings of the drAtrb field of the MDB, * Reference: _Inside Macintosh: Files_ p. 2-61 */ @@ -167,6 +169,9 @@ typedef union hfs_btree_key { struct hfs_ext_key ext; } hfs_btree_key; +#define HFS_MAX_CAT_KEYLEN (sizeof(struct hfs_cat_key) - sizeof(u8)) +#define HFS_MAX_EXT_KEYLEN (sizeof(struct hfs_ext_key) - sizeof(u8)) + typedef union hfs_btree_key btree_key; struct hfs_extent { diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index 47552d4a632..0f69c416eeb 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -602,15 +602,15 @@ int __journal_remove_checkpoint(struct journal_head *jh) /* * There is one special case to worry about: if we have just pulled the - * buffer off a committing transaction's forget list, then even if the - * checkpoint list is empty, the transaction obviously cannot be - * dropped! + * buffer off a running or committing transaction's checkpoing list, + * then even if the checkpoint list is empty, the transaction obviously + * cannot be dropped! * - * The locking here around j_committing_transaction is a bit sleazy. + * The locking here around t_state is a bit sleazy. * See the comment at the end of journal_commit_transaction(). */ - if (transaction == journal->j_committing_transaction) { - JBUFFER_TRACE(jh, "belongs to committing transaction"); + if (transaction->t_state != T_FINISHED) { + JBUFFER_TRACE(jh, "belongs to running/committing transaction"); goto out; } diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 8f1f2aa5fb3..610264b99a8 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -858,10 +858,10 @@ restart_loop: } spin_unlock(&journal->j_list_lock); /* - * This is a bit sleazy. We borrow j_list_lock to protect - * journal->j_committing_transaction in __journal_remove_checkpoint. - * Really, __journal_remove_checkpoint should be using j_state_lock but - * it's a bit hassle to hold that across __journal_remove_checkpoint + * This is a bit sleazy. We use j_list_lock to protect transition + * of a transaction into T_FINISHED state and calling + * __journal_drop_transaction(). Otherwise we could race with + * other checkpointing code processing the transaction... */ spin_lock(&journal->j_state_lock); spin_lock(&journal->j_list_lock); diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 08ff6c7028c..038ed743619 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -288,10 +288,12 @@ handle_t *journal_start(journal_t *journal, int nblocks) jbd_free_handle(handle); current->journal_info = NULL; handle = ERR_PTR(err); + goto out; } lock_acquire(&handle->h_lockdep_map, 0, 0, 0, 2, _THIS_IP_); +out: return handle; } diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index d568ae84674..8adebd3e43c 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -105,7 +105,7 @@ static int jffs2_garbage_collect_thread(void *_c) /* Put_super will send a SIGKILL and then wait on the sem. */ - while (signal_pending(current)) { + while (signal_pending(current) || freezing(current)) { siginfo_t info; unsigned long signr; diff --git a/fs/namei.c b/fs/namei.c index 3b993db26ce..73e2e665817 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1605,7 +1605,7 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) if (S_ISLNK(inode->i_mode)) return -ELOOP; - if (S_ISDIR(inode->i_mode) && (flag & FMODE_WRITE)) + if (S_ISDIR(inode->i_mode) && (acc_mode & MAY_WRITE)) return -EISDIR; /* @@ -1620,7 +1620,7 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) return -EACCES; flag &= ~O_TRUNC; - } else if (IS_RDONLY(inode) && (flag & FMODE_WRITE)) + } else if (IS_RDONLY(inode) && (acc_mode & MAY_WRITE)) return -EROFS; error = vfs_permission(nd, acc_mode); diff --git a/fs/namespace.c b/fs/namespace.c index 06083885b21..61bf376e29e 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -41,8 +41,8 @@ static struct kmem_cache *mnt_cache __read_mostly; static struct rw_semaphore namespace_sem; /* /sys/fs */ -decl_subsys(fs, NULL, NULL); -EXPORT_SYMBOL_GPL(fs_subsys); +struct kobject *fs_kobj; +EXPORT_SYMBOL_GPL(fs_kobj); static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) { @@ -1861,10 +1861,9 @@ void __init mnt_init(void) if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", __FUNCTION__, err); - err = subsystem_register(&fs_subsys); - if (err) - printk(KERN_WARNING "%s: subsystem_register error: %d\n", - __FUNCTION__, err); + fs_kobj = kobject_create_and_add("fs", NULL); + if (!fs_kobj) + printk(KERN_WARNING "%s: kobj create error\n", __FUNCTION__); init_rootfs(); init_mount_tree(); } diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 70587f383f1..a6f62549761 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -410,9 +410,6 @@ static int nfs_create_rpc_client(struct nfs_client *clp, int proto, */ static void nfs_destroy_server(struct nfs_server *server) { - if (!IS_ERR(server->client_acl)) - rpc_shutdown_client(server->client_acl); - if (!(server->flags & NFS_MOUNT_NONLM)) lockd_down(); /* release rpc.lockd */ } @@ -755,6 +752,9 @@ void nfs_free_server(struct nfs_server *server) if (server->destroy != NULL) server->destroy(server); + + if (!IS_ERR(server->client_acl)) + rpc_shutdown_client(server->client_acl); if (!IS_ERR(server->client)) rpc_shutdown_client(server->client); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 35334539d94..f697b5c74b7 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -38,6 +38,7 @@ #include "nfs4_fs.h" #include "delegation.h" #include "iostat.h" +#include "internal.h" /* #define NFS_DEBUG_VERBOSE 1 */ diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index afcab007a22..3c9d16b4f80 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -263,17 +263,19 @@ static const struct rpc_call_ops nfs_read_direct_ops = { * handled automatically by nfs_direct_read_result(). Otherwise, if * no requests have been sent, just return an error. */ -static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, unsigned long user_addr, size_t count, loff_t pos) +static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, + const struct iovec *iov, + loff_t pos) { struct nfs_open_context *ctx = dreq->ctx; struct inode *inode = ctx->path.dentry->d_inode; + unsigned long user_addr = (unsigned long)iov->iov_base; + size_t count = iov->iov_len; size_t rsize = NFS_SERVER(inode)->rsize; unsigned int pgbase; int result; ssize_t started = 0; - get_dreq(dreq); - do { struct nfs_read_data *data; size_t bytes; @@ -347,15 +349,46 @@ static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, unsigned lo count -= bytes; } while (count != 0); + if (started) + return started; + return result < 0 ? (ssize_t) result : -EFAULT; +} + +static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, + const struct iovec *iov, + unsigned long nr_segs, + loff_t pos) +{ + ssize_t result = -EINVAL; + size_t requested_bytes = 0; + unsigned long seg; + + get_dreq(dreq); + + for (seg = 0; seg < nr_segs; seg++) { + const struct iovec *vec = &iov[seg]; + result = nfs_direct_read_schedule_segment(dreq, vec, pos); + if (result < 0) + break; + requested_bytes += result; + if ((size_t)result < vec->iov_len) + break; + pos += vec->iov_len; + } + if (put_dreq(dreq)) nfs_direct_complete(dreq); - if (started) + if (requested_bytes != 0) return 0; - return result < 0 ? (ssize_t) result : -EFAULT; + + if (result < 0) + return result; + return -EIO; } -static ssize_t nfs_direct_read(struct kiocb *iocb, unsigned long user_addr, size_t count, loff_t pos) +static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { ssize_t result = 0; sigset_t oldset; @@ -372,9 +405,8 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, unsigned long user_addr, size if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; - nfs_add_stats(inode, NFSIOS_DIRECTREADBYTES, count); rpc_clnt_sigmask(clnt, &oldset); - result = nfs_direct_read_schedule(dreq, user_addr, count, pos); + result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos); if (!result) result = nfs_direct_wait(dreq); rpc_clnt_sigunmask(clnt, &oldset); @@ -601,17 +633,19 @@ static const struct rpc_call_ops nfs_write_direct_ops = { * handled automatically by nfs_direct_write_result(). Otherwise, if * no requests have been sent, just return an error. */ -static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, unsigned long user_addr, size_t count, loff_t pos, int sync) +static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, + const struct iovec *iov, + loff_t pos, int sync) { struct nfs_open_context *ctx = dreq->ctx; struct inode *inode = ctx->path.dentry->d_inode; + unsigned long user_addr = (unsigned long)iov->iov_base; + size_t count = iov->iov_len; size_t wsize = NFS_SERVER(inode)->wsize; unsigned int pgbase; int result; ssize_t started = 0; - get_dreq(dreq); - do { struct nfs_write_data *data; size_t bytes; @@ -689,15 +723,48 @@ static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, unsigned l count -= bytes; } while (count != 0); + if (started) + return started; + return result < 0 ? (ssize_t) result : -EFAULT; +} + +static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, + const struct iovec *iov, + unsigned long nr_segs, + loff_t pos, int sync) +{ + ssize_t result = 0; + size_t requested_bytes = 0; + unsigned long seg; + + get_dreq(dreq); + + for (seg = 0; seg < nr_segs; seg++) { + const struct iovec *vec = &iov[seg]; + result = nfs_direct_write_schedule_segment(dreq, vec, + pos, sync); + if (result < 0) + break; + requested_bytes += result; + if ((size_t)result < vec->iov_len) + break; + pos += vec->iov_len; + } + if (put_dreq(dreq)) - nfs_direct_write_complete(dreq, inode); + nfs_direct_write_complete(dreq, dreq->inode); - if (started) + if (requested_bytes != 0) return 0; - return result < 0 ? (ssize_t) result : -EFAULT; + + if (result < 0) + return result; + return -EIO; } -static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, size_t count, loff_t pos) +static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos, + size_t count) { ssize_t result = 0; sigset_t oldset; @@ -720,10 +787,8 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, siz if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; - nfs_add_stats(inode, NFSIOS_DIRECTWRITTENBYTES, count); - rpc_clnt_sigmask(clnt, &oldset); - result = nfs_direct_write_schedule(dreq, user_addr, count, pos, sync); + result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, sync); if (!result) result = nfs_direct_wait(dreq); rpc_clnt_sigunmask(clnt, &oldset); @@ -759,21 +824,16 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, ssize_t retval = -EINVAL; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; - /* XXX: temporary */ - const char __user *buf = iov[0].iov_base; - size_t count = iov[0].iov_len; + size_t count; + + count = iov_length(iov, nr_segs); + nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); - dprintk("nfs: direct read(%s/%s, %lu@%Ld)\n", + dprintk("nfs: direct read(%s/%s, %zd@%Ld)\n", file->f_path.dentry->d_parent->d_name.name, file->f_path.dentry->d_name.name, - (unsigned long) count, (long long) pos); + count, (long long) pos); - if (nr_segs != 1) - goto out; - - retval = -EFAULT; - if (!access_ok(VERIFY_WRITE, buf, count)) - goto out; retval = 0; if (!count) goto out; @@ -782,7 +842,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, if (retval) goto out; - retval = nfs_direct_read(iocb, (unsigned long) buf, count, pos); + retval = nfs_direct_read(iocb, iov, nr_segs, pos); if (retval > 0) iocb->ki_pos = pos + retval; @@ -821,17 +881,15 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, ssize_t retval = -EINVAL; struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; - /* XXX: temporary */ - const char __user *buf = iov[0].iov_base; - size_t count = iov[0].iov_len; + size_t count; - dprintk("nfs: direct write(%s/%s, %lu@%Ld)\n", + count = iov_length(iov, nr_segs); + nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count); + + dfprintk(VFS, "nfs: direct write(%s/%s, %zd@%Ld)\n", file->f_path.dentry->d_parent->d_name.name, file->f_path.dentry->d_name.name, - (unsigned long) count, (long long) pos); - - if (nr_segs != 1) - goto out; + count, (long long) pos); retval = generic_write_checks(file, &pos, &count, 0); if (retval) @@ -844,15 +902,11 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, if (!count) goto out; - retval = -EFAULT; - if (!access_ok(VERIFY_READ, buf, count)) - goto out; - retval = nfs_sync_mapping(mapping); if (retval) goto out; - retval = nfs_direct_write(iocb, (unsigned long) buf, count, pos); + retval = nfs_direct_write(iocb, iov, nr_segs, pos, count); if (retval > 0) iocb->ki_pos = pos + retval; diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 522e5ad4d8a..e6242cdbaf9 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -43,6 +43,36 @@ #define NFSDBG_FACILITY NFSDBG_CLIENT /* + * Set the superblock root dentry. + * Note that this function frees the inode in case of error. + */ +static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *inode) +{ + /* The mntroot acts as the dummy root dentry for this superblock */ + if (sb->s_root == NULL) { + sb->s_root = d_alloc_root(inode); + if (sb->s_root == NULL) { + iput(inode); + return -ENOMEM; + } + /* Circumvent igrab(): we know the inode is not being freed */ + atomic_inc(&inode->i_count); + /* + * Ensure that this dentry is invisible to d_find_alias(). + * Otherwise, it may be spliced into the tree by + * d_materialise_unique if a parent directory from the same + * filesystem gets mounted at a later time. + * This again causes shrink_dcache_for_umount_subtree() to + * Oops, since the test for IS_ROOT() will fail. + */ + spin_lock(&dcache_lock); + list_del_init(&sb->s_root->d_alias); + spin_unlock(&dcache_lock); + } + return 0; +} + +/* * get an NFS2/NFS3 root dentry from the root filehandle */ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh) @@ -54,33 +84,6 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh) struct inode *inode; int error; - /* create a dummy root dentry with dummy inode for this superblock */ - if (!sb->s_root) { - struct nfs_fh dummyfh; - struct dentry *root; - struct inode *iroot; - - memset(&dummyfh, 0, sizeof(dummyfh)); - memset(&fattr, 0, sizeof(fattr)); - nfs_fattr_init(&fattr); - fattr.valid = NFS_ATTR_FATTR; - fattr.type = NFDIR; - fattr.mode = S_IFDIR | S_IRUSR | S_IWUSR; - fattr.nlink = 2; - - iroot = nfs_fhget(sb, &dummyfh, &fattr); - if (IS_ERR(iroot)) - return ERR_PTR(PTR_ERR(iroot)); - - root = d_alloc_root(iroot); - if (!root) { - iput(iroot); - return ERR_PTR(-ENOMEM); - } - - sb->s_root = root; - } - /* get the actual root for this mount */ fsinfo.fattr = &fattr; @@ -96,6 +99,10 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh) return ERR_PTR(PTR_ERR(inode)); } + error = nfs_superblock_set_dummy_root(sb, inode); + if (error != 0) + return ERR_PTR(error); + /* root dentries normally start off anonymous and get spliced in later * if the dentry tree reaches them; however if the dentry already * exists, we'll pick it up at this point and use it as the root @@ -241,33 +248,6 @@ struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh) dprintk("--> nfs4_get_root()\n"); - /* create a dummy root dentry with dummy inode for this superblock */ - if (!sb->s_root) { - struct nfs_fh dummyfh; - struct dentry *root; - struct inode *iroot; - - memset(&dummyfh, 0, sizeof(dummyfh)); - memset(&fattr, 0, sizeof(fattr)); - nfs_fattr_init(&fattr); - fattr.valid = NFS_ATTR_FATTR; - fattr.type = NFDIR; - fattr.mode = S_IFDIR | S_IRUSR | S_IWUSR; - fattr.nlink = 2; - - iroot = nfs_fhget(sb, &dummyfh, &fattr); - if (IS_ERR(iroot)) - return ERR_PTR(PTR_ERR(iroot)); - - root = d_alloc_root(iroot); - if (!root) { - iput(iroot); - return ERR_PTR(-ENOMEM); - } - - sb->s_root = root; - } - /* get the info about the server and filesystem */ error = nfs4_server_capabilities(server, mntfh); if (error < 0) { @@ -289,6 +269,10 @@ struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh) return ERR_PTR(PTR_ERR(inode)); } + error = nfs_superblock_set_dummy_root(sb, inode); + if (error != 0) + return ERR_PTR(error); + /* root dentries normally start off anonymous and get spliced in later * if the dentry tree reaches them; however if the dentry already * exists, we'll pick it up at this point and use it as the root diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index b35069a2aa9..bd1b9d663fb 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -115,6 +115,7 @@ struct nfs4_lock_state { #define NFS_LOCK_INITIALIZED 1 int ls_flags; struct nfs_seqid_counter ls_seqid; + struct rpc_sequence ls_sequence; struct nfs_unique_id ls_id; nfs4_stateid ls_stateid; atomic_t ls_count; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f03d9d5f5ba..9e2e1c7291d 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -741,10 +741,10 @@ static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata) if (data->rpc_status == 0) { memcpy(data->o_res.stateid.data, data->c_res.stateid.data, sizeof(data->o_res.stateid.data)); + nfs_confirm_seqid(&data->owner->so_seqid, 0); renew_lease(data->o_res.server, data->timestamp); data->rpc_done = 1; } - nfs_confirm_seqid(&data->owner->so_seqid, data->rpc_status); nfs_increment_open_seqid(data->rpc_status, data->c_arg.seqid); } @@ -759,7 +759,6 @@ static void nfs4_open_confirm_release(void *calldata) /* In case of error, no cleanup! */ if (!data->rpc_done) goto out_free; - nfs_confirm_seqid(&data->owner->so_seqid, 0); state = nfs4_opendata_to_nfs4_state(data); if (!IS_ERR(state)) nfs4_close_state(&data->path, state, data->o_arg.open_flags); @@ -886,7 +885,6 @@ static void nfs4_open_release(void *calldata) /* In case we need an open_confirm, no cleanup! */ if (data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM) goto out_free; - nfs_confirm_seqid(&data->owner->so_seqid, 0); state = nfs4_opendata_to_nfs4_state(data); if (!IS_ERR(state)) nfs4_close_state(&data->path, state, data->o_arg.open_flags); @@ -3333,6 +3331,12 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, p->arg.fh = NFS_FH(inode); p->arg.fl = &p->fl; + if (!(lsp->ls_seqid.flags & NFS_SEQID_CONFIRMED)) { + p->arg.open_seqid = nfs_alloc_seqid(&lsp->ls_state->owner->so_seqid); + if (p->arg.open_seqid == NULL) + goto out_free; + + } p->arg.lock_seqid = nfs_alloc_seqid(&lsp->ls_seqid); if (p->arg.lock_seqid == NULL) goto out_free; @@ -3345,6 +3349,8 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, memcpy(&p->fl, fl, sizeof(p->fl)); return p; out_free: + if (p->arg.open_seqid != NULL) + nfs_free_seqid(p->arg.open_seqid); kfree(p); return NULL; } @@ -3361,23 +3367,23 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata) .rpc_cred = sp->so_cred, }; - if (nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0) - return; dprintk("%s: begin!\n", __FUNCTION__); /* Do we need to do an open_to_lock_owner? */ if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) { - data->arg.open_seqid = nfs_alloc_seqid(&sp->so_seqid); - if (data->arg.open_seqid == NULL) { - data->rpc_status = -ENOMEM; - task->tk_action = NULL; - goto out; - } + if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) + return; data->arg.open_stateid = &state->stateid; data->arg.new_lock_owner = 1; + /* Retest in case we raced... */ + if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) + goto do_rpc; } + if (nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0) + return; + data->arg.new_lock_owner = 0; +do_rpc: data->timestamp = jiffies; rpc_call_setup(task, &msg, 0); -out: dprintk("%s: done!, ret = %d\n", __FUNCTION__, data->rpc_status); } @@ -3413,8 +3419,6 @@ static void nfs4_lock_release(void *calldata) struct nfs4_lockdata *data = calldata; dprintk("%s: begin!\n", __FUNCTION__); - if (data->arg.open_seqid != NULL) - nfs_free_seqid(data->arg.open_seqid); if (data->cancelled != 0) { struct rpc_task *task; task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp, @@ -3424,6 +3428,8 @@ static void nfs4_lock_release(void *calldata) dprintk("%s: cancelling lock!\n", __FUNCTION__); } else nfs_free_seqid(data->arg.lock_seqid); + if (data->arg.open_seqid != NULL) + nfs_free_seqid(data->arg.open_seqid); nfs4_put_lock_state(data->lsp); put_nfs_open_context(data->ctx); kfree(data); diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index 3ea352d82eb..5e2e4af1a0e 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -133,9 +133,7 @@ nfs4_renewd_prepare_shutdown(struct nfs_server *server) void nfs4_kill_renewd(struct nfs_client *clp) { - down_read(&clp->cl_sem); cancel_delayed_work_sync(&clp->cl_renewd); - up_read(&clp->cl_sem); } /* diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 23a9a36556b..5a39c6f78ac 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -509,7 +509,10 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f lsp = kzalloc(sizeof(*lsp), GFP_KERNEL); if (lsp == NULL) return NULL; - lsp->ls_seqid.sequence = &state->owner->so_sequence; + rpc_init_wait_queue(&lsp->ls_sequence.wait, "lock_seqid_waitqueue"); + spin_lock_init(&lsp->ls_sequence.lock); + INIT_LIST_HEAD(&lsp->ls_sequence.list); + lsp->ls_seqid.sequence = &lsp->ls_sequence; atomic_set(&lsp->ls_count, 1); lsp->ls_owner = fl_owner; spin_lock(&clp->cl_lock); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index fa517ae9207..0b0c72a072f 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1054,10 +1054,11 @@ static int nfs_validate_mount_data(void *options, { struct nfs_mount_data *data = (struct nfs_mount_data *)options; + memset(args, 0, sizeof(*args)); + if (data == NULL) goto out_no_data; - memset(args, 0, sizeof(*args)); args->flags = (NFS_MOUNT_VER3 | NFS_MOUNT_TCP); args->rsize = NFS_MAX_FILE_IO_SIZE; args->wsize = NFS_MAX_FILE_IO_SIZE; @@ -1474,6 +1475,11 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags, error = PTR_ERR(mntroot); goto error_splat_super; } + if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) { + dput(mntroot); + error = -ESTALE; + goto error_splat_super; + } s->s_flags |= MS_ACTIVE; mnt->mnt_sb = s; @@ -1531,10 +1537,11 @@ static int nfs4_validate_mount_data(void *options, struct nfs4_mount_data *data = (struct nfs4_mount_data *)options; char *c; + memset(args, 0, sizeof(*args)); + if (data == NULL) goto out_no_data; - memset(args, 0, sizeof(*args)); args->rsize = NFS_MAX_FILE_IO_SIZE; args->wsize = NFS_MAX_FILE_IO_SIZE; args->timeo = 600; @@ -1819,6 +1826,11 @@ static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags, error = PTR_ERR(mntroot); goto error_splat_super; } + if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) { + dput(mntroot); + error = -ESTALE; + goto error_splat_super; + } s->s_flags |= MS_ACTIVE; mnt->mnt_sb = s; @@ -1893,6 +1905,11 @@ static int nfs4_referral_get_sb(struct file_system_type *fs_type, int flags, error = PTR_ERR(mntroot); goto error_splat_super; } + if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) { + dput(mntroot); + error = -ESTALE; + goto error_splat_super; + } s->s_flags |= MS_ACTIVE; mnt->mnt_sb = s; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 89527a487ed..51cc1bd6a11 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1436,7 +1436,8 @@ out: return ret; } -int nfs_wb_page_priority(struct inode *inode, struct page *page, int how) +static int nfs_wb_page_priority(struct inode *inode, struct page *page, + int how) { loff_t range_start = page_offset(page); loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1); diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 2d116d2298f..f917fd25858 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -388,8 +388,11 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, * Round the length of the data which was specified up to * the next multiple of XDR units and then compare that * against the length which was actually received. + * Note that when RPCSEC/GSS (for example) is used, the + * data buffer can be padded so dlen might be larger + * than required. It must never be smaller. */ - if (dlen != XDR_QUADLEN(len)*4) + if (dlen < XDR_QUADLEN(len)*4) return 0; if (args->count > max_blocksize) { diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 986f9b32083..b86e3658a0a 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -313,8 +313,11 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, * Round the length of the data which was specified up to * the next multiple of XDR units and then compare that * against the length which was actually received. + * Note that when RPCSEC/GSS (for example) is used, the + * data buffer can be padded so dlen might be larger + * than required. It must never be smaller. */ - if (dlen != XDR_QUADLEN(len)*4) + if (dlen < XDR_QUADLEN(len)*4) return 0; rqstp->rq_vec[0].iov_base = (void*)p; diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index ce62c152823..23c8cda43f1 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -2389,6 +2389,18 @@ static int __ocfs2_rotate_tree_left(struct inode *inode, goto out; } + /* + * Caller might still want to make changes to the + * tree root, so re-add it to the journal here. + */ + ret = ocfs2_journal_access(handle, inode, + path_root_bh(left_path), + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out; + } + ret = ocfs2_rotate_subtree_left(inode, handle, left_path, right_path, subtree_root, dealloc, &deleted); @@ -3289,16 +3301,6 @@ static int ocfs2_insert_path(struct inode *inode, int ret, subtree_index; struct buffer_head *leaf_bh = path_leaf_bh(right_path); - /* - * Pass both paths to the journal. The majority of inserts - * will be touching all components anyway. - */ - ret = ocfs2_journal_access_path(inode, handle, right_path); - if (ret < 0) { - mlog_errno(ret); - goto out; - } - if (left_path) { int credits = handle->h_buffer_credits; @@ -3323,6 +3325,16 @@ static int ocfs2_insert_path(struct inode *inode, } } + /* + * Pass both paths to the journal. The majority of inserts + * will be touching all components anyway. + */ + ret = ocfs2_journal_access_path(inode, handle, right_path); + if (ret < 0) { + mlog_errno(ret); + goto out; + } + if (insert->ins_split != SPLIT_NONE) { /* * We could call ocfs2_insert_at_leaf() for some types @@ -3331,6 +3343,17 @@ static int ocfs2_insert_path(struct inode *inode, */ ocfs2_split_record(inode, left_path, right_path, insert_rec, insert->ins_split); + + /* + * Split might have modified either leaf and we don't + * have a guarantee that the later edge insert will + * dirty this for us. + */ + if (left_path) + ret = ocfs2_journal_dirty(handle, + path_leaf_bh(left_path)); + if (ret) + mlog_errno(ret); } else ocfs2_insert_at_leaf(insert_rec, path_leaf_el(right_path), insert, inode); @@ -3430,6 +3453,17 @@ static int ocfs2_do_insert_extent(struct inode *inode, mlog_errno(ret); goto out; } + + /* + * ocfs2_rotate_tree_right() might have extended the + * transaction without re-journaling our tree root. + */ + ret = ocfs2_journal_access(handle, inode, di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out; + } } else if (type->ins_appending == APPEND_TAIL && type->ins_contig != CONTIG_LEFT) { ret = ocfs2_append_rec_to_path(inode, handle, insert_rec, @@ -3941,7 +3975,7 @@ static int __ocfs2_mark_extent_written(struct inode *inode, { int ret = 0; struct ocfs2_extent_list *el = path_leaf_el(path); - struct buffer_head *eb_bh, *last_eb_bh = NULL; + struct buffer_head *last_eb_bh = NULL; struct ocfs2_extent_rec *rec = &el->l_recs[split_index]; struct ocfs2_merge_ctxt ctxt; struct ocfs2_extent_list *rightmost_el; @@ -3960,14 +3994,6 @@ static int __ocfs2_mark_extent_written(struct inode *inode, goto out; } - eb_bh = path_leaf_bh(path); - ret = ocfs2_journal_access(handle, inode, eb_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (ret) { - mlog_errno(ret); - goto out; - } - ctxt.c_contig_type = ocfs2_figure_merge_contig_type(inode, el, split_index, split_rec); @@ -4029,8 +4055,6 @@ static int __ocfs2_mark_extent_written(struct inode *inode, mlog_errno(ret); } - ocfs2_journal_dirty(handle, eb_bh); - out: brelse(last_eb_bh); return ret; @@ -6093,8 +6117,6 @@ start: mlog(0, "clusters_to_del = %u in this pass, tail blk=%llu\n", clusters_to_del, (unsigned long long)path_leaf_bh(path)->b_blocknr); - BUG_ON(clusters_to_del == 0); - mutex_lock(&tl_inode->i_mutex); tl_sem = 1; /* ocfs2_truncate_log_needs_flush guarantees us at least one diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 556e34ccb00..56f7790cad4 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1514,7 +1514,7 @@ int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size) { struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; - if (new_size < le16_to_cpu(di->id2.i_data.id_count)) + if (new_size <= le16_to_cpu(di->id2.i_data.id_count)) return 1; return 0; } diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c index a4882c8df94..23c732f2752 100644 --- a/fs/ocfs2/cluster/masklog.c +++ b/fs/ocfs2/cluster/masklog.c @@ -146,7 +146,7 @@ static struct kset mlog_kset = { .kobj = {.ktype = &mlog_ktype}, }; -int mlog_sys_init(struct kset *o2cb_subsys) +int mlog_sys_init(struct kset *o2cb_kset) { int i = 0; @@ -157,7 +157,7 @@ int mlog_sys_init(struct kset *o2cb_subsys) mlog_attr_ptrs[i] = NULL; kobject_set_name(&mlog_kset.kobj, "logmask"); - kobj_set_kset_s(&mlog_kset, *o2cb_subsys); + mlog_kset.kobj.kset = o2cb_kset; return kset_register(&mlog_kset); } diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h index cd046060114..597e064bb94 100644 --- a/fs/ocfs2/cluster/masklog.h +++ b/fs/ocfs2/cluster/masklog.h @@ -212,7 +212,7 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits; #define mlog_errno(st) do { \ int _st = (st); \ if (_st != -ERESTARTSYS && _st != -EINTR && \ - _st != AOP_TRUNCATED_PAGE) \ + _st != AOP_TRUNCATED_PAGE && _st != -ENOSPC) \ mlog(ML_ERROR, "status = %lld\n", (long long)_st); \ } while (0) diff --git a/fs/ocfs2/cluster/sys.c b/fs/ocfs2/cluster/sys.c index 64f6f378fd0..a4b07730b2e 100644 --- a/fs/ocfs2/cluster/sys.c +++ b/fs/ocfs2/cluster/sys.c @@ -28,96 +28,55 @@ #include <linux/module.h> #include <linux/kobject.h> #include <linux/sysfs.h> +#include <linux/fs.h> #include "ocfs2_nodemanager.h" #include "masklog.h" #include "sys.h" -struct o2cb_attribute { - struct attribute attr; - ssize_t (*show)(char *buf); - ssize_t (*store)(const char *buf, size_t count); -}; - -#define O2CB_ATTR(_name, _mode, _show, _store) \ -struct o2cb_attribute o2cb_attr_##_name = __ATTR(_name, _mode, _show, _store) - -#define to_o2cb_attr(_attr) container_of(_attr, struct o2cb_attribute, attr) -static ssize_t o2cb_interface_revision_show(char *buf) +static ssize_t version_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) { return snprintf(buf, PAGE_SIZE, "%u\n", O2NM_API_VERSION); } - -static O2CB_ATTR(interface_revision, S_IFREG | S_IRUGO, o2cb_interface_revision_show, NULL); +static struct kobj_attribute attr_version = + __ATTR(interface_revision, S_IFREG | S_IRUGO, version_show, NULL); static struct attribute *o2cb_attrs[] = { - &o2cb_attr_interface_revision.attr, + &attr_version.attr, NULL, }; -static ssize_t -o2cb_show(struct kobject * kobj, struct attribute * attr, char * buffer); -static ssize_t -o2cb_store(struct kobject * kobj, struct attribute * attr, - const char * buffer, size_t count); -static struct sysfs_ops o2cb_sysfs_ops = { - .show = o2cb_show, - .store = o2cb_store, +static struct attribute_group o2cb_attr_group = { + .attrs = o2cb_attrs, }; -static struct kobj_type o2cb_subsys_type = { - .default_attrs = o2cb_attrs, - .sysfs_ops = &o2cb_sysfs_ops, -}; - -/* gives us o2cb_subsys */ -static decl_subsys(o2cb, NULL, NULL); - -static ssize_t -o2cb_show(struct kobject * kobj, struct attribute * attr, char * buffer) -{ - struct o2cb_attribute *o2cb_attr = to_o2cb_attr(attr); - struct kset *sbs = to_kset(kobj); - - BUG_ON(sbs != &o2cb_subsys); - - if (o2cb_attr->show) - return o2cb_attr->show(buffer); - return -EIO; -} - -static ssize_t -o2cb_store(struct kobject * kobj, struct attribute * attr, - const char * buffer, size_t count) -{ - struct o2cb_attribute *o2cb_attr = to_o2cb_attr(attr); - struct kset *sbs = to_kset(kobj); - - BUG_ON(sbs != &o2cb_subsys); - - if (o2cb_attr->store) - return o2cb_attr->store(buffer, count); - return -EIO; -} +static struct kset *o2cb_kset; void o2cb_sys_shutdown(void) { mlog_sys_shutdown(); - subsystem_unregister(&o2cb_subsys); + kset_unregister(o2cb_kset); } int o2cb_sys_init(void) { int ret; - o2cb_subsys.kobj.ktype = &o2cb_subsys_type; - ret = subsystem_register(&o2cb_subsys); + o2cb_kset = kset_create_and_add("o2cb", NULL, fs_kobj); + if (!o2cb_kset) + return -ENOMEM; + + ret = sysfs_create_group(&o2cb_kset->kobj, &o2cb_attr_group); if (ret) - return ret; + goto error; - ret = mlog_sys_init(&o2cb_subsys); + ret = mlog_sys_init(o2cb_kset); if (ret) - subsystem_unregister(&o2cb_subsys); + goto error; + return 0; +error: + kset_unregister(o2cb_kset); return ret; } diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index d84bd155997..ee50c9610e7 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -72,14 +72,6 @@ #include "tcp_internal.h" -/* - * The linux network stack isn't sparse endian clean.. It has macros like - * ntohs() which perform the endian checks and structs like sockaddr_in - * which aren't annotated. So __force is found here to get the build - * clean. When they emerge from the dark ages and annotate the code - * we can remove these. - */ - #define SC_NODEF_FMT "node %s (num %u) at %u.%u.%u.%u:%u" #define SC_NODEF_ARGS(sc) sc->sc_node->nd_name, sc->sc_node->nd_num, \ NIPQUAD(sc->sc_node->nd_ipv4_address), \ @@ -1500,7 +1492,7 @@ static void o2net_start_connect(struct work_struct *work) myaddr.sin_family = AF_INET; myaddr.sin_addr.s_addr = mynode->nd_ipv4_address; - myaddr.sin_port = (__force u16)htons(0); /* any port */ + myaddr.sin_port = htons(0); /* any port */ ret = sock->ops->bind(sock, (struct sockaddr *)&myaddr, sizeof(myaddr)); @@ -1701,11 +1693,11 @@ static int o2net_accept_one(struct socket *sock) if (ret < 0) goto out; - node = o2nm_get_node_by_ip((__force __be32)sin.sin_addr.s_addr); + node = o2nm_get_node_by_ip(sin.sin_addr.s_addr); if (node == NULL) { mlog(ML_NOTICE, "attempt to connect from unknown node at " "%u.%u.%u.%u:%d\n", NIPQUAD(sin.sin_addr.s_addr), - ntohs((__force __be16)sin.sin_port)); + ntohs(sin.sin_port)); ret = -EINVAL; goto out; } @@ -1714,7 +1706,7 @@ static int o2net_accept_one(struct socket *sock) mlog(ML_NOTICE, "unexpected connect attempted from a lower " "numbered node '%s' at " "%u.%u.%u.%u:%d with num %u\n", node->nd_name, NIPQUAD(sin.sin_addr.s_addr), - ntohs((__force __be16)sin.sin_port), node->nd_num); + ntohs(sin.sin_port), node->nd_num); ret = -EINVAL; goto out; } @@ -1725,7 +1717,7 @@ static int o2net_accept_one(struct socket *sock) mlog(ML_CONN, "attempt to connect from node '%s' at " "%u.%u.%u.%u:%d but it isn't heartbeating\n", node->nd_name, NIPQUAD(sin.sin_addr.s_addr), - ntohs((__force __be16)sin.sin_port)); + ntohs(sin.sin_port)); ret = -EINVAL; goto out; } @@ -1742,7 +1734,7 @@ static int o2net_accept_one(struct socket *sock) mlog(ML_NOTICE, "attempt to connect from node '%s' at " "%u.%u.%u.%u:%d but it already has an open connection\n", node->nd_name, NIPQUAD(sin.sin_addr.s_addr), - ntohs((__force __be16)sin.sin_port)); + ntohs(sin.sin_port)); goto out; } diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 1957a5ed219..9923278ea6d 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -344,12 +344,24 @@ static void ocfs2_dentry_iput(struct dentry *dentry, struct inode *inode) { struct ocfs2_dentry_lock *dl = dentry->d_fsdata; - mlog_bug_on_msg(!dl && !(dentry->d_flags & DCACHE_DISCONNECTED), - "dentry: %.*s\n", dentry->d_name.len, - dentry->d_name.name); + if (!dl) { + /* + * No dentry lock is ok if we're disconnected or + * unhashed. + */ + if (!(dentry->d_flags & DCACHE_DISCONNECTED) && + !d_unhashed(dentry)) { + unsigned long long ino = 0ULL; + if (inode) + ino = (unsigned long long)OCFS2_I(inode)->ip_blkno; + mlog(ML_ERROR, "Dentry is missing cluster lock. " + "inode: %llu, d_flags: 0x%x, d_name: %.*s\n", + ino, dentry->d_flags, dentry->d_name.len, + dentry->d_name.name); + } - if (!dl) goto out; + } mlog_bug_on_msg(dl->dl_count == 0, "dentry: %.*s, count: %u\n", dentry->d_name.len, dentry->d_name.name, diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 62e4a7daa28..a54d33d95ad 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -908,7 +908,7 @@ lookup: * but they might own this lockres. wait on them. */ bit = find_next_bit(dlm->recovery_map, O2NM_MAX_NODES, 0); if (bit < O2NM_MAX_NODES) { - mlog(ML_NOTICE, "%s:%.*s: at least one node (%d) to" + mlog(ML_NOTICE, "%s:%.*s: at least one node (%d) to " "recover before lock mastery can begin\n", dlm->name, namelen, (char *)lockid, bit); wait_on_recovery = 1; @@ -962,7 +962,7 @@ redo_request: spin_lock(&dlm->spinlock); bit = find_next_bit(dlm->recovery_map, O2NM_MAX_NODES, 0); if (bit < O2NM_MAX_NODES) { - mlog(ML_NOTICE, "%s:%.*s: at least one node (%d) to" + mlog(ML_NOTICE, "%s:%.*s: at least one node (%d) to " "recover before lock mastery can begin\n", dlm->name, namelen, (char *)lockid, bit); wait_on_recovery = 1; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index bbac7cd33e0..b75b2e1f0e4 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -399,7 +399,7 @@ static int ocfs2_truncate_file(struct inode *inode, if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { status = ocfs2_truncate_inline(inode, di_bh, new_i_size, - i_size_read(inode), 0); + i_size_read(inode), 1); if (status) mlog_errno(status); @@ -1521,6 +1521,7 @@ static int ocfs2_remove_inode_range(struct inode *inode, u32 trunc_start, trunc_len, cpos, phys_cpos, alloc_size; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_cached_dealloc_ctxt dealloc; + struct address_space *mapping = inode->i_mapping; ocfs2_init_dealloc_ctxt(&dealloc); @@ -1529,10 +1530,20 @@ static int ocfs2_remove_inode_range(struct inode *inode, if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { ret = ocfs2_truncate_inline(inode, di_bh, byte_start, - byte_start + byte_len, 1); - if (ret) + byte_start + byte_len, 0); + if (ret) { mlog_errno(ret); - return ret; + goto out; + } + /* + * There's no need to get fancy with the page cache + * truncate of an inline-data inode. We're talking + * about less than a page here, which will be cached + * in the dinode buffer anyway. + */ + unmap_mapping_range(mapping, 0, 0, 0); + truncate_inode_pages(mapping, 0); + goto out; } trunc_start = ocfs2_clusters_for_bytes(osb->sb, byte_start); diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 1d5e0cb0fda..ebb2bbe30f3 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -455,8 +455,8 @@ static int ocfs2_read_locked_inode(struct inode *inode, status = -EINVAL; fe = (struct ocfs2_dinode *) bh->b_data; if (!OCFS2_IS_VALID_DINODE(fe)) { - mlog(ML_ERROR, "Invalid dinode #%llu: signature = %.*s\n", - (unsigned long long)le64_to_cpu(fe->i_blkno), 7, + mlog(0, "Invalid dinode #%llu: signature = %.*s\n", + (unsigned long long)args->fi_blkno, 7, fe->i_signature); goto bail; } @@ -863,7 +863,7 @@ static int ocfs2_query_inode_wipe(struct inode *inode, status = ocfs2_try_open_lock(inode, 1); if (status == -EAGAIN) { status = 0; - mlog(0, "Skipping delete of %llu because it is in use on" + mlog(0, "Skipping delete of %llu because it is in use on " "other nodes\n", (unsigned long long)oi->ip_blkno); goto bail; } diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index f9d01e25298..8d81f6c1b87 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -174,6 +174,12 @@ int ocfs2_commit_trans(struct ocfs2_super *osb, * transaction. extend_trans will either extend the current handle by * nblocks, or commit it and start a new one with nblocks credits. * + * This might call journal_restart() which will commit dirty buffers + * and then restart the transaction. Before calling + * ocfs2_extend_trans(), any changed blocks should have been + * dirtied. After calling it, all blocks which need to be changed must + * go through another set of journal_access/journal_dirty calls. + * * WARNING: This will not release any semaphores or disk locks taken * during the transaction, so make sure they were taken *before* * start_trans or we'll have ordering deadlocks. @@ -193,11 +199,15 @@ int ocfs2_extend_trans(handle_t *handle, int nblocks) mlog(0, "Trying to extend transaction by %d blocks\n", nblocks); +#ifdef OCFS2_DEBUG_FS + status = 1; +#else status = journal_extend(handle, nblocks); if (status < 0) { mlog_errno(status); goto bail; } +#endif if (status > 0) { mlog(0, "journal_extend failed, trying journal_restart\n"); @@ -1277,11 +1287,12 @@ static int ocfs2_queue_orphans(struct ocfs2_super *osb, ocfs2_orphan_filldir); if (status) { mlog_errno(status); - goto out; + goto out_cluster; } *head = priv.head; +out_cluster: ocfs2_meta_unlock(orphan_dir_inode, 0); out: mutex_unlock(&orphan_dir_inode->i_mutex); diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index d272847d5a0..58ea88b5af3 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -484,6 +484,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb, alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data; +#ifdef OCFS2_DEBUG_FS if (le32_to_cpu(alloc->id1.bitmap1.i_used) != ocfs2_local_alloc_count_bits(alloc)) { ocfs2_error(osb->sb, "local alloc inode %llu says it has " @@ -494,6 +495,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb, status = -EIO; goto bail; } +#endif free_bits = le32_to_cpu(alloc->id1.bitmap1.i_total) - le32_to_cpu(alloc->id1.bitmap1.i_used); @@ -712,9 +714,8 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, void *bitmap; struct ocfs2_local_alloc *la = OCFS2_LOCAL_ALLOC(alloc); - mlog_entry("total = %u, COUNT = %u, used = %u\n", + mlog_entry("total = %u, used = %u\n", le32_to_cpu(alloc->id1.bitmap1.i_total), - ocfs2_local_alloc_count_bits(alloc), le32_to_cpu(alloc->id1.bitmap1.i_used)); if (!alloc->id1.bitmap1.i_total) { diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index be562ac3e89..5ee77542066 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -438,14 +438,14 @@ unlock_osb: } if (!ret) { - if (!ocfs2_is_hard_readonly(osb)) - ocfs2_set_journal_params(osb); - /* Only save off the new mount options in case of a successful * remount. */ osb->s_mount_opt = parsed_options.mount_opt; osb->s_atime_quantum = parsed_options.atime_quantum; osb->preferred_slot = parsed_options.slot; + + if (!ocfs2_is_hard_readonly(osb)) + ocfs2_set_journal_params(osb); } out: return ret; diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index d8817384008..6b7ff161894 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -131,7 +131,7 @@ static void property_stop(struct seq_file *f, void *v) /* Nothing to do */ } -static struct seq_operations property_op = { +static const struct seq_operations property_op = { .start = property_start, .next = property_next, .stop = property_stop, diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 722e12e5acc..739da701ae7 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -195,96 +195,45 @@ check_partition(struct gendisk *hd, struct block_device *bdev) return ERR_PTR(res); } -/* - * sysfs bindings for partitions - */ - -struct part_attribute { - struct attribute attr; - ssize_t (*show)(struct hd_struct *,char *); - ssize_t (*store)(struct hd_struct *,const char *, size_t); -}; - -static ssize_t -part_attr_show(struct kobject * kobj, struct attribute * attr, char * page) +static ssize_t part_start_show(struct device *dev, + struct device_attribute *attr, char *buf) { - struct hd_struct * p = container_of(kobj,struct hd_struct,kobj); - struct part_attribute * part_attr = container_of(attr,struct part_attribute,attr); - ssize_t ret = 0; - if (part_attr->show) - ret = part_attr->show(p, page); - return ret; -} -static ssize_t -part_attr_store(struct kobject * kobj, struct attribute * attr, - const char *page, size_t count) -{ - struct hd_struct * p = container_of(kobj,struct hd_struct,kobj); - struct part_attribute * part_attr = container_of(attr,struct part_attribute,attr); - ssize_t ret = 0; + struct hd_struct *p = dev_to_part(dev); - if (part_attr->store) - ret = part_attr->store(p, page, count); - return ret; + return sprintf(buf, "%llu\n",(unsigned long long)p->start_sect); } -static struct sysfs_ops part_sysfs_ops = { - .show = part_attr_show, - .store = part_attr_store, -}; - -static ssize_t part_uevent_store(struct hd_struct * p, - const char *page, size_t count) +static ssize_t part_size_show(struct device *dev, + struct device_attribute *attr, char *buf) { - kobject_uevent(&p->kobj, KOBJ_ADD); - return count; + struct hd_struct *p = dev_to_part(dev); + return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects); } -static ssize_t part_dev_read(struct hd_struct * p, char *page) -{ - struct gendisk *disk = container_of(p->kobj.parent,struct gendisk,kobj); - dev_t dev = MKDEV(disk->major, disk->first_minor + p->partno); - return print_dev_t(page, dev); -} -static ssize_t part_start_read(struct hd_struct * p, char *page) -{ - return sprintf(page, "%llu\n",(unsigned long long)p->start_sect); -} -static ssize_t part_size_read(struct hd_struct * p, char *page) -{ - return sprintf(page, "%llu\n",(unsigned long long)p->nr_sects); -} -static ssize_t part_stat_read(struct hd_struct * p, char *page) + +static ssize_t part_stat_show(struct device *dev, + struct device_attribute *attr, char *buf) { - return sprintf(page, "%8u %8llu %8u %8llu\n", + struct hd_struct *p = dev_to_part(dev); + + return sprintf(buf, "%8u %8llu %8u %8llu\n", p->ios[0], (unsigned long long)p->sectors[0], p->ios[1], (unsigned long long)p->sectors[1]); } -static struct part_attribute part_attr_uevent = { - .attr = {.name = "uevent", .mode = S_IWUSR }, - .store = part_uevent_store -}; -static struct part_attribute part_attr_dev = { - .attr = {.name = "dev", .mode = S_IRUGO }, - .show = part_dev_read -}; -static struct part_attribute part_attr_start = { - .attr = {.name = "start", .mode = S_IRUGO }, - .show = part_start_read -}; -static struct part_attribute part_attr_size = { - .attr = {.name = "size", .mode = S_IRUGO }, - .show = part_size_read -}; -static struct part_attribute part_attr_stat = { - .attr = {.name = "stat", .mode = S_IRUGO }, - .show = part_stat_read -}; #ifdef CONFIG_FAIL_MAKE_REQUEST +static ssize_t part_fail_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hd_struct *p = dev_to_part(dev); -static ssize_t part_fail_store(struct hd_struct * p, + return sprintf(buf, "%d\n", p->make_it_fail); +} + +static ssize_t part_fail_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { + struct hd_struct *p = dev_to_part(dev); int i; if (count > 0 && sscanf(buf, "%d", &i) > 0) @@ -292,50 +241,53 @@ static ssize_t part_fail_store(struct hd_struct * p, return count; } -static ssize_t part_fail_read(struct hd_struct * p, char *page) -{ - return sprintf(page, "%d\n", p->make_it_fail); -} -static struct part_attribute part_attr_fail = { - .attr = {.name = "make-it-fail", .mode = S_IRUGO | S_IWUSR }, - .store = part_fail_store, - .show = part_fail_read -}; +#endif +static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL); +static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); +static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); +#ifdef CONFIG_FAIL_MAKE_REQUEST +static struct device_attribute dev_attr_fail = + __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); #endif -static struct attribute * default_attrs[] = { - &part_attr_uevent.attr, - &part_attr_dev.attr, - &part_attr_start.attr, - &part_attr_size.attr, - &part_attr_stat.attr, +static struct attribute *part_attrs[] = { + &dev_attr_start.attr, + &dev_attr_size.attr, + &dev_attr_stat.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST - &part_attr_fail.attr, + &dev_attr_fail.attr, #endif - NULL, + NULL }; -extern struct kset block_subsys; +static struct attribute_group part_attr_group = { + .attrs = part_attrs, +}; -static void part_release(struct kobject *kobj) +static struct attribute_group *part_attr_groups[] = { + &part_attr_group, + NULL +}; + +static void part_release(struct device *dev) { - struct hd_struct * p = container_of(kobj,struct hd_struct,kobj); + struct hd_struct *p = dev_to_part(dev); kfree(p); } -struct kobj_type ktype_part = { +struct device_type part_type = { + .name = "partition", + .groups = part_attr_groups, .release = part_release, - .default_attrs = default_attrs, - .sysfs_ops = &part_sysfs_ops, }; static inline void partition_sysfs_add_subdir(struct hd_struct *p) { struct kobject *k; - k = kobject_get(&p->kobj); - p->holder_dir = kobject_add_dir(k, "holders"); + k = kobject_get(&p->dev.kobj); + p->holder_dir = kobject_create_and_add("holders", k); kobject_put(k); } @@ -343,15 +295,16 @@ static inline void disk_sysfs_add_subdirs(struct gendisk *disk) { struct kobject *k; - k = kobject_get(&disk->kobj); - disk->holder_dir = kobject_add_dir(k, "holders"); - disk->slave_dir = kobject_add_dir(k, "slaves"); + k = kobject_get(&disk->dev.kobj); + disk->holder_dir = kobject_create_and_add("holders", k); + disk->slave_dir = kobject_create_and_add("slaves", k); kobject_put(k); } void delete_partition(struct gendisk *disk, int part) { struct hd_struct *p = disk->part[part-1]; + if (!p) return; if (!p->nr_sects) @@ -361,113 +314,55 @@ void delete_partition(struct gendisk *disk, int part) p->nr_sects = 0; p->ios[0] = p->ios[1] = 0; p->sectors[0] = p->sectors[1] = 0; - sysfs_remove_link(&p->kobj, "subsystem"); - kobject_unregister(p->holder_dir); - kobject_uevent(&p->kobj, KOBJ_REMOVE); - kobject_del(&p->kobj); - kobject_put(&p->kobj); + kobject_put(p->holder_dir); + device_del(&p->dev); + put_device(&p->dev); } void add_partition(struct gendisk *disk, int part, sector_t start, sector_t len, int flags) { struct hd_struct *p; + int err; p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return; - + p->start_sect = start; p->nr_sects = len; p->partno = part; p->policy = disk->policy; - if (isdigit(disk->kobj.k_name[strlen(disk->kobj.k_name)-1])) - kobject_set_name(&p->kobj, "%sp%d", - kobject_name(&disk->kobj), part); + if (isdigit(disk->dev.bus_id[strlen(disk->dev.bus_id)-1])) + snprintf(p->dev.bus_id, BUS_ID_SIZE, + "%sp%d", disk->dev.bus_id, part); else - kobject_set_name(&p->kobj, "%s%d", - kobject_name(&disk->kobj),part); - p->kobj.parent = &disk->kobj; - p->kobj.ktype = &ktype_part; - kobject_init(&p->kobj); - kobject_add(&p->kobj); - if (!disk->part_uevent_suppress) - kobject_uevent(&p->kobj, KOBJ_ADD); - sysfs_create_link(&p->kobj, &block_subsys.kobj, "subsystem"); + snprintf(p->dev.bus_id, BUS_ID_SIZE, + "%s%d", disk->dev.bus_id, part); + + device_initialize(&p->dev); + p->dev.devt = MKDEV(disk->major, disk->first_minor + part); + p->dev.class = &block_class; + p->dev.type = &part_type; + p->dev.parent = &disk->dev; + disk->part[part-1] = p; + + /* delay uevent until 'holders' subdir is created */ + p->dev.uevent_suppress = 1; + device_add(&p->dev); + partition_sysfs_add_subdir(p); + p->dev.uevent_suppress = 0; if (flags & ADDPART_FLAG_WHOLEDISK) { static struct attribute addpartattr = { .name = "whole_disk", .mode = S_IRUSR | S_IRGRP | S_IROTH, }; - - sysfs_create_file(&p->kobj, &addpartattr); + err = sysfs_create_file(&p->dev.kobj, &addpartattr); } - partition_sysfs_add_subdir(p); - disk->part[part-1] = p; -} -static char *make_block_name(struct gendisk *disk) -{ - char *name; - static char *block_str = "block:"; - int size; - char *s; - - size = strlen(block_str) + strlen(disk->disk_name) + 1; - name = kmalloc(size, GFP_KERNEL); - if (!name) - return NULL; - strcpy(name, block_str); - strcat(name, disk->disk_name); - /* ewww... some of these buggers have / in name... */ - s = strchr(name, '/'); - if (s) - *s = '!'; - return name; -} - -static int disk_sysfs_symlinks(struct gendisk *disk) -{ - struct device *target = get_device(disk->driverfs_dev); - int err; - char *disk_name = NULL; - - if (target) { - disk_name = make_block_name(disk); - if (!disk_name) { - err = -ENOMEM; - goto err_out; - } - - err = sysfs_create_link(&disk->kobj, &target->kobj, "device"); - if (err) - goto err_out_disk_name; - - err = sysfs_create_link(&target->kobj, &disk->kobj, disk_name); - if (err) - goto err_out_dev_link; - } - - err = sysfs_create_link(&disk->kobj, &block_subsys.kobj, - "subsystem"); - if (err) - goto err_out_disk_name_lnk; - - kfree(disk_name); - - return 0; - -err_out_disk_name_lnk: - if (target) { - sysfs_remove_link(&target->kobj, disk_name); -err_out_dev_link: - sysfs_remove_link(&disk->kobj, "device"); -err_out_disk_name: - kfree(disk_name); -err_out: - put_device(target); - } - return err; + /* suppress uevent if the disk supresses it */ + if (!disk->dev.uevent_suppress) + kobject_uevent(&p->dev.kobj, KOBJ_ADD); } /* Not exported, helper to add_disk(). */ @@ -479,19 +374,29 @@ void register_disk(struct gendisk *disk) struct hd_struct *p; int err; - kobject_set_name(&disk->kobj, "%s", disk->disk_name); - /* ewww... some of these buggers have / in name... */ - s = strchr(disk->kobj.k_name, '/'); + 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); + /* ewww... some of these buggers have / in the name... */ + s = strchr(disk->dev.bus_id, '/'); if (s) *s = '!'; - if ((err = kobject_add(&disk->kobj))) + + /* delay uevents, until we scanned partition table */ + disk->dev.uevent_suppress = 1; + + if (device_add(&disk->dev)) return; - err = disk_sysfs_symlinks(disk); +#ifndef CONFIG_SYSFS_DEPRECATED + err = sysfs_create_link(block_depr, &disk->dev.kobj, + kobject_name(&disk->dev.kobj)); if (err) { - kobject_del(&disk->kobj); + device_del(&disk->dev); return; } - disk_sysfs_add_subdirs(disk); +#endif + disk_sysfs_add_subdirs(disk); /* No minors to use for partitions */ if (disk->minors == 1) @@ -505,25 +410,23 @@ void register_disk(struct gendisk *disk) if (!bdev) goto exit; - /* scan partition table, but suppress uevents */ bdev->bd_invalidated = 1; - disk->part_uevent_suppress = 1; err = blkdev_get(bdev, FMODE_READ, 0); - disk->part_uevent_suppress = 0; if (err < 0) goto exit; blkdev_put(bdev); exit: - /* announce disk after possible partitions are already created */ - kobject_uevent(&disk->kobj, KOBJ_ADD); + /* announce disk after possible partitions are created */ + disk->dev.uevent_suppress = 0; + kobject_uevent(&disk->dev.kobj, KOBJ_ADD); /* announce possible partitions */ for (i = 1; i < disk->minors; i++) { p = disk->part[i-1]; if (!p || !p->nr_sects) continue; - kobject_uevent(&p->kobj, KOBJ_ADD); + kobject_uevent(&p->dev.kobj, KOBJ_ADD); } } @@ -602,19 +505,11 @@ void del_gendisk(struct gendisk *disk) disk_stat_set_all(disk, 0); disk->stamp = 0; - kobject_uevent(&disk->kobj, KOBJ_REMOVE); - kobject_unregister(disk->holder_dir); - kobject_unregister(disk->slave_dir); - if (disk->driverfs_dev) { - char *disk_name = make_block_name(disk); - sysfs_remove_link(&disk->kobj, "device"); - if (disk_name) { - sysfs_remove_link(&disk->driverfs_dev->kobj, disk_name); - kfree(disk_name); - } - put_device(disk->driverfs_dev); - disk->driverfs_dev = NULL; - } - sysfs_remove_link(&disk->kobj, "subsystem"); - kobject_del(&disk->kobj); + kobject_put(disk->holder_dir); + kobject_put(disk->slave_dir); + disk->driverfs_dev = NULL; +#ifndef CONFIG_SYSFS_DEPRECATED + sysfs_remove_link(block_depr, disk->dev.bus_id); +#endif + device_del(&disk->dev); } diff --git a/fs/proc/array.c b/fs/proc/array.c index eba339ecba2..eb97f2897e2 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -169,7 +169,7 @@ static inline char *task_state(struct task_struct *p, char *buffer) ppid = pid_alive(p) ? task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0; tpid = pid_alive(p) && p->ptrace ? - task_ppid_nr_ns(rcu_dereference(p->parent), ns) : 0; + task_pid_nr_ns(rcu_dereference(p->parent), ns) : 0; buffer += sprintf(buffer, "State:\t%s\n" "Tgid:\t%d\n" @@ -374,7 +374,9 @@ static cputime_t task_stime(struct task_struct *p) stime = nsec_to_clock_t(p->se.sum_exec_runtime) - cputime_to_clock_t(task_utime(p)); - p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime)); + if (stime >= 0) + p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime)); + return p->prev_stime; } #endif @@ -462,8 +464,8 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole) } sid = task_session_nr_ns(task, ns); + ppid = task_tgid_nr_ns(task->real_parent, ns); pgid = task_pgrp_nr_ns(task, ns); - ppid = task_ppid_nr_ns(task, ns); unlock_task_sighand(task, &flags); } diff --git a/fs/proc/base.c b/fs/proc/base.c index a17c2685907..7411bfb0b7c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -202,6 +202,26 @@ static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vf (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \ security_ptrace(current,task) == 0)) +struct mm_struct *mm_for_maps(struct task_struct *task) +{ + struct mm_struct *mm = get_task_mm(task); + if (!mm) + return NULL; + down_read(&mm->mmap_sem); + task_lock(task); + if (task->mm != mm) + goto out; + if (task->mm != current->mm && __ptrace_may_attach(task) < 0) + goto out; + task_unlock(task); + return mm; +out: + task_unlock(task); + up_read(&mm->mmap_sem); + mmput(mm); + return NULL; +} + static int proc_pid_cmdline(struct task_struct *task, char * buffer) { int res = 0; @@ -2411,19 +2431,23 @@ out: * Find the first task with tgid >= tgid * */ -static struct task_struct *next_tgid(unsigned int tgid, - struct pid_namespace *ns) -{ +struct tgid_iter { + unsigned int tgid; struct task_struct *task; +}; +static struct tgid_iter next_tgid(struct pid_namespace *ns, struct tgid_iter iter) +{ struct pid *pid; + if (iter.task) + put_task_struct(iter.task); rcu_read_lock(); retry: - task = NULL; - pid = find_ge_pid(tgid, ns); + iter.task = NULL; + pid = find_ge_pid(iter.tgid, ns); if (pid) { - tgid = pid_nr_ns(pid, ns) + 1; - task = pid_task(pid, PIDTYPE_PID); + iter.tgid = pid_nr_ns(pid, ns); + iter.task = pid_task(pid, PIDTYPE_PID); /* What we to know is if the pid we have find is the * pid of a thread_group_leader. Testing for task * being a thread_group_leader is the obvious thing @@ -2436,23 +2460,25 @@ retry: * found doesn't happen to be a thread group leader. * As we don't care in the case of readdir. */ - if (!task || !has_group_leader_pid(task)) + if (!iter.task || !has_group_leader_pid(iter.task)) { + iter.tgid += 1; goto retry; - get_task_struct(task); + } + get_task_struct(iter.task); } rcu_read_unlock(); - return task; + return iter; } #define TGID_OFFSET (FIRST_PROCESS_ENTRY + ARRAY_SIZE(proc_base_stuff)) static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldir, - struct task_struct *task, int tgid) + struct tgid_iter iter) { char name[PROC_NUMBUF]; - int len = snprintf(name, sizeof(name), "%d", tgid); + int len = snprintf(name, sizeof(name), "%d", iter.tgid); return proc_fill_cache(filp, dirent, filldir, name, len, - proc_pid_instantiate, task, NULL); + proc_pid_instantiate, iter.task, NULL); } /* for the /proc/ directory itself, after non-process stuff has been done */ @@ -2460,8 +2486,7 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) { unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY; struct task_struct *reaper = get_proc_task(filp->f_path.dentry->d_inode); - struct task_struct *task; - int tgid; + struct tgid_iter iter; struct pid_namespace *ns; if (!reaper) @@ -2474,14 +2499,14 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) } ns = filp->f_dentry->d_sb->s_fs_info; - tgid = filp->f_pos - TGID_OFFSET; - for (task = next_tgid(tgid, ns); - task; - put_task_struct(task), task = next_tgid(tgid + 1, ns)) { - tgid = task_pid_nr_ns(task, ns); - filp->f_pos = tgid + TGID_OFFSET; - if (proc_pid_fill_cache(filp, dirent, filldir, task, tgid) < 0) { - put_task_struct(task); + iter.task = NULL; + iter.tgid = filp->f_pos - TGID_OFFSET; + for (iter = next_tgid(ns, iter); + iter.task; + iter.tgid += 1, iter = next_tgid(ns, iter)) { + filp->f_pos = iter.tgid + TGID_OFFSET; + if (proc_pid_fill_cache(filp, dirent, filldir, iter) < 0) { + put_task_struct(iter.task); goto out; } } diff --git a/fs/proc/generic.c b/fs/proc/generic.c index a9806bc21ec..6a2fe5187b6 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -397,8 +397,11 @@ struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nam if (de->namelen != dentry->d_name.len) continue; if (!memcmp(dentry->d_name.name, de->name, de->namelen)) { - unsigned int ino = de->low_ino; + unsigned int ino; + if (de->shadow_proc) + de = de->shadow_proc(current, de); + ino = de->low_ino; de_get(de); spin_unlock(&proc_subdir_lock); error = -EINVAL; @@ -555,41 +558,6 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp return 0; } -/* - * Kill an inode that got unregistered.. - */ -static void proc_kill_inodes(struct proc_dir_entry *de) -{ - struct list_head *p; - struct super_block *sb; - - /* - * Actually it's a partial revoke(). - */ - spin_lock(&sb_lock); - list_for_each_entry(sb, &proc_fs_type.fs_supers, s_instances) { - file_list_lock(); - list_for_each(p, &sb->s_files) { - struct file *filp = list_entry(p, struct file, - f_u.fu_list); - struct dentry *dentry = filp->f_path.dentry; - struct inode *inode; - const struct file_operations *fops; - - if (dentry->d_op != &proc_dentry_operations) - continue; - inode = dentry->d_inode; - if (PDE(inode) != de) - continue; - fops = filp->f_op; - filp->f_op = NULL; - fops_put(fops); - } - file_list_unlock(); - } - spin_unlock(&sb_lock); -} - static struct proc_dir_entry *proc_create(struct proc_dir_entry **parent, const char *name, mode_t mode, @@ -620,6 +588,7 @@ static struct proc_dir_entry *proc_create(struct proc_dir_entry **parent, ent->namelen = len; ent->mode = mode; ent->nlink = nlink; + atomic_set(&ent->count, 1); ent->pde_users = 0; spin_lock_init(&ent->pde_unload_lock); ent->pde_unload_completion = NULL; @@ -717,7 +686,6 @@ void free_proc_entry(struct proc_dir_entry *de) /* * Remove a /proc entry and free it if it's not currently in use. - * If it is in use, we set the 'deleted' flag. */ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) { @@ -764,17 +732,10 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) continue_removing: if (S_ISDIR(de->mode)) parent->nlink--; - if (!S_ISREG(de->mode)) - proc_kill_inodes(de); de->nlink = 0; WARN_ON(de->subdir); - if (!atomic_read(&de->count)) + if (atomic_dec_and_test(&de->count)) free_proc_entry(de); - else { - de->deleted = 1; - printk("remove_proc_entry: %s/%s busy, count=%d\n", - parent->name, de->name, atomic_read(&de->count)); - } break; } spin_unlock(&proc_subdir_lock); diff --git a/fs/proc/inode.c b/fs/proc/inode.c index abe6a3f0436..1a551d92e1d 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -43,13 +43,8 @@ void de_put(struct proc_dir_entry *de) return; } - if (atomic_dec_and_test(&de->count)) { - if (de->deleted) { - printk("de_put: deferred delete of %s\n", - de->name); - free_proc_entry(de); - } - } + if (atomic_dec_and_test(&de->count)) + free_proc_entry(de); unlock_kernel(); } } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 1b2b6c6bb47..05b3e900626 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -27,6 +27,8 @@ struct vmalloc_info { unsigned long largest_chunk; }; +extern struct mm_struct *mm_for_maps(struct task_struct *); + #ifdef CONFIG_MMU #define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) extern void get_vmalloc_info(struct vmalloc_info *vmi); @@ -78,5 +80,3 @@ static inline int proc_fd(struct inode *inode) { return PROC_I(inode)->fd; } - -extern struct file_system_type proc_fs_type; diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index e0d064e9764..3462bfde89f 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -410,7 +410,7 @@ static const struct file_operations proc_modules_operations = { }; #endif -#ifdef CONFIG_SLAB +#ifdef CONFIG_SLABINFO static int slabinfo_open(struct inode *inode, struct file *file) { return seq_open(file, &slabinfo_op); @@ -728,7 +728,7 @@ void __init proc_misc_init(void) #endif create_seq_entry("stat", 0, &proc_stat_operations); create_seq_entry("interrupts", 0, &proc_interrupts_operations); -#ifdef CONFIG_SLAB +#ifdef CONFIG_SLABINFO create_seq_entry("slabinfo",S_IWUSR|S_IRUGO,&proc_slabinfo_operations); #ifdef CONFIG_DEBUG_SLAB_LEAK create_seq_entry("slab_allocators", 0 ,&proc_slabstats_operations); diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 131f9c68be5..0afe21ee060 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -50,89 +50,14 @@ struct net *get_proc_net(const struct inode *inode) } EXPORT_SYMBOL_GPL(get_proc_net); -static struct proc_dir_entry *proc_net_shadow; +static struct proc_dir_entry *shadow_pde; -static struct dentry *proc_net_shadow_dentry(struct dentry *parent, +static struct proc_dir_entry *proc_net_shadow(struct task_struct *task, struct proc_dir_entry *de) { - struct dentry *shadow = NULL; - struct inode *inode; - if (!de) - goto out; - de_get(de); - inode = proc_get_inode(parent->d_inode->i_sb, de->low_ino, de); - if (!inode) - goto out_de_put; - shadow = d_alloc_name(parent, de->name); - if (!shadow) - goto out_iput; - shadow->d_op = parent->d_op; /* proc_dentry_operations */ - d_instantiate(shadow, inode); -out: - return shadow; -out_iput: - iput(inode); -out_de_put: - de_put(de); - goto out; -} - -static void *proc_net_follow_link(struct dentry *parent, struct nameidata *nd) -{ - struct net *net = current->nsproxy->net_ns; - struct dentry *shadow; - shadow = proc_net_shadow_dentry(parent, net->proc_net); - if (!shadow) - return ERR_PTR(-ENOENT); - - dput(nd->dentry); - /* My dentry count is 1 and that should be enough as the - * shadow dentry is thrown away immediately. - */ - nd->dentry = shadow; - return NULL; + return task->nsproxy->net_ns->proc_net; } -static struct dentry *proc_net_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) -{ - struct net *net = current->nsproxy->net_ns; - struct dentry *shadow; - - shadow = proc_net_shadow_dentry(nd->dentry, net->proc_net); - if (!shadow) - return ERR_PTR(-ENOENT); - - dput(nd->dentry); - nd->dentry = shadow; - - return shadow->d_inode->i_op->lookup(shadow->d_inode, dentry, nd); -} - -static int proc_net_setattr(struct dentry *dentry, struct iattr *iattr) -{ - struct net *net = current->nsproxy->net_ns; - struct dentry *shadow; - int ret; - - shadow = proc_net_shadow_dentry(dentry->d_parent, net->proc_net); - if (!shadow) - return -ENOENT; - ret = shadow->d_inode->i_op->setattr(shadow, iattr); - dput(shadow); - return ret; -} - -static const struct file_operations proc_net_dir_operations = { - .read = generic_read_dir, -}; - -static struct inode_operations proc_net_dir_inode_operations = { - .follow_link = proc_net_follow_link, - .lookup = proc_net_lookup, - .setattr = proc_net_setattr, -}; - static __net_init int proc_net_ns_init(struct net *net) { struct proc_dir_entry *root, *netd, *net_statd; @@ -185,9 +110,8 @@ static struct pernet_operations __net_initdata proc_net_ns_ops = { int __init proc_net_init(void) { - proc_net_shadow = proc_mkdir("net", NULL); - proc_net_shadow->proc_iops = &proc_net_dir_inode_operations; - proc_net_shadow->proc_fops = &proc_net_dir_operations; + shadow_pde = proc_mkdir("net", NULL); + shadow_pde->shadow_proc = proc_net_shadow; return register_pernet_subsys(&proc_net_ns_ops); } diff --git a/fs/proc/root.c b/fs/proc/root.c index 1f86bb860e0..81f99e691f9 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -98,7 +98,7 @@ static void proc_kill_sb(struct super_block *sb) put_pid_ns(ns); } -struct file_system_type proc_fs_type = { +static struct file_system_type proc_fs_type = { .name = "proc", .get_sb = proc_get_sb, .kill_sb = proc_kill_sb, @@ -207,6 +207,7 @@ struct proc_dir_entry proc_root = { .name = "/proc", .mode = S_IFDIR | S_IRUGO | S_IXUGO, .nlink = 2, + .count = ATOMIC_INIT(1), .proc_iops = &proc_root_inode_operations, .proc_fops = &proc_root_operations, .parent = &proc_root, diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index c24d81a5a04..8043a3eab52 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -397,12 +397,11 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (!priv->task) return NULL; - mm = get_task_mm(priv->task); + mm = mm_for_maps(priv->task); if (!mm) return NULL; priv->tail_vma = tail_vma = get_gate_vma(priv->task); - down_read(&mm->mmap_sem); /* Start with last addr hint */ if (last_addr && (vma = find_vma(mm, last_addr))) { diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index d8b8c7183c2..1932c2ca345 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -165,15 +165,13 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (!priv->task) return NULL; - mm = get_task_mm(priv->task); + mm = mm_for_maps(priv->task); if (!mm) { put_task_struct(priv->task); priv->task = NULL; return NULL; } - down_read(&mm->mmap_sem); - /* start from the Nth VMA */ for (vml = mm->context.vmlist; vml; vml = vml->next) if (n-- == 0) diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c index 9aa7a06e093..00114462167 100644 --- a/fs/reiserfs/procfs.c +++ b/fs/reiserfs/procfs.c @@ -420,12 +420,6 @@ static void *r_start(struct seq_file *m, loff_t * pos) return NULL; up_write(&s->s_umount); - - if (de->deleted) { - deactivate_super(s); - return NULL; - } - return s; } diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 337162935d2..4948d9bc405 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -440,7 +440,7 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) /** * sysfs_remove_one - remove sysfs_dirent from parent * @acxt: addrm context to use - * @sd: sysfs_dirent to be added + * @sd: sysfs_dirent to be removed * * Mark @sd removed and drop nlink of parent inode if @sd is a * directory. @sd is unlinked from the children list. @@ -678,8 +678,10 @@ static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, sd = sysfs_find_dirent(parent_sd, dentry->d_name.name); /* no such entry */ - if (!sd) + if (!sd) { + ret = ERR_PTR(-ENOENT); goto out_unlock; + } /* attach dentry and inode */ inode = sysfs_get_inode(sd); @@ -781,6 +783,7 @@ int sysfs_rename_dir(struct kobject * kobj, const char *new_name) old_dentry = sysfs_get_dentry(sd); if (IS_ERR(old_dentry)) { error = PTR_ERR(old_dentry); + old_dentry = NULL; goto out; } @@ -848,6 +851,7 @@ int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj) old_dentry = sysfs_get_dentry(sd); if (IS_ERR(old_dentry)) { error = PTR_ERR(old_dentry); + old_dentry = NULL; goto out; } old_parent = old_dentry->d_parent; @@ -855,6 +859,7 @@ int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj) new_parent = sysfs_get_dentry(new_parent_sd); if (IS_ERR(new_parent)) { error = PTR_ERR(new_parent); + new_parent = NULL; goto out; } @@ -878,7 +883,6 @@ again: error = 0; d_add(new_dentry, NULL); d_move(old_dentry, new_dentry); - dput(new_dentry); /* Remove from old parent's list and insert into new parent's list. */ sysfs_unlink_sibling(sd); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 27d1785b764..8acf82bba44 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -20,43 +20,6 @@ #include "sysfs.h" -#define to_sattr(a) container_of(a,struct subsys_attribute, attr) - -/* - * Subsystem file operations. - * These operations allow subsystems to have files that can be - * read/written. - */ -static ssize_t -subsys_attr_show(struct kobject * kobj, struct attribute * attr, char * page) -{ - struct kset *kset = to_kset(kobj); - struct subsys_attribute * sattr = to_sattr(attr); - ssize_t ret = -EIO; - - if (sattr->show) - ret = sattr->show(kset, page); - return ret; -} - -static ssize_t -subsys_attr_store(struct kobject * kobj, struct attribute * attr, - const char * page, size_t count) -{ - struct kset *kset = to_kset(kobj); - struct subsys_attribute * sattr = to_sattr(attr); - ssize_t ret = -EIO; - - if (sattr->store) - ret = sattr->store(kset, page, count); - return ret; -} - -static struct sysfs_ops subsys_sysfs_ops = { - .show = subsys_attr_show, - .store = subsys_attr_store, -}; - /* * There's one sysfs_buffer for each open file and one * sysfs_open_dirent for each sysfs_dirent with one or more open @@ -66,7 +29,7 @@ static struct sysfs_ops subsys_sysfs_ops = { * sysfs_dirent->s_attr.open points to sysfs_open_dirent. s_attr.open * is protected by sysfs_open_dirent_lock. */ -static spinlock_t sysfs_open_dirent_lock = SPIN_LOCK_UNLOCKED; +static DEFINE_SPINLOCK(sysfs_open_dirent_lock); struct sysfs_open_dirent { atomic_t refcnt; @@ -119,7 +82,11 @@ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer sysfs_put_active_two(attr_sd); - BUG_ON(count > (ssize_t)PAGE_SIZE); + /* + * The code works fine with PAGE_SIZE return but it's likely to + * indicate truncated result or overflow in normal use cases. + */ + BUG_ON(count >= (ssize_t)PAGE_SIZE); if (count >= 0) { buffer->needs_read_fill = 0; buffer->count = count; @@ -350,31 +317,23 @@ static int sysfs_open_file(struct inode *inode, struct file *file) { struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - struct sysfs_buffer * buffer; - struct sysfs_ops * ops = NULL; - int error; + struct sysfs_buffer *buffer; + struct sysfs_ops *ops; + int error = -EACCES; /* need attr_sd for attr and ops, its parent for kobj */ if (!sysfs_get_active_two(attr_sd)) return -ENODEV; - /* if the kobject has no ktype, then we assume that it is a subsystem - * itself, and use ops for it. - */ - if (kobj->kset && kobj->kset->ktype) - ops = kobj->kset->ktype->sysfs_ops; - else if (kobj->ktype) + /* every kobject with an attribute needs a ktype assigned */ + if (kobj->ktype && kobj->ktype->sysfs_ops) ops = kobj->ktype->sysfs_ops; - else - ops = &subsys_sysfs_ops; - - error = -EACCES; - - /* No sysfs operations, either from having no subsystem, - * or the subsystem have no operations. - */ - if (!ops) + else { + printk(KERN_ERR "missing sysfs attribute operations for " + "kobject: %s\n", kobject_name(kobj)); + WARN_ON(1); goto err_out; + } /* File needs write support. * The inode's perms must say it's ok, diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index 3eac20c63c4..5f66c446615 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -19,39 +19,6 @@ #include "sysfs.h" -static int object_depth(struct sysfs_dirent *sd) -{ - int depth = 0; - - for (; sd->s_parent; sd = sd->s_parent) - depth++; - - return depth; -} - -static int object_path_length(struct sysfs_dirent * sd) -{ - int length = 1; - - for (; sd->s_parent; sd = sd->s_parent) - length += strlen(sd->s_name) + 1; - - return length; -} - -static void fill_object_path(struct sysfs_dirent *sd, char *buffer, int length) -{ - --length; - for (; sd->s_parent; sd = sd->s_parent) { - int cur = strlen(sd->s_name); - - /* back up enough to print this bus id with '/' */ - length -= cur; - strncpy(buffer + length, sd->s_name, cur); - *(buffer + --length) = '/'; - } -} - /** * sysfs_create_link - create symlink between two objects. * @kobj: object whose directory we're creating the link in. @@ -112,7 +79,6 @@ int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char return error; } - /** * sysfs_remove_link - remove symlink in object's directory. * @kobj: object we're acting for. @@ -124,24 +90,54 @@ void sysfs_remove_link(struct kobject * kobj, const char * name) sysfs_hash_and_remove(kobj->sd, name); } -static int sysfs_get_target_path(struct sysfs_dirent * parent_sd, - struct sysfs_dirent * target_sd, char *path) +static int sysfs_get_target_path(struct sysfs_dirent *parent_sd, + struct sysfs_dirent *target_sd, char *path) { - char * s; - int depth, size; + struct sysfs_dirent *base, *sd; + char *s = path; + int len = 0; + + /* go up to the root, stop at the base */ + base = parent_sd; + while (base->s_parent) { + sd = target_sd->s_parent; + while (sd->s_parent && base != sd) + sd = sd->s_parent; + + if (base == sd) + break; + + strcpy(s, "../"); + s += 3; + base = base->s_parent; + } + + /* determine end of target string for reverse fillup */ + sd = target_sd; + while (sd->s_parent && sd != base) { + len += strlen(sd->s_name) + 1; + sd = sd->s_parent; + } - depth = object_depth(parent_sd); - size = object_path_length(target_sd) + depth * 3 - 1; - if (size > PATH_MAX) + /* check limits */ + if (len < 2) + return -EINVAL; + len--; + if ((s - path) + len > PATH_MAX) return -ENAMETOOLONG; - pr_debug("%s: depth = %d, size = %d\n", __FUNCTION__, depth, size); + /* reverse fillup of target string from target to base */ + sd = target_sd; + while (sd->s_parent && sd != base) { + int slen = strlen(sd->s_name); - for (s = path; depth--; s += 3) - strcpy(s,"../"); + len -= slen; + strncpy(s + len, sd->s_name, slen); + if (len) + s[--len] = '/'; - fill_object_path(target_sd, path, size); - pr_debug("%s: path = '%s'\n", __FUNCTION__, path); + sd = sd->s_parent; + } return 0; } diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index 30f8c2bb0c3..aaf2878305c 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -179,7 +179,7 @@ bad_entry: goto fail; Eend: p = (struct ufs_dir_entry *)(kaddr + offs); - ufs_error (sb, "ext2_check_page", + ufs_error(sb, __FUNCTION__, "entry in directory #%lu spans the page boundary" "offset=%lu", dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs); diff --git a/fs/ufs/super.c b/fs/ufs/super.c index c78c04fd993..0072cb33ebe 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -755,13 +755,13 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) break; case UFS_MOUNT_UFSTYPE_NEXTSTEP: - /*TODO: check may be we need set special dir block size?*/ UFSD("ufstype=nextstep\n"); uspi->s_fsize = block_size = 1024; uspi->s_fmask = ~(1024 - 1); uspi->s_fshift = 10; uspi->s_sbsize = super_block_size = 2048; uspi->s_sbbase = 0; + uspi->s_dirblksize = 1024; flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD; if (!(sb->s_flags & MS_RDONLY)) { if (!silent) @@ -771,13 +771,13 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) break; case UFS_MOUNT_UFSTYPE_NEXTSTEP_CD: - /*TODO: check may be we need set special dir block size?*/ UFSD("ufstype=nextstep-cd\n"); uspi->s_fsize = block_size = 2048; uspi->s_fmask = ~(2048 - 1); uspi->s_fshift = 11; uspi->s_sbsize = super_block_size = 2048; uspi->s_sbbase = 0; + uspi->s_dirblksize = 1024; flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD; if (!(sb->s_flags & MS_RDONLY)) { if (!silent) diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index b9c8589e05c..a49dd8d4b06 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -725,15 +725,15 @@ xfs_buf_associate_memory( { int rval; int i = 0; - size_t ptr; - size_t end, end_cur; - off_t offset; + unsigned long pageaddr; + unsigned long offset; + size_t buflen; int page_count; - page_count = PAGE_CACHE_ALIGN(len) >> PAGE_CACHE_SHIFT; - offset = (off_t) mem - ((off_t)mem & PAGE_CACHE_MASK); - if (offset && (len > PAGE_CACHE_SIZE)) - page_count++; + pageaddr = (unsigned long)mem & PAGE_CACHE_MASK; + offset = (unsigned long)mem - pageaddr; + buflen = PAGE_CACHE_ALIGN(len + offset); + page_count = buflen >> PAGE_CACHE_SHIFT; /* Free any previous set of page pointers */ if (bp->b_pages) @@ -747,22 +747,15 @@ xfs_buf_associate_memory( return rval; bp->b_offset = offset; - ptr = (size_t) mem & PAGE_CACHE_MASK; - end = PAGE_CACHE_ALIGN((size_t) mem + len); - end_cur = end; - /* set up first page */ - bp->b_pages[0] = mem_to_page(mem); - - ptr += PAGE_CACHE_SIZE; - bp->b_page_count = ++i; - while (ptr < end) { - bp->b_pages[i] = mem_to_page((void *)ptr); - bp->b_page_count = ++i; - ptr += PAGE_CACHE_SIZE; + + for (i = 0; i < bp->b_page_count; i++) { + bp->b_pages[i] = mem_to_page((void *)pageaddr); + pageaddr += PAGE_CACHE_SIZE; } bp->b_locked = 0; - bp->b_count_desired = bp->b_buffer_length = len; + bp->b_count_desired = len; + bp->b_buffer_length = buflen; bp->b_flags |= XBF_MAPPED; return 0; @@ -1032,7 +1025,7 @@ xfs_buf_ioend( xfs_buf_t *bp, int schedule) { - bp->b_flags &= ~(XBF_READ | XBF_WRITE); + bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD); if (bp->b_error == 0) bp->b_flags |= XBF_DONE; @@ -1750,6 +1743,8 @@ xfsbufd( current->flags |= PF_MEMALLOC; + set_freezable(); + do { if (unlikely(freezing(current))) { set_bit(XBT_FORCE_SLEEP, &target->bt_flags); diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index fb8dd34041e..21a1c2b1c5f 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -218,6 +218,15 @@ xfs_vm_fault( } #endif /* CONFIG_XFS_DMAPI */ +/* + * Unfortunately we can't just use the clean and simple readdir implementation + * below, because nfs might call back into ->lookup from the filldir callback + * and that will deadlock the low-level btree code. + * + * Hopefully we'll find a better workaround that allows to use the optimal + * version at least for local readdirs for 2.6.25. + */ +#if 0 STATIC int xfs_file_readdir( struct file *filp, @@ -249,6 +258,126 @@ xfs_file_readdir( return -error; return 0; } +#else + +struct hack_dirent { + u64 ino; + loff_t offset; + int namlen; + unsigned int d_type; + char name[]; +}; + +struct hack_callback { + char *dirent; + size_t len; + size_t used; +}; + +STATIC int +xfs_hack_filldir( + void *__buf, + const char *name, + int namlen, + loff_t offset, + u64 ino, + unsigned int d_type) +{ + struct hack_callback *buf = __buf; + struct hack_dirent *de = (struct hack_dirent *)(buf->dirent + buf->used); + unsigned int reclen; + + reclen = ALIGN(sizeof(struct hack_dirent) + namlen, sizeof(u64)); + if (buf->used + reclen > buf->len) + return -EINVAL; + + de->namlen = namlen; + de->offset = offset; + de->ino = ino; + de->d_type = d_type; + memcpy(de->name, name, namlen); + buf->used += reclen; + return 0; +} + +STATIC int +xfs_file_readdir( + struct file *filp, + void *dirent, + filldir_t filldir) +{ + struct inode *inode = filp->f_path.dentry->d_inode; + xfs_inode_t *ip = XFS_I(inode); + struct hack_callback buf; + struct hack_dirent *de; + int error; + loff_t size; + int eof = 0; + xfs_off_t start_offset, curr_offset, offset; + + /* + * Try fairly hard to get memory + */ + buf.len = PAGE_CACHE_SIZE; + do { + buf.dirent = kmalloc(buf.len, GFP_KERNEL); + if (buf.dirent) + break; + buf.len >>= 1; + } while (buf.len >= 1024); + + if (!buf.dirent) + return -ENOMEM; + + curr_offset = filp->f_pos; + if (curr_offset == 0x7fffffff) + offset = 0xffffffff; + else + offset = filp->f_pos; + + while (!eof) { + unsigned int reclen; + + start_offset = offset; + + buf.used = 0; + error = -xfs_readdir(ip, &buf, buf.len, &offset, + xfs_hack_filldir); + if (error || offset == start_offset) { + size = 0; + break; + } + + size = buf.used; + de = (struct hack_dirent *)buf.dirent; + curr_offset = de->offset /* & 0x7fffffff */; + while (size > 0) { + if (filldir(dirent, de->name, de->namlen, + curr_offset & 0x7fffffff, + de->ino, de->d_type)) { + goto done; + } + + reclen = ALIGN(sizeof(struct hack_dirent) + de->namlen, + sizeof(u64)); + size -= reclen; + de = (struct hack_dirent *)((char *)de + reclen); + curr_offset = de->offset /* & 0x7fffffff */; + } + } + + done: + if (!error) { + if (size == 0) + filp->f_pos = offset & 0x7fffffff; + else if (de) + filp->f_pos = curr_offset; + } + + kfree(buf.dirent); + return error; +} +#endif STATIC int xfs_file_mmap( diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c index 2b34bad48b0..98a56568bb2 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -1047,24 +1047,20 @@ xfs_ioc_bulkstat( if ((count = bulkreq.icount) <= 0) return -XFS_ERROR(EINVAL); + if (bulkreq.ubuffer == NULL) + return -XFS_ERROR(EINVAL); + if (cmd == XFS_IOC_FSINUMBERS) error = xfs_inumbers(mp, &inlast, &count, bulkreq.ubuffer, xfs_inumbers_fmt); else if (cmd == XFS_IOC_FSBULKSTAT_SINGLE) error = xfs_bulkstat_single(mp, &inlast, bulkreq.ubuffer, &done); - else { /* XFS_IOC_FSBULKSTAT */ - if (count == 1 && inlast != 0) { - inlast++; - error = xfs_bulkstat_single(mp, &inlast, - bulkreq.ubuffer, &done); - } else { - error = xfs_bulkstat(mp, &inlast, &count, - (bulkstat_one_pf)xfs_bulkstat_one, NULL, - sizeof(xfs_bstat_t), bulkreq.ubuffer, - BULKSTAT_FG_QUICK, &done); - } - } + else /* XFS_IOC_FSBULKSTAT */ + error = xfs_bulkstat(mp, &inlast, &count, + (bulkstat_one_pf)xfs_bulkstat_one, NULL, + sizeof(xfs_bstat_t), bulkreq.ubuffer, + BULKSTAT_FG_QUICK, &done); if (error) return -error; diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c index 0046bdd5b7f..bf2a956b63c 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl32.c +++ b/fs/xfs/linux-2.6/xfs_ioctl32.c @@ -291,6 +291,9 @@ xfs_ioc_bulkstat_compat( if ((count = bulkreq.icount) <= 0) return -XFS_ERROR(EINVAL); + if (bulkreq.ubuffer == NULL) + return -XFS_ERROR(EINVAL); + if (cmd == XFS_IOC_FSINUMBERS) error = xfs_inumbers(mp, &inlast, &count, bulkreq.ubuffer, xfs_inumbers_fmt_compat); diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index ac50f8a3758..5e8bb7f71b5 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -117,7 +117,7 @@ xfs_ichgtime( */ SYNCHRONIZE(); ip->i_update_core = 1; - if (!(inode->i_state & I_SYNC)) + if (!(inode->i_state & I_NEW)) mark_inode_dirty_sync(inode); } @@ -169,7 +169,7 @@ xfs_ichgtime_fast( */ SYNCHRONIZE(); ip->i_update_core = 1; - if (!(inode->i_state & I_SYNC)) + if (!(inode->i_state & I_NEW)) mark_inode_dirty_sync(inode); } @@ -332,9 +332,7 @@ xfs_vn_mknod( ASSERT(vp); ip = vn_to_inode(vp); - if (S_ISCHR(mode) || S_ISBLK(mode)) - ip->i_rdev = rdev; - else if (S_ISDIR(mode)) + if (S_ISDIR(mode)) xfs_validate_fields(ip); d_instantiate(dentry, ip); xfs_validate_fields(dir); diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c index b5f91281b70..d488645f833 100644 --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -1008,6 +1008,9 @@ xfs_qm_sync( boolean_t nowait; int error; + if (! XFS_IS_QUOTA_ON(mp)) + return 0; + restarts = 0; /* * We won't block unless we are asked to. diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c index c171767e242..a5f4f4fb886 100644 --- a/fs/xfs/xfs_dir2_block.c +++ b/fs/xfs/xfs_dir2_block.c @@ -508,7 +508,7 @@ xfs_dir2_block_getdents( continue; cook = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk, - ptr - (char *)block); + (char *)dep - (char *)block); ino = be64_to_cpu(dep->inumber); #if XFS_BIG_INUMS ino += mp->m_inoadd; @@ -519,9 +519,7 @@ xfs_dir2_block_getdents( */ if (filldir(dirent, dep->name, dep->namelen, cook, ino, DT_UNKNOWN)) { - *offset = xfs_dir2_db_off_to_dataptr(mp, - mp->m_dirdatablk, - (char *)dep - (char *)block); + *offset = cook; xfs_da_brelse(NULL, bp); return 0; } diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c index e7c12fa1303..0ca0020ba09 100644 --- a/fs/xfs/xfs_dir2_leaf.c +++ b/fs/xfs/xfs_dir2_leaf.c @@ -1091,7 +1091,7 @@ xfs_dir2_leaf_getdents( * Won't fit. Return to caller. */ if (filldir(dirent, dep->name, dep->namelen, - xfs_dir2_byte_to_dataptr(mp, curoff + length), + xfs_dir2_byte_to_dataptr(mp, curoff), ino, DT_UNKNOWN)) break; diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c index 182c70315ad..919d275a1ce 100644 --- a/fs/xfs/xfs_dir2_sf.c +++ b/fs/xfs/xfs_dir2_sf.c @@ -752,7 +752,7 @@ xfs_dir2_sf_getdents( #if XFS_BIG_INUMS ino += mp->m_inoadd; #endif - if (filldir(dirent, ".", 1, dotdot_offset, ino, DT_DIR)) { + if (filldir(dirent, ".", 1, dot_offset, ino, DT_DIR)) { *offset = dot_offset; return 0; } @@ -762,13 +762,11 @@ xfs_dir2_sf_getdents( * Put .. entry unless we're starting past it. */ if (*offset <= dotdot_offset) { - off = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk, - XFS_DIR2_DATA_FIRST_OFFSET); ino = xfs_dir2_sf_get_inumber(sfp, &sfp->hdr.parent); #if XFS_BIG_INUMS ino += mp->m_inoadd; #endif - if (filldir(dirent, "..", 2, off, ino, DT_DIR)) { + if (filldir(dirent, "..", 2, dotdot_offset, ino, DT_DIR)) { *offset = dotdot_offset; return 0; } @@ -793,8 +791,7 @@ xfs_dir2_sf_getdents( #endif if (filldir(dirent, sfep->name, sfep->namelen, - off + xfs_dir2_data_entsize(sfep->namelen), - ino, DT_UNKNOWN)) { + off, ino, DT_UNKNOWN)) { *offset = off; return 0; } diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index 488836e204a..fb69ef180b2 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -267,7 +267,7 @@ finish_inode: icl = NULL; if (radix_tree_gang_lookup(&pag->pag_ici_root, (void**)&iq, first_index, 1)) { - if ((iq->i_ino & mask) == first_index) + if ((XFS_INO_TO_AGINO(mp, iq->i_ino) & mask) == first_index) icl = iq->i_cluster; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index abf509a8891..34494808281 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1459,8 +1459,10 @@ xfs_itruncate_start( mp = ip->i_mount; vp = XFS_ITOV(ip); - vn_iowait(ip); /* wait for the completion of any pending DIOs */ - + /* wait for the completion of any pending DIOs */ + if (new_size < ip->i_size) + vn_iowait(ip); + /* * Call toss_pages or flushinval_pages to get rid of pages * overlapping the region being removed. We have to use diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 9972992fd3c..9fc4c288652 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -316,6 +316,8 @@ xfs_bulkstat_use_dinode( return 1; } +#define XFS_BULKSTAT_UBLEFT(ubleft) ((ubleft) >= statstruct_size) + /* * Return stat information in bulk (by-inode) for the filesystem. */ @@ -353,7 +355,7 @@ xfs_bulkstat( xfs_inobt_rec_incore_t *irbp; /* current irec buffer pointer */ xfs_inobt_rec_incore_t *irbuf; /* start of irec buffer */ xfs_inobt_rec_incore_t *irbufend; /* end of good irec buffer entries */ - xfs_ino_t lastino=0; /* last inode number returned */ + xfs_ino_t lastino; /* last inode number returned */ int nbcluster; /* # of blocks in a cluster */ int nicluster; /* # of inodes in a cluster */ int nimask; /* mask for inode clusters */ @@ -373,6 +375,7 @@ xfs_bulkstat( * Get the last inode value, see if there's nothing to do. */ ino = (xfs_ino_t)*lastinop; + lastino = ino; dip = NULL; agno = XFS_INO_TO_AGNO(mp, ino); agino = XFS_INO_TO_AGINO(mp, ino); @@ -382,6 +385,9 @@ xfs_bulkstat( *ubcountp = 0; return 0; } + if (!ubcountp || *ubcountp <= 0) { + return EINVAL; + } ubcount = *ubcountp; /* statstruct's */ ubleft = ubcount * statstruct_size; /* bytes */ *ubcountp = ubelem = 0; @@ -402,7 +408,8 @@ xfs_bulkstat( * inode returned; 0 means start of the allocation group. */ rval = 0; - while (ubleft >= statstruct_size && agno < mp->m_sb.sb_agcount) { + while (XFS_BULKSTAT_UBLEFT(ubleft) && agno < mp->m_sb.sb_agcount) { + cond_resched(); bp = NULL; down_read(&mp->m_peraglock); error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp); @@ -499,6 +506,7 @@ xfs_bulkstat( break; error = xfs_inobt_lookup_ge(cur, agino, 0, 0, &tmp); + cond_resched(); } /* * If ran off the end of the ag either with an error, @@ -542,6 +550,7 @@ xfs_bulkstat( */ agino = gino + XFS_INODES_PER_CHUNK; error = xfs_inobt_increment(cur, 0, &tmp); + cond_resched(); } /* * Drop the btree buffers and the agi buffer. @@ -555,12 +564,12 @@ xfs_bulkstat( */ irbufend = irbp; for (irbp = irbuf; - irbp < irbufend && ubleft >= statstruct_size; irbp++) { + irbp < irbufend && XFS_BULKSTAT_UBLEFT(ubleft); irbp++) { /* * Now process this chunk of inodes. */ for (agino = irbp->ir_startino, chunkidx = clustidx = 0; - ubleft > 0 && + XFS_BULKSTAT_UBLEFT(ubleft) && irbp->ir_freecount < XFS_INODES_PER_CHUNK; chunkidx++, clustidx++, agino++) { ASSERT(chunkidx < XFS_INODES_PER_CHUNK); @@ -663,15 +672,13 @@ xfs_bulkstat( ubleft, private_data, bno, &ubused, dip, &fmterror); if (fmterror == BULKSTAT_RV_NOTHING) { - if (error == EFAULT) { - ubleft = 0; - rval = error; - break; - } - else if (error == ENOMEM) + if (error && error != ENOENT && + error != EINVAL) { ubleft = 0; - else - lastino = ino; + rval = error; + break; + } + lastino = ino; continue; } if (fmterror == BULKSTAT_RV_GIVEUP) { @@ -686,6 +693,8 @@ xfs_bulkstat( ubelem++; lastino = ino; } + + cond_resched(); } if (bp) @@ -694,11 +703,12 @@ xfs_bulkstat( /* * Set up for the next loop iteration. */ - if (ubleft > 0) { + if (XFS_BULKSTAT_UBLEFT(ubleft)) { if (end_of_ag) { agno++; agino = 0; - } + } else + agino = XFS_INO_TO_AGINO(mp, lastino); } else break; } @@ -707,6 +717,11 @@ xfs_bulkstat( */ kmem_free(irbuf, irbsize); *ubcountp = ubelem; + /* + * Found some inodes, return them now and return the error next time. + */ + if (ubelem) + rval = 0; if (agno >= mp->m_sb.sb_agcount) { /* * If we ran out of filesystem, mark lastino as off |