diff options
Diffstat (limited to 'fs')
42 files changed, 706 insertions, 458 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 429a0022850..635f3e286ad 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 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..f02fdef463a 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -269,6 +269,13 @@ 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 +293,6 @@ 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/compat_ioctl.c b/fs/compat_ioctl.c index bd26e4cbb99..e8b7c3a98a5 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1954,6 +1954,12 @@ 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) 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/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..84f9f7dfdf5 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); 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..5e8d82f6666 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); - - if (nr_segs != 1) - goto out; + count, (long long) pos); - 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; @@ -821,21 +881,21 @@ 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; + + count = iov_length(iov, nr_segs); + nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count); - dprintk("nfs: direct write(%s/%s, %lu@%Ld)\n", + 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) goto out; + if (!count) + goto out; /* return 0 */ retval = -EINVAL; if ((ssize_t) count < 0) @@ -844,15 +904,11 @@ 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..0ee43843f4e 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -43,6 +43,25 @@ #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); + } + 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 +73,6 @@ 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 +88,10 @@ 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 +237,6 @@ 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 +258,10 @@ 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/super.c b/fs/nfs/super.c index fa517ae9207..2426e713b77 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_dir_inode_operations) { + 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; 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/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.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/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/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/proc/array.c b/fs/proc/array.c index eba339ecba2..65c62e1bfd6 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -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 diff --git a/fs/proc/base.c b/fs/proc/base.c index a17c2685907..02a63ac0417 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2411,19 +2411,23 @@ 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 +2440,25 @@ 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 +2466,7 @@ 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 +2479,14 @@ 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..39f3d651903 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -555,41 +555,6 @@ 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, @@ -764,8 +729,6 @@ 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)) diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 1b2b6c6bb47..1820eb2ef76 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -78,5 +78,3 @@ 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/root.c b/fs/proc/root.c index 1f86bb860e0..ec9cb3b6c93 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, diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 27d1785b764..4045bdcc4b3 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -119,7 +119,11 @@ 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; |