diff options
| -rw-r--r-- | Documentation/filesystems/cifs/AUTHORS | 1 | ||||
| -rw-r--r-- | Documentation/filesystems/cifs/TODO | 97 | ||||
| -rw-r--r-- | fs/cifs/cifs_debug.c | 2 | ||||
| -rw-r--r-- | fs/cifs/cifsfs.h | 2 | ||||
| -rw-r--r-- | fs/cifs/cifsglob.h | 19 | ||||
| -rw-r--r-- | fs/cifs/cifsproto.h | 4 | ||||
| -rw-r--r-- | fs/cifs/cifssmb.c | 119 | ||||
| -rw-r--r-- | fs/cifs/connect.c | 8 | ||||
| -rw-r--r-- | fs/cifs/file.c | 872 | ||||
| -rw-r--r-- | fs/cifs/misc.c | 13 | ||||
| -rw-r--r-- | fs/cifs/sess.c | 1192 | ||||
| -rw-r--r-- | fs/cifs/smb1ops.c | 8 | ||||
| -rw-r--r-- | fs/cifs/smb2inode.c | 2 | ||||
| -rw-r--r-- | fs/cifs/smb2maperror.c | 2 | ||||
| -rw-r--r-- | fs/cifs/smb2misc.c | 6 | ||||
| -rw-r--r-- | fs/cifs/smb2ops.c | 73 | ||||
| -rw-r--r-- | fs/cifs/smb2pdu.c | 94 | ||||
| -rw-r--r-- | fs/cifs/smb2proto.h | 2 | ||||
| -rw-r--r-- | fs/cifs/smb2transport.c | 5 | ||||
| -rw-r--r-- | fs/cifs/transport.c | 25 |
20 files changed, 1702 insertions, 844 deletions
diff --git a/Documentation/filesystems/cifs/AUTHORS b/Documentation/filesystems/cifs/AUTHORS index ca4a67a0bb1e..c98800df677f 100644 --- a/Documentation/filesystems/cifs/AUTHORS +++ b/Documentation/filesystems/cifs/AUTHORS @@ -40,6 +40,7 @@ Gunter Kukkukk (testing and suggestions for support of old servers) Igor Mammedov (DFS support) Jeff Layton (many, many fixes, as well as great work on the cifs Kerberos code) Scott Lovenberg +Pavel Shilovsky (for great work adding SMB2 support, and various SMB3 features) Test case and Bug Report contributors ------------------------------------- diff --git a/Documentation/filesystems/cifs/TODO b/Documentation/filesystems/cifs/TODO index 355abcdcda98..066ffddc3964 100644 --- a/Documentation/filesystems/cifs/TODO +++ b/Documentation/filesystems/cifs/TODO @@ -1,4 +1,4 @@ -Version 1.53 May 20, 2008 +Version 2.03 August 1, 2014 A Partial List of Missing Features ================================== @@ -7,63 +7,49 @@ Contributions are welcome. There are plenty of opportunities for visible, important contributions to this module. Here is a partial list of the known problems and missing features: -a) Support for SecurityDescriptors(Windows/CIFS ACLs) for chmod/chgrp/chown -so that these operations can be supported to Windows servers +a) SMB3 (and SMB3.02) missing optional features: + - RDMA + - multichannel (started) + - directory leases (improved metadata caching) + - T10 copy offload (copy chunk is only mechanism supported) + - encrypted shares -b) Mapping POSIX ACLs (and eventually NFSv4 ACLs) to CIFS -SecurityDescriptors +b) improved sparse file support -c) Better pam/winbind integration (e.g. to handle uid mapping -better) - -d) Cleanup now unneeded SessSetup code in -fs/cifs/connect.c and add back in NTLMSSP code if any servers -need it - -e) fix NTLMv2 signing when two mounts with different users to same -server. - -f) Directory entry caching relies on a 1 second timer, rather than +c) Directory entry caching relies on a 1 second timer, rather than using FindNotify or equivalent. - (started) -g) quota support (needs minor kernel change since quota calls +d) quota support (needs minor kernel change since quota calls to make it to network filesystems or deviceless filesystems) -h) investigate sync behavior (including syncpage) and check -for proper behavior of intr/nointr - -i) improve support for very old servers (OS/2 and Win9x for example) +e) improve support for very old servers (OS/2 and Win9x for example) Including support for changing the time remotely (utimes command). -j) hook lower into the sockets api (as NFS/SunRPC does) to avoid the +f) hook lower into the sockets api (as NFS/SunRPC does) to avoid the extra copy in/out of the socket buffers in some cases. -k) Better optimize open (and pathbased setfilesize) to reduce the +g) Better optimize open (and pathbased setfilesize) to reduce the oplock breaks coming from windows srv. Piggyback identical file opens on top of each other by incrementing reference count rather than resending (helps reduce server resource utilization and avoid spurious oplock breaks). -l) Improve performance of readpages by sending more than one read -at a time when 8 pages or more are requested. In conjuntion -add support for async_cifs_readpages. - -m) Add support for storing symlink info to Windows servers +h) Add support for storing symlink info to Windows servers in the Extended Attribute format their SFU clients would recognize. -n) Finish fcntl D_NOTIFY support so kde and gnome file list windows +i) Finish inotify support so kde and gnome file list windows will autorefresh (partially complete by Asser). Needs minor kernel vfs change to support removing D_NOTIFY on a file. -o) Add GUI tool to configure /proc/fs/cifs settings and for display of +j) Add GUI tool to configure /proc/fs/cifs settings and for display of the CIFS statistics (started) -p) implement support for security and trusted categories of xattrs +k) implement support for security and trusted categories of xattrs (requires minor protocol extension) to enable better support for SELINUX -q) Implement O_DIRECT flag on open (already supported on mount) +l) Implement O_DIRECT flag on open (already supported on mount) -r) Create UID mapping facility so server UIDs can be mapped on a per +m) Create UID mapping facility so server UIDs can be mapped on a per mount or a per server basis to client UIDs or nobody if no mapping exists. This is helpful when Unix extensions are negotiated to allow better permission checking when UIDs differ on the server @@ -71,28 +57,29 @@ and client. Add new protocol request to the CIFS protocol standard for asking the server for the corresponding name of a particular uid. -s) Add support for CIFS Unix and also the newer POSIX extensions to the -server side for Samba 4. +n) DOS attrs - returned as pseudo-xattr in Samba format (check VFAT and NTFS for this too) + +o) mount check for unmatched uids -t) In support for OS/2 (LANMAN 1.2 and LANMAN2.1 based SMB servers) -need to add ability to set time to server (utimes command) +p) Add support for new vfs entry point for fallocate -u) DOS attrs - returned as pseudo-xattr in Samba format (check VFAT and NTFS for this too) +q) Add tools to take advantage of cifs/smb3 specific ioctls and features +such as "CopyChunk" (fast server side file copy) -v) mount check for unmatched uids +r) encrypted file support -w) Add support for new vfs entry point for fallocate +s) improved stats gathering, tools (perhaps integration with nfsometer?) -x) Fix Samba 3 server to handle Linux kernel aio so dbench with lots of -processes can proceed better in parallel (on the server) +t) allow setting more NTFS/SMB3 file attributes remotely (currently limited to compressed +file attribute via chflags) -y) Fix Samba 3 to handle reads/writes over 127K (and remove the cifs mount -restriction of wsize max being 127K) +u) mount helper GUI (to simplify the various configuration options on mount) -KNOWN BUGS (updated April 24, 2007) + +KNOWN BUGS ==================================== See http://bugzilla.samba.org - search on product "CifsVFS" for -current bug list. +current bug list. Also check http://bugzilla.kernel.org (Product = File System, Component = CIFS) 1) existing symbolic links (Windows reparse points) are recognized but can not be created remotely. They are implemented for Samba and those that @@ -100,30 +87,18 @@ support the CIFS Unix extensions, although earlier versions of Samba overly restrict the pathnames. 2) follow_link and readdir code does not follow dfs junctions but recognizes them -3) create of new files to FAT partitions on Windows servers can -succeed but still return access denied (appears to be Windows -server not cifs client problem) and has not been reproduced recently. -NTFS partitions do not have this problem. -4) Unix/POSIX capabilities are reset after reconnection, and affect -a few fields in the tree connection but we do do not know which -superblocks to apply these changes to. We should probably walk -the list of superblocks to set these. Also need to check the -flags on the second mount to the same share, and see if we -can do the same trick that NFS does to remount duplicate shares. Misc testing to do ================== 1) check out max path names and max path name components against various server types. Try nested symlinks (8 deep). Return max path name in stat -f information -2) Modify file portion of ltp so it can run against a mounted network -share and run it against cifs vfs in automated fashion. +2) Improve xfstest's cifs enablement and adapt xfstests where needed to test +cifs better 3) Additional performance testing and optimization using iozone and similar - there are some easy changes that can be done to parallelize sequential writes, and when signing is disabled to request larger read sizes (larger than negotiated size) and send larger write sizes to modern servers. -4) More exhaustively test against less common servers. More testing -against Windows 9x, Windows ME servers. - +4) More exhaustively test against less common servers diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index f3ac4154cbb6..44ec72684df5 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -213,7 +213,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) tcon->nativeFileSystem); } seq_printf(m, "DevInfo: 0x%x Attributes: 0x%x" - "\n\tPathComponentMax: %d Status: 0x%d", + "\n\tPathComponentMax: %d Status: %d", le32_to_cpu(tcon->fsDevInfo.DeviceCharacteristics), le32_to_cpu(tcon->fsAttrInfo.Attributes), le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength), diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 70f178a7c759..560480263336 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -136,5 +136,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.03" +#define CIFS_VERSION "2.04" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index de6aed8c78e5..0012e1e291d4 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -404,6 +404,11 @@ struct smb_version_operations { const struct cifs_fid *, u32 *); int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *, int); + /* writepages retry size */ + unsigned int (*wp_retry_size)(struct inode *); + /* get mtu credits */ + int (*wait_mtu_credits)(struct TCP_Server_Info *, unsigned int, + unsigned int *, unsigned int *); }; struct smb_version_values { @@ -640,6 +645,16 @@ add_credits(struct TCP_Server_Info *server, const unsigned int add, } static inline void +add_credits_and_wake_if(struct TCP_Server_Info *server, const unsigned int add, + const int optype) +{ + if (add) { + server->ops->add_credits(server, add, optype); + wake_up(&server->request_q); + } +} + +static inline void set_credits(struct TCP_Server_Info *server, const int val) { server->ops->set_credits(server, val); @@ -1044,6 +1059,7 @@ struct cifs_readdata { struct address_space *mapping; __u64 offset; unsigned int bytes; + unsigned int got_bytes; pid_t pid; int result; struct work_struct work; @@ -1053,6 +1069,7 @@ struct cifs_readdata { struct kvec iov; unsigned int pagesz; unsigned int tailsz; + unsigned int credits; unsigned int nr_pages; struct page *pages[]; }; @@ -1073,6 +1090,7 @@ struct cifs_writedata { int result; unsigned int pagesz; unsigned int tailsz; + unsigned int credits; unsigned int nr_pages; struct page *pages[]; }; @@ -1398,6 +1416,7 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param, #define CIFS_OBREAK_OP 0x0100 /* oplock break request */ #define CIFS_NEG_OP 0x0200 /* negotiate request */ #define CIFS_OP_MASK 0x0380 /* mask request type */ +#define CIFS_HAS_CREDITS 0x0400 /* already has credits */ /* Security Flags: indicate type of session setup needed */ #define CIFSSEC_MAY_SIGN 0x00001 diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index ca7980a1e303..c31ce98c1704 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -36,6 +36,7 @@ extern struct smb_hdr *cifs_buf_get(void); extern void cifs_buf_release(void *); extern struct smb_hdr *cifs_small_buf_get(void); extern void cifs_small_buf_release(void *); +extern void free_rsp_buf(int, void *); extern void cifs_rqst_page_to_kvec(struct smb_rqst *rqst, unsigned int idx, struct kvec *iov); extern int smb_send(struct TCP_Server_Info *, struct smb_hdr *, @@ -89,6 +90,9 @@ extern struct mid_q_entry *cifs_setup_async_request(struct TCP_Server_Info *, struct smb_rqst *); extern int cifs_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server, bool log_error); +extern int cifs_wait_mtu_credits(struct TCP_Server_Info *server, + unsigned int size, unsigned int *num, + unsigned int *credits); extern int SendReceive2(const unsigned int /* xid */ , struct cifs_ses *, struct kvec *, int /* nvec to send */, int * /* type of buf returned */ , const int flags); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 6ce4e0954b98..66f65001a6d8 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -196,10 +196,6 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) if (rc) goto out; - /* - * FIXME: check if wsize needs updated due to negotiated smb buffer - * size shrinking - */ atomic_inc(&tconInfoReconnectCount); /* tell server Unix caps we support */ @@ -1517,7 +1513,6 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return length; server->total_read += length; - rdata->bytes = length; cifs_dbg(FYI, "total_read=%u buflen=%u remaining=%u\n", server->total_read, buflen, data_len); @@ -1560,12 +1555,18 @@ cifs_readv_callback(struct mid_q_entry *mid) rc); } /* FIXME: should this be counted toward the initiating task? */ - task_io_account_read(rdata->bytes); - cifs_stats_bytes_read(tcon, rdata->bytes); + task_io_account_read(rdata->got_bytes); + cifs_stats_bytes_read(tcon, rdata->got_bytes); break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: rdata->result = -EAGAIN; + if (server->sign && rdata->got_bytes) + /* reset bytes number since we can not check a sign */ + rdata->got_bytes = 0; + /* FIXME: should this be counted toward the initiating task? */ + task_io_account_read(rdata->got_bytes); + cifs_stats_bytes_read(tcon, rdata->got_bytes); break; default: rdata->result = -EIO; @@ -1734,10 +1735,7 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms, /* cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */ if (*buf) { - 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); + free_rsp_buf(resp_buf_type, iov[0].iov_base); } else if (resp_buf_type != CIFS_NO_BUFFER) { /* return buffer to caller to free */ *buf = iov[0].iov_base; @@ -1899,28 +1897,80 @@ cifs_writedata_release(struct kref *refcount) static void cifs_writev_requeue(struct cifs_writedata *wdata) { - int i, rc; + int i, rc = 0; struct inode *inode = wdata->cfile->dentry->d_inode; struct TCP_Server_Info *server; + unsigned int rest_len; - for (i = 0; i < wdata->nr_pages; i++) { - lock_page(wdata->pages[i]); - clear_page_dirty_for_io(wdata->pages[i]); - } - + server = tlink_tcon(wdata->cfile->tlink)->ses->server; + i = 0; + rest_len = wdata->bytes; do { - server = tlink_tcon(wdata->cfile->tlink)->ses->server; - rc = server->ops->async_writev(wdata, cifs_writedata_release); - } while (rc == -EAGAIN); + struct cifs_writedata *wdata2; + unsigned int j, nr_pages, wsize, tailsz, cur_len; + + wsize = server->ops->wp_retry_size(inode); + if (wsize < rest_len) { + nr_pages = wsize / PAGE_CACHE_SIZE; + if (!nr_pages) { + rc = -ENOTSUPP; + break; + } + cur_len = nr_pages * PAGE_CACHE_SIZE; + tailsz = PAGE_CACHE_SIZE; + } else { + nr_pages = DIV_ROUND_UP(rest_len, PAGE_CACHE_SIZE); + cur_len = rest_len; + tailsz = rest_len - (nr_pages - 1) * PAGE_CACHE_SIZE; + } - for (i = 0; i < wdata->nr_pages; i++) { - unlock_page(wdata->pages[i]); - if (rc != 0) { - SetPageError(wdata->pages[i]); - end_page_writeback(wdata->pages[i]); - page_cache_release(wdata->pages[i]); + wdata2 = cifs_writedata_alloc(nr_pages, cifs_writev_complete); + if (!wdata2) { + rc = -ENOMEM; + break; } - } + + for (j = 0; j < nr_pages; j++) { + wdata2->pages[j] = wdata->pages[i + j]; + lock_page(wdata2->pages[j]); + clear_page_dirty_for_io(wdata2->pages[j]); + } + + wdata2->sync_mode = wdata->sync_mode; + wdata2->nr_pages = nr_pages; + wdata2->offset = page_offset(wdata2->pages[0]); + wdata2->pagesz = PAGE_CACHE_SIZE; + wdata2->tailsz = tailsz; + wdata2->bytes = cur_len; + + wdata2->cfile = find_writable_file(CIFS_I(inode), false); + if (!wdata2->cfile) { + cifs_dbg(VFS, "No writable handles for inode\n"); + rc = -EBADF; + break; + } + wdata2->pid = wdata2->cfile->pid; + rc = server->ops->async_writev(wdata2, cifs_writedata_release); + + for (j = 0; j < nr_pages; j++) { + unlock_page(wdata2->pages[j]); + if (rc != 0 && rc != -EAGAIN) { + SetPageError(wdata2->pages[j]); + end_page_writeback(wdata2->pages[j]); + page_cache_release(wdata2->pages[j]); + } + } + + if (rc) { + kref_put(&wdata2->refcount, cifs_writedata_release); + if (rc == -EAGAIN) + continue; + break; + } + + rest_len -= cur_len; + i += nr_pages; + } while (i < wdata->nr_pages); mapping_set_error(inode->i_mapping, rc); kref_put(&wdata->refcount, cifs_writedata_release); @@ -2203,10 +2253,7 @@ CIFSSMBWrite2(const unsigned int xid, struct cifs_io_parms *io_parms, } /* cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */ - 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); + free_rsp_buf(resp_buf_type, iov[0].iov_base); /* Note: On -EAGAIN error only caller can retry on handle based calls since file handle passed in no longer valid */ @@ -2451,10 +2498,7 @@ 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); + free_rsp_buf(resp_buf_type, iov[0].iov_base); /* Note: On -EAGAIN error only caller can retry on handle based calls since file handle passed in no longer valid */ @@ -3838,10 +3882,7 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid, } } qsec_out: - if (buf_type == CIFS_SMALL_BUFFER) - cifs_small_buf_release(iov[0].iov_base); - else if (buf_type == CIFS_LARGE_BUFFER) - cifs_buf_release(iov[0].iov_base); + free_rsp_buf(buf_type, iov[0].iov_base); /* cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */ return rc; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index b98366f21f9e..03ed8a09581c 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -557,7 +557,7 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct kvec *iov_orig, try_to_freeze(); if (server_unresponsive(server)) { - total_read = -EAGAIN; + total_read = -ECONNABORTED; break; } @@ -571,7 +571,7 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct kvec *iov_orig, break; } else if (server->tcpStatus == CifsNeedReconnect) { cifs_reconnect(server); - total_read = -EAGAIN; + total_read = -ECONNABORTED; break; } else if (length == -ERESTARTSYS || length == -EAGAIN || @@ -588,7 +588,7 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct kvec *iov_orig, cifs_dbg(FYI, "Received no data or error: expecting %d\n" "got %d", to_read, length); cifs_reconnect(server); - total_read = -EAGAIN; + total_read = -ECONNABORTED; break; } } @@ -786,7 +786,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) cifs_dbg(VFS, "SMB response too long (%u bytes)\n", pdu_length); cifs_reconnect(server); wake_up(&server->response_q); - return -EAGAIN; + return -ECONNABORTED; } /* switch to large buffer if too big for a small one */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index b88b1ade4d3d..4ab2f79ffa7a 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1670,8 +1670,8 @@ cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data, break; } - len = min((size_t)cifs_sb->wsize, - write_size - total_written); + len = min(server->ops->wp_retry_size(dentry->d_inode), + (unsigned int)write_size - total_written); /* iov[0] is reserved for smb header */ iov[1].iov_base = (char *)write_data + total_written; iov[1].iov_len = len; @@ -1878,15 +1878,163 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) return rc; } +static struct cifs_writedata * +wdata_alloc_and_fillpages(pgoff_t tofind, struct address_space *mapping, + pgoff_t end, pgoff_t *index, + unsigned int *found_pages) +{ + unsigned int nr_pages; + struct page **pages; + struct cifs_writedata *wdata; + + wdata = cifs_writedata_alloc((unsigned int)tofind, + cifs_writev_complete); + if (!wdata) + return NULL; + + /* + * find_get_pages_tag seems to return a max of 256 on each + * iteration, so we must call it several times in order to + * fill the array or the wsize is effectively limited to + * 256 * PAGE_CACHE_SIZE. + */ + *found_pages = 0; + pages = wdata->pages; + do { + nr_pages = find_get_pages_tag(mapping, index, + PAGECACHE_TAG_DIRTY, tofind, + pages); + *found_pages += nr_pages; + tofind -= nr_pages; + pages += nr_pages; + } while (nr_pages && tofind && *index <= end); + + return wdata; +} + +static unsigned int +wdata_prepare_pages(struct cifs_writedata *wdata, unsigned int found_pages, + struct address_space *mapping, + struct writeback_control *wbc, + pgoff_t end, pgoff_t *index, pgoff_t *next, bool *done) +{ + unsigned int nr_pages = 0, i; + struct page *page; + + for (i = 0; i < found_pages; i++) { + page = wdata->pages[i]; + /* + * At this point we hold neither mapping->tree_lock nor + * lock on the page itself: the page may be truncated or + * invalidated (changing page->mapping to NULL), or even + * swizzled back from swapper_space to tmpfs file + * mapping + */ + + if (nr_pages == 0) + lock_page(page); + else if (!trylock_page(page)) + break; + + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + break; + } + + if (!wbc->range_cyclic && page->index > end) { + *done = true; + unlock_page(page); + break; + } + + if (*next && (page->index != *next)) { + /* Not next consecutive page */ + unlock_page(page); + break; + } + + if (wbc->sync_mode != WB_SYNC_NONE) + wait_on_page_writeback(page); + + if (PageWriteback(page) || + !clear_page_dirty_for_io(page)) { + unlock_page(page); + break; + } + + /* + * This actually clears the dirty bit in the radix tree. + * See cifs_writepage() for more commentary. + */ + set_page_writeback(page); + if (page_offset(page) >= i_size_read(mapping->host)) { + *done = true; + unlock_page(page); + end_page_writeback(page); + break; + } + + wdata->pages[i] = page; + *next = page->index + 1; + ++nr_pages; + } + + /* reset index to refind any pages skipped */ + if (nr_pages == 0) + *index = wdata->pages[0]->index + 1; + + /* put any pages we aren't going to use */ + for (i = nr_pages; i < found_pages; i++) { + page_cache_release(wdata->pages[i]); + wdata->pages[i] = NULL; + } + + return nr_pages; +} + +static int +wdata_send_pages(struct cifs_writedata *wdata, unsigned int nr_pages, + struct address_space *mapping, struct writeback_control *wbc) +{ + int rc = 0; + struct TCP_Server_Info *server; + unsigned int i; + + wdata->sync_mode = wbc->sync_mode; + wdata->nr_pages = nr_pages; + wdata->offset = page_offset(wdata->pages[0]); + wdata->pagesz = PAGE_CACHE_SIZE; + wdata->tailsz = min(i_size_read(mapping->host) - + page_offset(wdata->pages[nr_pages - 1]), + (loff_t)PAGE_CACHE_SIZE); + wdata->bytes = ((nr_pages - 1) * PAGE_CACHE_SIZE) + wdata->tailsz; + + if (wdata->cfile != NULL) + cifsFileInfo_put(wdata->cfile); + wdata->cfile = find_writable_file(CIFS_I(mapping->host), false); + if (!wdata->cfile) { + cifs_dbg(VFS, "No writable handles for inode\n"); + rc = -EBADF; + } else { + wdata->pid = wdata->cfile->pid; + server = tlink_tcon(wdata->cfile->tlink)->ses->server; + rc = server->ops->async_writev(wdata, cifs_writedata_release); + } + + for (i = 0; i < nr_pages; ++i) + unlock_page(wdata->pages[i]); + + return rc; +} + static int cifs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct cifs_sb_info *cifs_sb = CIFS_SB(mapping->host->i_sb); + struct TCP_Server_Info *server; bool done = false, scanned = false, range_whole = false; pgoff_t end, index; struct cifs_writedata *wdata; - struct TCP_Server_Info *server; - struct page *page; int rc = 0; /* @@ -1906,152 +2054,50 @@ static int cifs_writepages(struct address_space *mapping, range_whole = true; scanned = true; } + server = cifs_sb_master_tcon(cifs_sb)->ses->server; retry: while (!done && index <= end) { - unsigned int i, nr_pages, found_pages; - pgoff_t next = 0, tofind; - struct page **pages; + unsigned int i, nr_pages, found_pages, wsize, credits; + pgoff_t next = 0, tofind, saved_index = index; + + rc = server->ops->wait_mtu_credits(server, cifs_sb->wsize, + &wsize, &credits); + if (rc) + break; - tofind = min((cifs_sb->wsize / PAGE_CACHE_SIZE) - 1, - end - index) + 1; + tofind = min((wsize / PAGE_CACHE_SIZE) - 1, end - index) + 1; - wdata = cifs_writedata_alloc((unsigned int)tofind, - cifs_writev_complete); + wdata = wdata_alloc_and_fillpages(tofind, mapping, end, &index, + &found_pages); if (!wdata) { rc = -ENOMEM; + add_credits_and_wake_if(server, credits, 0); break; } - /* - * find_get_pages_tag seems to return a max of 256 on each - * iteration, so we must call it several times in order to - * fill the array or the wsize is effectively limited to - * 256 * PAGE_CACHE_SIZE. - */ - found_pages = 0; - pages = wdata->pages; - do { - nr_pages = find_get_pages_tag(mapping, &index, - PAGECACHE_TAG_DIRTY, - tofind, pages); - found_pages += nr_pages; - tofind -= nr_pages; - pages += nr_pages; - } while (nr_pages && tofind && index <= end); - if (found_pages == 0) { kref_put(&wdata->refcount, cifs_writedata_release); + add_credits_and_wake_if(server, credits, 0); break; } - nr_pages = 0; - for (i = 0; i < found_pages; i++) { - page = wdata->pages[i]; - /* - * At this point we hold neither mapping->tree_lock nor - * lock on the page itself: the page may be truncated or - * invalidated (changing page->mapping to NULL), or even - * swizzled back from swapper_space to tmpfs file - * mapping - */ - - if (nr_pages == 0) - lock_page(page); - else if (!trylock_page(page)) - break; - - if (unlikely(page->mapping != mapping)) { - unlock_page(page); - break; - } - - if (!wbc->range_cyclic && page->index > end) { - done = true; - unlock_page(page); - break; - } - - if (next && (page->index != next)) { - /* Not next consecutive page */ - unlock_page(page); - break; - } - - if (wbc->sync_mode != WB_SYNC_NONE) - wait_on_page_writeback(page); - - if (PageWriteback(page) || - !clear_page_dirty_for_io(page)) { - unlock_page(page); - break; - } - - /* - * This actually clears the dirty bit in the radix tree. - * See cifs_writepage() for more commentary. - */ - set_page_writeback(page); - - if (page_offset(page) >= i_size_read(mapping->host)) { - done = true; - unlock_page(page); - end_page_writeback(page); - break; - } - - wdata->pages[i] = page; - next = page->index + 1; - ++nr_pages; - } - - /* reset index to refind any pages skipped */ - if (nr_pages == 0) - index = wdata->pages[0]->index + 1; - - /* put any pages we aren't going to use */ - for (i = nr_pages; i < found_pages; i++) { - page_cache_release(wdata->pages[i]); - wdata->pages[i] = NULL; - } + nr_pages = wdata_prepare_pages(wdata, found_pages, mapping, wbc, + end, &index, &next, &done); /* nothing to write? */ if (nr_pages == 0) { kref_put(&wdata->refcount, cifs_writedata_release); + add_credits_and_wake_if(server, credits, 0); continue; } - wdata->sync_mode = wbc->sync_mode; - wdata->nr_pages = nr_pages; - wdata->offset = page_offset(wdata->pages[0]); - wdata->pagesz = PAGE_CACHE_SIZE; - wdata->tailsz = - min(i_size_read(mapping->host) - - page_offset(wdata->pages[nr_pages - 1]), - (loff_t)PAGE_CACHE_SIZE); - wdata->bytes = ((nr_pages - 1) * PAGE_CACHE_SIZE) + - wdata->tailsz; - - do { - if (wdata->cfile != NULL) - cifsFileInfo_put(wdata->cfile); - wdata->cfile = find_writable_file(CIFS_I(mapping->host), - false); - if (!wdata->cfile) { - cifs_dbg(VFS, "No writable handles for inode\n"); - rc = -EBADF; - break; - } - wdata->pid = wdata->cfile->pid; - server = tlink_tcon(wdata->cfile->tlink)->ses->server; - rc = server->ops->async_writev(wdata, - cifs_writedata_release); - } while (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN); + wdata->credits = credits; - for (i = 0; i < nr_pages; ++i) - unlock_page(wdata->pages[i]); + rc = wdata_send_pages(wdata, nr_pages, mapping, wbc); /* send failure -- clean up the mess */ if (rc != 0) { + add_credits_and_wake_if(server, wdata->credits, 0); for (i = 0; i < nr_pages; ++i) { if (rc == -EAGAIN) redirty_page_for_writepage(wbc, @@ -2066,6 +2112,11 @@ retry: } kref_put(&wdata->refcount, cifs_writedata_release); + if (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN) { + index = saved_index; + continue; + } + wbc->nr_to_write -= nr_pages; if (wbc->nr_to_write <= 0) done = true; @@ -2362,123 +2413,109 @@ cifs_uncached_writev_complete(struct work_struct *work) kref_put(&wdata->refcount, cifs_uncached_writedata_release); } -/* attempt to send write to server, retry on any -EAGAIN errors */ static int -cifs_uncached_retry_writev(struct cifs_writedata *wdata) +wdata_fill_from_iovec(struct cifs_writedata *wdata, struct iov_iter *from, + size_t *len, unsigned long *num_pages) { |