diff options
Diffstat (limited to 'fs/smb')
59 files changed, 3926 insertions, 3989 deletions
diff --git a/fs/smb/client/Kconfig b/fs/smb/client/Kconfig index 2927bd174a88..2517dc242386 100644 --- a/fs/smb/client/Kconfig +++ b/fs/smb/client/Kconfig @@ -2,6 +2,7 @@ config CIFS tristate "SMB3 and CIFS support (advanced network filesystem)" depends on INET + select NETFS_SUPPORT select NLS select NLS_UCS2_UTILS select CRYPTO diff --git a/fs/smb/client/Makefile b/fs/smb/client/Makefile index 0b07eb94c93b..e11985f2460b 100644 --- a/fs/smb/client/Makefile +++ b/fs/smb/client/Makefile @@ -12,7 +12,7 @@ cifs-y := trace.o cifsfs.o cifs_debug.o connect.o dir.o file.o \ smb2ops.o smb2maperror.o smb2transport.o \ smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o \ dns_resolve.o cifs_spnego_negtokeninit.asn1.o asn1.o \ - namespace.o + namespace.o reparse.o $(obj)/asn1.o: $(obj)/cifs_spnego_negtokeninit.asn1.h diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 3de5047a7ff9..0ff2491c311d 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -239,7 +239,8 @@ replay_again: .tcon = tcon, .path = path, .create_options = cifs_create_options(cifs_sb, CREATE_NOT_FILE), - .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES, + .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES | + FILE_READ_EA, .disposition = FILE_OPEN, .fid = pfid, .replay = !!(retries), @@ -416,6 +417,7 @@ smb2_close_cached_fid(struct kref *ref) { struct cached_fid *cfid = container_of(ref, struct cached_fid, refcount); + int rc; spin_lock(&cfid->cfids->cfid_list_lock); if (cfid->on_list) { @@ -429,9 +431,10 @@ smb2_close_cached_fid(struct kref *ref) cfid->dentry = NULL; if (cfid->is_open) { - SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, + rc = SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, cfid->fid.volatile_fid); - atomic_dec(&cfid->tcon->num_remote_opens); + if (rc) /* should we retry on -EBUSY or -EAGAIN? */ + cifs_dbg(VFS, "close cached dir rc %d\n", rc); } free_cached_dir(cfid); diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index 3e4209f41c18..c71ae5c04306 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -250,6 +250,8 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); list_for_each_entry(cfile, &tcon->openFileList, tlist) { @@ -278,6 +280,24 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) return 0; } +static __always_inline const char *compression_alg_str(__le16 alg) +{ + switch (alg) { + case SMB3_COMPRESS_NONE: + return "NONE"; + case SMB3_COMPRESS_LZNT1: + return "LZNT1"; + case SMB3_COMPRESS_LZ77: + return "LZ77"; + case SMB3_COMPRESS_LZ77_HUFF: + return "LZ77-Huffman"; + case SMB3_COMPRESS_PATTERN: + return "Pattern_V1"; + default: + return "invalid"; + } +} + static int cifs_debug_data_proc_show(struct seq_file *m, void *v) { struct mid_q_entry *mid_entry; @@ -423,12 +443,6 @@ skip_rdma: server->echo_credits, server->oplock_credits, server->dialect); - if (server->compress_algorithm == SMB3_COMPRESS_LZNT1) - seq_printf(m, " COMPRESS_LZNT1"); - else if (server->compress_algorithm == SMB3_COMPRESS_LZ77) - seq_printf(m, " COMPRESS_LZ77"); - else if (server->compress_algorithm == SMB3_COMPRESS_LZ77_HUFF) - seq_printf(m, " COMPRESS_LZ77_HUFF"); if (server->sign) seq_printf(m, " signed"); if (server->posix_ext_supported) @@ -460,6 +474,14 @@ skip_rdma: server->leaf_fullpath); } + seq_puts(m, "\nCompression: "); + if (!server->compression.requested) + seq_puts(m, "disabled on mount"); + else if (server->compression.enabled) + seq_printf(m, "enabled (%s)", compression_alg_str(server->compression.alg)); + else + seq_puts(m, "disabled (not supported by this server)"); + seq_printf(m, "\n\n\tSessions: "); i = 0; list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { @@ -488,6 +510,8 @@ skip_rdma: ses->ses_count, ses->serverOS, ses->serverNOS, ses->capabilities, ses->ses_status); } + if (ses->expired_pwd) + seq_puts(m, "password no longer valid "); spin_unlock(&ses->ses_lock); seq_printf(m, "\n\tSecurity type: %s ", @@ -654,6 +678,8 @@ static ssize_t cifs_stats_proc_write(struct file *file, } #endif /* CONFIG_CIFS_STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { atomic_set(&tcon->num_smbs_sent, 0); spin_lock(&tcon->stat_lock); @@ -733,6 +759,8 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) } #endif /* STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { i++; seq_printf(m, "\n%d) %s", i, tcon->tree_name); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 0c269396ae15..a665aac9be9f 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -151,15 +151,12 @@ MODULE_PARM_DESC(disable_legacy_dialects, "To improve security it may be " "vers=1.0 (CIFS/SMB1) and vers=2.0 are weaker" " and less secure. Default: n/N/0"); -extern mempool_t *cifs_sm_req_poolp; -extern mempool_t *cifs_req_poolp; -extern mempool_t *cifs_mid_poolp; - struct workqueue_struct *cifsiod_wq; struct workqueue_struct *decrypt_wq; struct workqueue_struct *fileinfo_put_wq; struct workqueue_struct *cifsoplockd_wq; struct workqueue_struct *deferredclose_wq; +struct workqueue_struct *serverclose_wq; __u32 cifs_lock_secret; /* @@ -374,9 +371,13 @@ static struct kmem_cache *cifs_inode_cachep; static struct kmem_cache *cifs_req_cachep; static struct kmem_cache *cifs_mid_cachep; static struct kmem_cache *cifs_sm_req_cachep; +static struct kmem_cache *cifs_io_request_cachep; +static struct kmem_cache *cifs_io_subrequest_cachep; mempool_t *cifs_sm_req_poolp; mempool_t *cifs_req_poolp; mempool_t *cifs_mid_poolp; +mempool_t cifs_io_request_pool; +mempool_t cifs_io_subrequest_pool; static struct inode * cifs_alloc_inode(struct super_block *sb) @@ -392,6 +393,7 @@ cifs_alloc_inode(struct super_block *sb) * server, can not assume caching of file data or metadata. */ cifs_set_oplock_level(cifs_inode, 0); + cifs_inode->lease_granted = false; cifs_inode->flags = 0; spin_lock_init(&cifs_inode->writers_lock); cifs_inode->writers = 0; @@ -673,6 +675,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_printf(s, ",backupgid=%u", from_kgid_munged(&init_user_ns, cifs_sb->ctx->backupgid)); + seq_show_option(s, "reparse", + cifs_reparse_type_str(cifs_sb->ctx->reparse_type)); seq_printf(s, ",rsize=%u", cifs_sb->ctx->rsize); seq_printf(s, ",wsize=%u", cifs_sb->ctx->wsize); @@ -740,6 +744,8 @@ static void cifs_umount_begin(struct super_block *sb) spin_lock(&cifs_tcp_ses_lock); spin_lock(&tcon->tc_lock); + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_see_umount); if ((tcon->tc_count > 1) || (tcon->status == TID_EXITING)) { /* we have other mounts to same share or we have already tried to umount this and woken up @@ -984,61 +990,6 @@ out: return root; } - -static ssize_t -cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter) -{ - ssize_t rc; - struct inode *inode = file_inode(iocb->ki_filp); - - if (iocb->ki_flags & IOCB_DIRECT) - return cifs_user_readv(iocb, iter); - - rc = cifs_revalidate_mapping(inode); - if (rc) - return rc; - - return generic_file_read_iter(iocb, iter); -} - -static ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) -{ - struct inode *inode = file_inode(iocb->ki_filp); - struct cifsInodeInfo *cinode = CIFS_I(inode); - ssize_t written; - int rc; - - if (iocb->ki_filp->f_flags & O_DIRECT) { - written = cifs_user_writev(iocb, from); - if (written > 0 && CIFS_CACHE_READ(cinode)) { - cifs_zap_mapping(inode); - cifs_dbg(FYI, - "Set no oplock for inode=%p after a write operation\n", - inode); - cinode->oplock = 0; - } - return written; - } - - written = cifs_get_writer(cinode); - if (written) - return written; - - written = generic_file_write_iter(iocb, from); - - if (CIFS_CACHE_WRITE(CIFS_I(inode))) - goto out; - - rc = filemap_fdatawrite(inode->i_mapping); - if (rc) - cifs_dbg(FYI, "cifs_file_write_iter: %d rc on %p inode\n", - rc, inode); - -out: - cifs_put_writer(cinode); - return written; -} - static loff_t cifs_llseek(struct file *file, loff_t offset, int whence) { struct cifsFileInfo *cfile = file->private_data; @@ -1085,7 +1036,7 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int whence) } static int -cifs_setlease(struct file *file, int arg, struct file_lock **lease, void **priv) +cifs_setlease(struct file *file, int arg, struct file_lease **lease, void **priv) { /* * Note that this is called by vfs setlease with i_lock held to @@ -1094,9 +1045,6 @@ cifs_setlease(struct file *file, int arg, struct file_lock **lease, void **priv) struct inode *inode = file_inode(file); struct cifsFileInfo *cfile = file->private_data; - if (!(S_ISREG(inode->i_mode))) - return -EINVAL; - /* Check if file is oplocked if this is request for new lease */ if (arg == F_UNLCK || ((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) || @@ -1278,7 +1226,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, struct cifsFileInfo *smb_file_src = src_file->private_data; struct cifsFileInfo *smb_file_target = dst_file->private_data; struct cifs_tcon *target_tcon, *src_tcon; - unsigned long long destend, fstart, fend, new_size; + unsigned long long destend, fstart, fend, old_size, new_size; unsigned int xid; int rc; @@ -1343,6 +1291,9 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false); if (rc) goto unlock; + if (fend > target_cifsi->netfs.zero_point) + target_cifsi->netfs.zero_point = fend + 1; + old_size = target_cifsi->netfs.remote_i_size; /* Discard all the folios that overlap the destination region. */ cifs_dbg(FYI, "about to discard pages %llx-%llx\n", fstart, fend); @@ -1355,12 +1306,13 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, if (target_tcon->ses->server->ops->duplicate_extents) { rc = target_tcon->ses->server->ops->duplicate_extents(xid, smb_file_src, smb_file_target, off, len, destoff); - if (rc == 0 && new_size > i_size_read(target_inode)) { + if (rc == 0 && new_size > old_size) { truncate_setsize(target_inode, new_size); - netfs_resize_file(&target_cifsi->netfs, new_size, true); fscache_resize_cookie(cifs_inode_cookie(target_inode), new_size); } + if (rc == 0 && new_size > target_cifsi->netfs.zero_point) + target_cifsi->netfs.zero_point = new_size; } /* force revalidate of size and timestamps of target file now @@ -1452,6 +1404,8 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false); if (rc) goto unlock; + if (fend > target_cifsi->netfs.zero_point) + target_cifsi->netfs.zero_point = fend + 1; /* Discard all the folios that overlap the destination region. */ truncate_inode_pages_range(&target_inode->i_data, fstart, fend); @@ -1568,8 +1522,8 @@ const struct file_operations cifs_file_strict_ops = { }; const struct file_operations cifs_file_direct_ops = { - .read_iter = cifs_direct_readv, - .write_iter = cifs_direct_writev, + .read_iter = netfs_unbuffered_read_iter, + .write_iter = netfs_file_write_iter, .open = cifs_open, .release = cifs_close, .lock = cifs_lock, @@ -1624,8 +1578,8 @@ const struct file_operations cifs_file_strict_nobrl_ops = { }; const struct file_operations cifs_file_direct_nobrl_ops = { - .read_iter = cifs_direct_readv, - .write_iter = cifs_direct_writev, + .read_iter = netfs_unbuffered_read_iter, + .write_iter = netfs_file_write_iter, .open = cifs_open, .release = cifs_close, .fsync = cifs_fsync, @@ -1667,7 +1621,7 @@ cifs_init_inodecache(void) cifs_inode_cachep = kmem_cache_create("cifs_inode_cache", sizeof(struct cifsInodeInfo), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_ACCOUNT), + SLAB_ACCOUNT), cifs_init_once); if (cifs_inode_cachep == NULL) return -ENOMEM; @@ -1800,6 +1754,48 @@ static void destroy_mids(void) kmem_cache_destroy(cifs_mid_cachep); } +static int cifs_init_netfs(void) +{ + cifs_io_request_cachep = + kmem_cache_create("cifs_io_request", + sizeof(struct cifs_io_request), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!cifs_io_request_cachep) + goto nomem_req; + + if (mempool_init_slab_pool(&cifs_io_request_pool, 100, cifs_io_request_cachep) < 0) + goto nomem_reqpool; + + cifs_io_subrequest_cachep = + kmem_cache_create("cifs_io_subrequest", + sizeof(struct cifs_io_subrequest), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!cifs_io_subrequest_cachep) + goto nomem_subreq; + + if (mempool_init_slab_pool(&cifs_io_subrequest_pool, 100, cifs_io_subrequest_cachep) < 0) + goto nomem_subreqpool; + + return 0; + +nomem_subreqpool: + kmem_cache_destroy(cifs_io_subrequest_cachep); +nomem_subreq: + mempool_destroy(&cifs_io_request_pool); +nomem_reqpool: + kmem_cache_destroy(cifs_io_request_cachep); +nomem_req: + return -ENOMEM; +} + +static void cifs_destroy_netfs(void) +{ + mempool_exit(&cifs_io_subrequest_pool); + kmem_cache_destroy(cifs_io_subrequest_cachep); + mempool_exit(&cifs_io_request_pool); + kmem_cache_destroy(cifs_io_request_cachep); +} + static int __init init_cifs(void) { @@ -1893,14 +1889,25 @@ init_cifs(void) goto out_destroy_cifsoplockd_wq; } + serverclose_wq = alloc_workqueue("serverclose", + WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); + if (!serverclose_wq) { + rc = -ENOMEM; + goto out_destroy_serverclose_wq; + } + rc = cifs_init_inodecache(); if (rc) goto out_destroy_deferredclose_wq; - rc = init_mids(); + rc = cifs_init_netfs(); if (rc) goto out_destroy_inodecache; + rc = init_mids(); + if (rc) + goto out_destroy_netfs; + rc = cifs_init_request_bufs(); if (rc) goto out_destroy_mids; @@ -1955,6 +1962,8 @@ out_destroy_request_bufs: cifs_destroy_request_bufs(); out_destroy_mids: destroy_mids(); +out_destroy_netfs: + cifs_destroy_netfs(); out_destroy_inodecache: cifs_destroy_inodecache(); out_destroy_deferredclose_wq: @@ -1967,6 +1976,8 @@ out_destroy_decrypt_wq: destroy_workqueue(decrypt_wq); out_destroy_cifsiod_wq: destroy_workqueue(cifsiod_wq); +out_destroy_serverclose_wq: + destroy_workqueue(serverclose_wq); out_clean_proc: cifs_proc_clean(); return rc; @@ -1991,11 +2002,13 @@ exit_cifs(void) #endif cifs_destroy_request_bufs(); destroy_mids(); + cifs_destroy_netfs(); cifs_destroy_inodecache(); destroy_workqueue(deferredclose_wq); destroy_workqueue(cifsoplockd_wq); destroy_workqueue(decrypt_wq); destroy_workqueue(fileinfo_put_wq); + destroy_workqueue(serverclose_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index 685f7d1139c6..62d5fee3e5eb 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -69,7 +69,6 @@ extern int cifs_revalidate_file_attr(struct file *filp); extern int cifs_revalidate_dentry_attr(struct dentry *); extern int cifs_revalidate_file(struct file *filp); extern int cifs_revalidate_dentry(struct dentry *); -extern int cifs_invalidate_mapping(struct inode *inode); extern int cifs_revalidate_mapping(struct inode *inode); extern int cifs_zap_mapping(struct inode *inode); extern int cifs_getattr(struct mnt_idmap *, const struct path *, @@ -85,6 +84,7 @@ extern const struct inode_operations cifs_namespace_inode_operations; /* Functions related to files and directories */ +extern const struct netfs_request_ops cifs_req_ops; extern const struct file_operations cifs_file_ops; extern const struct file_operations cifs_file_direct_ops; /* if directio mnt */ extern const struct file_operations cifs_file_strict_ops; /* if strictio mnt */ @@ -94,12 +94,10 @@ extern const struct file_operations cifs_file_strict_nobrl_ops; extern int cifs_open(struct inode *inode, struct file *file); extern int cifs_close(struct inode *inode, struct file *file); extern int cifs_closedir(struct inode *inode, struct file *file); -extern ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to); -extern ssize_t cifs_direct_readv(struct kiocb *iocb, struct iov_iter *to); extern ssize_t cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to); -extern ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from); -extern ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from); extern ssize_t cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from); +ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from); +ssize_t cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter); extern int cifs_flock(struct file *pfile, int cmd, struct file_lock *plock); extern int cifs_lock(struct file *, int, struct file_lock *); extern int cifs_fsync(struct file *, loff_t, loff_t, int); @@ -110,9 +108,6 @@ extern int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma); extern const struct file_operations cifs_dir_ops; extern int cifs_dir_open(struct inode *inode, struct file *file); extern int cifs_readdir(struct file *file, struct dir_context *ctx); -extern void cifs_pages_written_back(struct inode *inode, loff_t start, unsigned int len); -extern void cifs_pages_write_failed(struct inode *inode, loff_t start, unsigned int len); -extern void cifs_pages_write_redirty(struct inode *inode, loff_t start, unsigned int len); /* Functions related to dir entries */ extern const struct dentry_operations cifs_dentry_ops; @@ -152,6 +147,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 47 -#define CIFS_VERSION "2.47" +#define SMB3_PRODUCT_BUILD 49 +#define CIFS_VERSION "2.49" #endif /* _CIFSFS_H */ diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 53c75cfb33ab..73482734a8d8 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -153,6 +153,24 @@ enum securityEnum { Kerberos, /* Kerberos via SPNEGO */ }; +enum cifs_reparse_type { + CIFS_REPARSE_TYPE_NFS, + CIFS_REPARSE_TYPE_WSL, + CIFS_REPARSE_TYPE_DEFAULT = CIFS_REPARSE_TYPE_NFS, +}; + +static inline const char *cifs_reparse_type_str(enum cifs_reparse_type type) +{ + switch (type) { + case CIFS_REPARSE_TYPE_NFS: + return "nfs"; + case CIFS_REPARSE_TYPE_WSL: + return "wsl"; + default: + return "unknown"; + } +} + struct session_key { unsigned int len; char *response; @@ -208,6 +226,10 @@ struct cifs_open_info_data { struct reparse_posix_data *posix; }; } reparse; + struct { + __u8 eas[SMB2_WSL_MAX_QUERY_EA_RESP_SIZE]; + unsigned int eas_len; + } wsl; char *symlink_target; struct cifs_sid posix_owner; struct cifs_sid posix_group; @@ -217,19 +239,6 @@ struct cifs_open_info_data { }; }; -static inline bool cifs_open_data_reparse(struct cifs_open_info_data *data) -{ - struct smb2_file_all_info *fi = &data->fi; - u32 attrs = le32_to_cpu(fi->Attributes); - bool ret; - - ret = data->reparse_point || (attrs & ATTR_REPARSE); - if (ret) - attrs |= ATTR_REPARSE; - fi->Attributes = cpu_to_le32(attrs); - return ret; -} - /* ***************************************************************** * Except the CIFS PDUs themselves all the @@ -259,8 +268,7 @@ struct dfs_info3_param; struct cifs_fattr; struct smb3_fs_context; struct cifs_fid; -struct cifs_readdata; -struct cifs_writedata; +struct cifs_io_subrequest; struct cifs_io_parms; struct cifs_search_info; struct cifsInodeInfo; @@ -346,6 +354,9 @@ struct smb_version_operations { /* informational QFS call */ void (*qfs_tcon)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *); + /* query for server interfaces */ + int (*query_server_interfaces)(const unsigned int, struct cifs_tcon *, + bool); /* check if a path is accessible or not */ int (*is_path_accessible)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *, const char *); @@ -371,7 +382,8 @@ struct smb_version_operations { struct cifs_open_info_data *data); /* set size by path */ int (*set_path_size)(const unsigned int, struct cifs_tcon *, - const char *, __u64, struct cifs_sb_info *, bool); + const char *, __u64, struct cifs_sb_info *, bool, + struct dentry *); /* set size by file handle */ int (*set_file_size)(const unsigned int, struct cifs_tcon *, struct cifsFileInfo *, __u64, bool); @@ -401,7 +413,7 @@ struct smb_version_operations { struct cifs_sb_info *); /* unlink file */ int (*unlink)(const unsigned int, struct cifs_tcon *, const char *, - struct cifs_sb_info *); + struct cifs_sb_info *, struct dentry *); /* open, rename and delete file */ int (*rename_pending_delete)(const char *, struct dentry *, const unsigned int); @@ -429,18 +441,17 @@ struct smb_version_operations { /* set fid protocol-specific info */ void (*set_fid)(struct cifsFileInfo *, struct cifs_fid *, __u32); /* close a file */ - void (*close)(const unsigned int, struct cifs_tcon *, + int (*close)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); /* close a file, returning file attributes and timestamps */ - void (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, + int (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *pfile_info); /* send a flush request to the server */ int (*flush)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); /* async read from the server */ - int (*async_readv)(struct cifs_readdata *); + int (*async_readv)(struct cifs_io_subrequest *); /* async write to the server */ - int (*async_writev)(struct cifs_writedata *, - void (*release)(struct kref *)); + void (*async_writev)(struct cifs_io_subrequest *); /* sync read from the server */ int (*sync_read)(const unsigned int, struct cifs_fid *, struct cifs_io_parms *, unsigned int *, char **, @@ -535,8 +546,8 @@ struct smb_version_operations { /* 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 *, struct cifs_credits *); + int (*wait_mtu_credits)(struct TCP_Server_Info *, size_t, + size_t *, struct cifs_credits *); /* adjust previously taken mtu credits to request size */ int (*adjust_credits)(struct TCP_Server_Info *server, struct cifs_credits *credits, @@ -759,7 +770,11 @@ struct TCP_Server_Info { unsigned int max_write; unsigned int min_offload; unsigned int retrans; - __le16 compress_algorithm; + struct { + bool requested; /* "compress" mount option set*/ + bool enabled; /* actually negotiated with server */ + __le16 alg; /* preferred alg negotiated with server */ + } compression; __u16 signing_algorithm; __le16 cipher_type; /* save initital negprot hash */ @@ -866,11 +881,12 @@ add_credits(struct TCP_Server_Info *server, const struct cifs_credits *credits, static inline void add_credits_and_wake_if(struct TCP_Server_Info *server, - const struct cifs_credits *credits, const int optype) + struct cifs_credits *credits, const int optype) { if (credits->value) { server->ops->add_credits(server, credits, optype); wake_up(&server->request_q); + credits->value = 0; } } @@ -1060,12 +1076,14 @@ struct cifs_ses { and after mount option parsing we fill it */ char *domainName; char *password; + char *password2; /* When key rotation used, new password may be set before it expires */ char workstation_name[CIFS_MAX_WORKSTATION_LEN]; struct session_key auth_key; struct ntlmssp_auth *ntlmssp; /* ciphertext, flags, server challenge */ enum securityEnum sectype; /* what security flavor was specified? */ bool sign; /* is signing required? */ bool domainAuto:1; + bool expired_pwd; /* track if access denied or expired pwd so can know if need to update */ unsigned int flags; __u16 session_flags; __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; @@ -1171,6 +1189,7 @@ struct cifs_fattr { */ struct cifs_tcon { struct list_head tcon_list; + int debug_id; /* Debugging for tracing */ int tc_count; struct list_head rlist; /* reconnect list */ spinlock_t tc_lock; /* protect anything here that is not protected */ @@ -1257,13 +1276,14 @@ struct cifs_tcon { __u32 max_cached_dirs; #ifdef CONFIG_CIFS_FSCACHE u64 resource_id; /* server resource id */ + bool fscache_acquired; /* T if we've tried acquiring a cookie */ struct fscache_volume *fscache; /* cookie for share */ + struct mutex fscache_lock; /* Prevent regetting a cookie */ #endif struct list_head pending_opens; /* list of incomplete opens */ struct cached_fids *cfids; /* BB add field for back pointer to sb struct(s)? */ #ifdef CONFIG_CIFS_DFS_UPCALL - struct list_head dfs_ses_list; struct delayed_work dfs_cache_work; #endif struct delayed_work query_interfaces; /* query interfaces workqueue job */ @@ -1379,6 +1399,7 @@ struct cifs_open_parms { umode_t mode; bool reconnect:1; bool replay:1; /* indicates that this open is for a replay */ + struct kvec *ea_cctx; }; struct cifs_fid { @@ -1420,6 +1441,8 @@ struct cifsFileInfo { bool invalidHandle:1; /* file closed via session abend */ bool swapfile:1; bool oplock_break_cancelled:1; + bool status_file_deleted:1; /* file has been deleted */ + bool offload:1; /* offload final part of _put to a wq */ unsigned int oplock_epoch; /* epoch from the lease break */ __u32 oplock_level; /* oplock/lease level from the lease break */ int count; @@ -1428,6 +1451,7 @@ struct cifsFileInfo { struct cifs_search_info srch_inf; struct work_struct oplock_break; /* work for oplock breaks */ struct work_struct put; /* work for the final part of _put */ + struct work_struct serverclose; /* work for serverclose */ struct delayed_work deferred; bool deferred_close_scheduled; /* Flag to indicate close is scheduled */ char *symlink_target; @@ -1467,50 +1491,30 @@ struct cifs_aio_ctx { bool direct_io; }; -/* asynchronous read support */ -struct cifs_readdata { - struct kref refcount; - struct list_head list; - struct completion done; +struct cifs_io_request { + struct netfs_io_request rreq; struct cifsFileInfo *cfile; - struct address_space *mapping; - struct cifs_aio_ctx *ctx; - __u64 offset; - ssize_t got_bytes; - unsigned int bytes; - pid_t pid; - int result; - struct work_struct work; - struct iov_iter iter; - struct kvec iov[2]; - struct TCP_Server_Info *server; -#ifdef CONFIG_CIFS_SMB_DIRECT - struct smbd_mr *mr; -#endif - struct cifs_credits credits; }; -/* asynchronous write support */ -struct cifs_writedata { - struct kref refcount; - struct list_head list; - struct completion done; - enum writeback_sync_modes sync_mode; - struct work_struct work; - struct cifsFileInfo *cfile; - struct cifs_aio_ctx *ctx; - struct iov_iter iter; - struct bio_vec *bv; - __u64 offset; +/* asynchronous read support */ +struct cifs_io_subrequest { + union { + struct netfs_io_subrequest subreq; + struct netfs_io_request *rreq; + struct cifs_io_request *req; + }; + ssize_t got_bytes; pid_t pid; - unsigned int bytes; + unsigned int xid; int result; + bool have_xid; + bool replay; + struct kvec iov[2]; struct TCP_Server_Info *server; #ifdef CONFIG_CIFS_SMB_DIRECT struct smbd_mr *mr; #endif struct cifs_credits credits; - bool replay; }; /* @@ -1784,7 +1788,6 @@ struct cifs_mount_ctx { struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; - struct list_head dfs_ses_list; }; static inline void __free_dfs_info_param(struct dfs_info3_param *param) @@ -1992,6 +1995,7 @@ require use of the stronger protocol */ * ->chans_need_reconnect * ->chans_in_reconnect * cifs_tcon->tc_lock (anything that is not protected by another lock and can change) + * inode->i_rwsem, taken by fs/netfs/locking.c e.g. should be taken before cifsInodeInfo locks * cifsInodeInfo->open_file_lock cifsInodeInfo->openFileList cifs_alloc_inode * cifsInodeInfo->writers_lock cifsInodeInfo->writers cifsInodeInfo_alloc * cifsInodeInfo->lock_sem cifsInodeInfo->llist cifs_init_once @@ -2085,9 +2089,14 @@ extern struct workqueue_struct *decrypt_wq; extern struct workqueue_struct *fileinfo_put_wq; extern struct workqueue_struct *cifsoplockd_wq; extern struct workqueue_struct *deferredclose_wq; +extern struct workqueue_struct *serverclose_wq; extern __u32 cifs_lock_secret; +extern mempool_t *cifs_sm_req_poolp; +extern mempool_t *cifs_req_poolp; extern mempool_t *cifs_mid_poolp; +extern mempool_t cifs_io_request_pool; +extern mempool_t cifs_io_subrequest_pool; /* Operations for different SMB versions */ #define SMB1_VERSION_STRING "1.0" @@ -2277,6 +2286,17 @@ static inline void cifs_sg_set_buf(struct sg_table *sgtable, } } +#define CIFS_OPARMS(_cifs_sb, _tcon, _path, _da, _cd, _co, _mode) \ + ((struct cifs_open_parms) { \ + .tcon = _tcon, \ + .path = _path, \ + .desired_access = (_da), \ + .disposition = (_cd), \ + .create_options = cifs_create_options(_cifs_sb, (_co)), \ + .mode = (_mode), \ + .cifs_sb = _cifs_sb, \ + }) + struct smb2_compound_vars { struct cifs_open_parms oparms; struct kvec rsp_iov[MAX_COMPOUND]; @@ -2288,6 +2308,17 @@ struct smb2_compound_vars { struct kvec close_iov; struct smb2_file_rename_info rename_info; struct smb2_file_link_info link_info; + struct kvec ea_iov; }; +static inline bool cifs_ses_exiting(struct cifs_ses *ses) +{ + bool ret; + + spin_lock(&ses->ses_lock); + ret = ses->ses_status == SES_EXITING; + spin_unlock(&ses->ses_lock); + return ret; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index c0513fbb8a59..c46d418c1c0c 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -882,7 +882,7 @@ typedef struct smb_com_open_rsp { __u8 OplockLevel; __u16 Fid; __le32 CreateAction; - struct_group(common_attributes, + struct_group_attr(common_attributes, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; @@ -2266,7 +2266,7 @@ typedef struct { /* QueryFileInfo/QueryPathinfo (also for SetPath/SetFile) data buffer formats */ /******************************************************************************/ typedef struct { /* data block encoding of response to level 263 QPathInfo */ - struct_group(common_attributes, + struct_group_attr(common_attributes, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index a841bf4967fa..c15bb5ee7eb7 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -121,7 +121,7 @@ extern struct mid_q_entry *cifs_setup_async_request(struct TCP_Server_Info *, 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, + size_t size, size_t *num, struct cifs_credits *credits); extern int SendReceive2(const unsigned int /* xid */ , struct cifs_ses *, struct kvec *, int /* nvec to send */, @@ -144,9 +144,12 @@ extern int cifs_reconnect(struct TCP_Server_Info *server, extern int checkSMB(char *buf, unsigned int len, struct TCP_Server_Info *srvr); extern bool is_valid_oplock_break(char *, struct TCP_Server_Info *); extern bool backup_cred(struct cifs_sb_info *); -extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof); +extern bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 eof, + bool from_readdir); extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset, unsigned int bytes_written); +void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result, + bool was_async); extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, int); extern int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags, @@ -201,17 +204,14 @@ extern void cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb); extern void cifs_dir_info_to_fattr(struct cifs_fattr *, FILE_DIRECTORY_INFO *, struct cifs_sb_info *); -extern int cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr); +extern int cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, + bool from_readdir); extern struct inode *cifs_iget(struct super_block *sb, struct cifs_fattr *fattr); int cifs_get_inode_info(struct inode **inode, const char *full_path, struct cifs_open_info_data *data, struct super_block *sb, int xid, const struct cifs_fid *fid); -bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, - struct cifs_fattr *fattr, - struct cifs_open_info_data *data); - extern int smb311_posix_get_inode_info(struct inode **inode, const char *full_path, struct cifs_open_info_data *data, @@ -296,12 +296,16 @@ extern void cifs_close_all_deferred_files(struct cifs_tcon *cifs_tcon); extern void cifs_close_deferred_file_under_dentry(struct cifs_tcon *cifs_tcon, const char *path); + +extern void cifs_mark_open_handles_for_deleted_file(struct inode *inode, + const char *path); + extern struct TCP_Server_Info * cifs_get_tcp_session(struct smb3_fs_context *ctx, struct TCP_Server_Info *primary_server); extern void cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect); -extern void cifs_put_tcon(struct cifs_tcon *tcon); +extern void cifs_put_tcon(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace); extern void cifs_release_automount_timer(void); @@ -402,7 +406,8 @@ extern int CIFSSMBSetFileDisposition(const unsigned int xid, __u32 pid_of_opener); extern int CIFSSMBSetEOF(const unsigned int xid, struct cifs_tcon *tcon, const char *file_name, __u64 size, - struct cifs_sb_info *cifs_sb, bool set_allocation); + struct cifs_sb_info *cifs_sb, bool set_allocation, + struct dentry *dentry); extern int CIFSSMBSetFileSize(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *cfile, __u64 size, bool set_allocation); @@ -438,7 +443,8 @@ extern int CIFSPOSIXDelFile(const unsigned int xid, struct cifs_tcon *tcon, const struct nls_table *nls_codepage, int remap_special_chars); extern int CIFSSMBDelFile(const unsigned int xid, struct cifs_tcon *tcon, - const char *name, struct cifs_sb_info *cifs_sb); + const char *name, struct cifs_sb_info *cifs_sb, + struct dentry *dentry); int CIFSSMBRename(const unsigned int xid, struct cifs_tcon *tcon, struct dentry *source_dentry, const char *from_name, const char *to_name, @@ -526,8 +532,9 @@ extern int CIFSSMBLogoff(const unsigned int xid, struct cifs_ses *ses); extern struct cifs_ses *sesInfoAlloc(void); extern void sesInfoFree(struct cifs_ses *); -extern struct cifs_tcon *tcon_info_alloc(bool dir_leases_enabled); -extern void tconInfoFree(struct cifs_tcon *); +extern struct cifs_tcon *tcon_info_alloc(bool dir_leases_enabled, + enum smb3_tcon_ref_trace trace); +extern void tconInfoFree(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace); extern int cifs_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server, __u32 *pexpected_response_sequence_number); @@ -594,15 +601,11 @@ void __cifs_put_smb_ses(struct cifs_ses *ses); extern struct cifs_ses * cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx); -void cifs_readdata_release(struct kref *refcount); -int cifs_async_readv(struct cifs_readdata *rdata); +int cifs_async_readv(struct cifs_io_subrequest *rdata); int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid); -int cifs_async_writev(struct cifs_writedata *wdata, - void (*release)(struct kref *kref)); +void cifs_async_writev(struct cifs_io_subrequest *wdata); void cifs_writev_complete(struct work_struct *work); -struct cifs_writedata *cifs_writedata_alloc(work_func_t complete); -void cifs_writedata_release(struct kref *refcount); int cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const unsigned char *path, char *pbuf, @@ -717,35 +720,33 @@ static inline int cifs_create_options(struct cifs_sb_info *cifs_sb, int options) return options; } -struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon); -void cifs_put_tcon_super(struct super_block *sb); int cifs_wait_for_server_reconnect(struct TCP_Server_Info *server, bool retry); -/* Put references of @ses and @ses->dfs_root_ses */ +/* Put references of @ses and its children */ static inline void cifs_put_smb_ses(struct cifs_ses *ses) { - struct cifs_ses *rses = ses->dfs_root_ses; + struct cifs_ses *next; - __cifs_put_smb_ses(ses); - if (rses) - __cifs_put_smb_ses(rses); + do { + next = ses->dfs_root_ses; + __cifs_put_smb_ses(ses); + } while ((ses = next)); } -/* Get an active reference of @ses and @ses->dfs_root_ses. +/* Get an active reference of @ses and its children. * * NOTE: make sure to call this function when incrementing reference count of * @ses to ensure that any DFS root session attached to it (@ses->dfs_root_ses) * will also get its reference count incremented. * - * cifs_put_smb_ses() will put both references, so call it when you're done. + * cifs_put_smb_ses() will put all references, so call it when you're done. */ static inline void cifs_smb_ses_inc_refcount(struct cifs_ses *ses) { lockdep_assert_held(&cifs_tcp_ses_lock); - ses->ses_count++; - if (ses->dfs_root_ses) - ses->dfs_root_ses->ses_count++; + for (; ses; ses = ses->dfs_root_ses) + ses->ses_count++; } static inline bool dfs_src_pathname_equal(const char *s1, const char *s2) diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 01e89070df5a..25e9ab947c17 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -24,6 +24,8 @@ #include <linux/swap.h> #include <linux/task_io_accounting_ops.h> #include <linux/uaccess.h> +#include <linux/netfs.h> +#include <trace/events/netfs.h> #include "cifspdu.h" #include "cifsfs.h" #include "cifsglob.h" @@ -738,7 +740,7 @@ PsxDelete: int CIFSSMBDelFile(const unsigned int xid, struct cifs_tcon *tcon, const char *name, - struct cifs_sb_info *cifs_sb) + struct cifs_sb_info *cifs_sb, struct dentry *dentry) { DELETE_FILE_REQ *pSMB = NULL; DELETE_FILE_RSP *pSMBr = NULL; @@ -1262,18 +1264,17 @@ openRetry: static void cifs_readv_callback(struct mid_q_entry *mid) { - struct cifs_readdata *rdata = mid->callback_data; - struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink); + struct cifs_io_subrequest *rdata = mid->callback_data; + struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; struct smb_rqst rqst = { .rq_iov = rdata->iov, .rq_nvec = 2, - .rq_iter_size = iov_iter_count(&rdata->iter), - .rq_iter = rdata->iter }; + .rq_iter = rdata->subreq.io_iter }; struct cifs_credits credits = { .value = 1, .instance = 0 }; - cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%u\n", + cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n", __func__, mid->mid, mid->mid_state, rdata->result, - rdata->bytes); + rdata->subreq.len); switch (mid->mid_state) { case MID_RESPONSE_RECEIVED: @@ -1305,30 +1306,36 @@ cifs_readv_callback(struct mid_q_entry *mid) rdata->result = -EIO; } - queue_work(cifsiod_wq, &rdata->work); + if (rdata->result == 0 || rdata->result == -EAGAIN) + iov_iter_advance(&rdata->subreq.io_iter, rdata->got_bytes); + rdata->credits.value = 0; + netfs_subreq_terminated(&rdata->subreq, + (rdata->result == 0 || rdata->result == -EAGAIN) ? + rdata->got_bytes : rdata->result, + false); release_mid(mid); add_credits(server, &credits, 0); } /* cifs_async_readv - send an async write, and set up mid to handle result */ int -cifs_async_readv(struct cifs_readdata *rdata) +cifs_async_readv(struct cifs_io_subrequest *rdata) { int rc; READ_REQ *smb = NULL; int wct; - struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink); + struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); struct smb_rqst rqst = { .rq_iov = rdata->iov, .rq_nvec = 2 }; - cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n", - __func__, rdata->offset, rdata->bytes); + cifs_dbg(FYI, "%s: offset=%llu bytes=%zu\n", + __func__, rdata->subreq.start, rdata->subreq.len); if (tcon->ses->capabilities & CAP_LARGE_FILES) wct = 12; else { wct = 10; /* old style read */ - if ((rdata->offset >> 32) > 0) { + if ((rdata->subreq.start >> 32) > 0) { /* can not handle this big offset for old */ return -EIO; } @@ -1342,13 +1349,13 @@ cifs_async_readv(struct cifs_readdata *rdata) smb->hdr.PidHigh = cpu_to_le16((__u16)(rdata->pid >> 16)); smb->AndXCommand = 0xFF; /* none */ - smb->Fid = rdata->cfile->fid.netfid; - smb->OffsetLow = cpu_to_le32(rdata->offset & 0xFFFFFFFF); + smb->Fid = rdata->req->cfile->fid.netfid; + smb->OffsetLow = cpu_to_le32(rdata->subreq.start & 0xFFFFFFFF); if (wct == 12) - smb->OffsetHigh = cpu_to_le32(rdata->offset >> 32); + smb->OffsetHigh = cpu_to_le32(rdata->subreq.start >> 32); smb->Remaining = 0; - smb->MaxCount = cpu_to_le16(rdata->bytes & 0xFFFF); - smb->MaxCountHigh = cpu_to_le32(rdata->bytes >> 16); + smb->MaxCount = cpu_to_le16(rdata->subreq.len & 0xFFFF); + smb->MaxCountHigh = cpu_to_le32(rdata->subreq.len >> 16); if (wct == 12) smb->ByteCount = 0; else { @@ -1364,15 +1371,11 @@ cifs_async_readv(struct cifs_readdata *rdata) rdata->iov[1].iov_base = (char *)smb + 4; rdata->iov[1].iov_len = get_rfc1002_length(smb); - kref_get(&rdata->refcount); rc = cifs_call_async(tcon->ses->server, &rqst, cifs_readv_receive, cifs_readv_callback, NULL, rdata, 0, NULL); if (rc == 0) cifs_stats_inc(&tcon->stats.cifs_stats.num_reads); - else - kref_put(&rdata->refcount, cifs_readdata_release); - cifs_small_buf_release(smb); return rc; } @@ -1615,16 +1618,17 @@ CIFSSMBWrite(const unsigned int xid, struct cifs_io_parms *io_parms, static void cifs_writev_callback(struct mid_q_entry *mid) { - struct cifs_writedata *wdata = mid->callback_data; - struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink); - unsigned int written; + struct cifs_io_subrequest *wdata = mid->callback_data; + struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink); WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf; struct cifs_credits credits = { .value = 1, .instance = 0 }; + ssize_t result; + size_t written; switch (mid->mid_state) { case MID_RESPONSE_RECEIVED: - wdata->result = cifs_check_receive(mid, tcon->ses->server, 0); - if (wdata->result != 0) + result = cifs_check_receive(mid, tcon->ses->server, 0); + if (result != 0) break; written = le16_to_cpu(smb->CountHigh); @@ -1636,37 +1640,37 @@ cifs_writev_callback(struct mid_q_entry *mid) * client. OS/2 servers are known to set incorrect * CountHigh values. */ - if (written > wdata->bytes) + if (written > wdata->subreq.len) written &= 0xFFFF; - if (written < wdata->bytes) - wdata->result = -ENOSPC; + if (written < wdata->subreq.len) + result = -ENOSPC; else - wdata->bytes = written; + result = written; break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: - wdata->result = -EAGAIN; + result = -EAGAIN; break; default: - wdata->result = -EIO; + result = -EIO; break; } - queue_work(cifsiod_wq, &wdata->work); + wdata->credits.value = 0; + cifs_write_subrequest_terminated(wdata, result, true); release_mid(mid); add_credits(tcon->ses->server, &credits, 0); } /* cifs_async_writev - send an async write, and set up mid to handle result */ -int -cifs_async_writev(struct cifs_writedata *wdata, - void (*release)(struct kref *kref)) +void +cifs_async_writev(struct cifs_io_subrequest *wdata) { int rc = -EACCES; WRITE_REQ *smb = NULL; int wct; - struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink); + struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink); struct kvec iov[2]; struct smb_rqst rqst = { }; @@ -1674,9 +1678,10 @@ cifs_async_writev(struct cifs_writedata *wdata, wct = 14; } else { wct = 12; - if (wdata->offset >> 32 > 0) { + if (wdata->subreq.start >> 32 > 0) { /* can not handle big offset for old srv */ - return -EIO; + rc = -EIO; + goto out; } } @@ -1688,10 +1693,10 @@ cifs_async_writev(struct cifs_writedata *wdata, smb->hdr.PidHigh = cpu_to_le16((__u16)(wdata->pid >> 16)); smb->AndXCommand = 0xFF; /* none */ - smb->Fid = wdata->cfile->fid.netfid; - smb->OffsetLow = cpu_to_le32(wdata->offset & 0xFFFFFFFF); + smb->Fid = wdata->req->cfile->fid.netfid; + smb->OffsetLow = cpu_to_le32(wdata->subreq.start & 0xFFFFFFFF); if (wct == 14) - smb->OffsetHigh = cpu_to_le32(wdata->offset >> 32); + smb->OffsetHigh = cpu_to_le32(wdata->subreq.start >> 32); smb->Reserved = 0xFFFFFFFF; smb->WriteMode = 0; smb->Remaining = 0; @@ -1707,39 +1712,40 @@ cifs_async_writev(struct cifs_writedata *wdata, rqst.rq_iov = iov; rqst.rq_nvec = 2; - rqst.rq_iter = wdata->iter; - rqst.rq_iter_size = iov_iter_count(&wdata->iter); + rqst.rq_iter = wdata->subreq.io_iter; + rqst.rq_iter_size = iov_iter_count(&wdata->subreq.io_iter); - cifs_dbg(FYI, "async write at %llu %u bytes\n", - wdata->offset, wdata->bytes); + cifs_dbg(FYI, "async write at %llu %zu bytes\n", + wdata->subreq.start, wdata->subreq.len); - smb->DataLengthLow = cpu_to_le16(wdata->bytes & 0xFFFF); - smb->DataLengthHigh = cpu_to_le16(wdata->bytes >> 16); + smb->DataLengthLow = cpu_to_le16(wdata->subreq.len & 0xFFFF); + smb->DataLengthHigh = cpu_to_le16(wdata->subreq.len >> 16); if (wct == 14) { - inc_rfc1001_len(&smb->hdr, wdata->bytes + 1); - put_bcc(wdata->bytes + 1, &smb->hdr); + inc_rfc1001_len(&smb->hdr, wdata->subreq.len + 1); + put_bcc(wdata->subreq.len + 1, &smb->hdr); } else { /* wct == 12 */ struct smb_com_writex_req *smbw = (struct smb_com_writex_req *)smb; - inc_rfc1001_len(&smbw->hdr, wdata->bytes + 5); - put_bcc(wdata->bytes + 5, &smbw->hdr); + inc_rfc1001_len(&smbw->hdr, wdata->subreq.len + 5); + put_bcc(wdata->subreq.len + 5, &smbw->hdr); iov[1].iov_len += 4; /* pad bigger by four bytes */ } - kref_get(&wdata->refcount); rc = cifs_call_async(tcon->ses->server, &rqst, NULL, cifs_writev_callback, NULL, wdata, 0, NULL); - + /* Can't touch wdata if rc == 0 */ if (rc == 0) cifs_stats_inc(&tcon->stats.cifs_stats.num_writes); - else - kref_put(&wdata->refcount, release); async_writev_out: cifs_small_buf_release(smb); - return rc; +out: + if (rc) { + add_credits_and_wake_if(wdata->server, &wdata->credits, 0); + cifs_write_subrequest_terminated(wdata, rc, false); + } } int @@ -2066,20 +2072,20 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon, parm_data = (struct cifs_posix_lock *) ((char *)&pSMBr->hdr.Protocol + data_offset); if (parm_data->lock_type == cpu_to_le16(CIFS_UNLCK)) - pLockData->fl_type = F_UNLCK; + pLockData->c.flc_type = F_UNLCK; else { if (parm_data->lock_type == cpu_to_le16(CIFS_RDLCK)) - pLockData->fl_type = F_RDLCK; + pLockData->c.flc_type = F_RDLCK; else if (parm_data->lock_type == cpu_to_le16(CIFS_WRLCK)) - pLockData->fl_type = F_WRLCK; + pLockData->c.flc_type = F_WRLCK; pLockData->fl_start = le64_to_cpu(parm_data->start); pLockData->fl_end = pLockData->fl_start + (le64_to_cpu(parm_data->length) ? le64_to_cpu(parm_data->length) - 1 : 0); - pLockData->fl_pid = -le32_to_cpu(parm_data->pid); + pLockData->c.flc_pid = -le32_to_cpu(parm_data->pid); } } @@ -4993,7 +4999,7 @@ QFSPosixRetry: int CIFSSMBSetEOF(const unsigned int xid, struct cifs_tcon *tcon, const char *file_name, __u64 size, struct cifs_sb_info *cifs_sb, - bool set_allocation) + bool set_allocation, struct dentry *dentry) { struct smb_com_transaction2_spi_req *pSMB = NULL; struct smb_com_transaction2_spi_rsp *pSMBr = NULL; @@ -5854,10 +5860,8 @@ SetEARetry: parm_data->list.EA_flags = 0; /* we checked above that name len is less than 255 */ parm_data->list.name_len = (__u8)name_len; - /* EA names are always ASCII */ - if (ea_name) - strncpy(parm_data->list.name, ea_name, name_len); - parm_data->list.name[name_len] = '\0'; + /* EA names are always ASCII and NUL-terminated */ + strscpy(parm_data->list.name, ea_name ?: "", name_len + 1); parm_data->list.value_len = cpu_to_le16(ea_value_len); /* caller ensures that ea_value_len is less than 64K but we need to ensure that it fits within the smb */ diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index ac9595504f4b..7a16e12f5da8 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -52,9 +52,6 @@ #include "fs_context.h" #include "cifs_swn.h" -extern mempool_t *cifs_req_poolp; -extern bool disable_legacy_dialects; - /* FIXME: should these be tunable? */ #define TLINK_ERROR_EXPIRE (1 * HZ) #define TLINK_IDLE_EXPIRE (600 * HZ) @@ -123,12 +120,16 @@ static void smb2_query_server_interfaces(struct work_struct *work) struct cifs_tcon *tcon = container_of(work, struct cifs_tcon, query_interfaces.work); + struct TCP_Server_Info *server = tcon->ses->server; /* * query server network interfaces, in case they change */ + if (!server->ops->query_server_interfaces) + return; + xid = get_xid(); - rc = SMB3_request_interfaces(xid, tcon, false); + rc = server->ops->query_server_interfaces(xid, tcon, false); free_xid(xid); if (rc) { @@ -174,6 +175,8 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; spin_lock(&ses->chan_lock); for (i = 0; i < ses->chan_count; i++) { if (!ses->chans[i].server) @@ -231,7 +234,13 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) { - /* check if iface is still active */ + spin_lock(&ses->ses_lock); + if (ses->ses_status == SES_EXITING) { + spin_unlock(&ses->ses_lock); + continue; + } + spin_unlock(&ses->ses_lock); + spin_lock(&ses->chan_lock); if (cifs_ses_get_chan_index(ses, server) == CIFS_INVAL_CHAN_INDEX) { @@ -1736,7 +1745,7 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, tcp_ses->channel_sequence_num = 0; /* only tracked for primary channel */ tcp_ses->reconnect_instance = 1; tcp_ses->lstrp = jiffies; - tcp_ses->compress_algorithm = cpu_to_le16(ctx->compression); + tcp_ses->compression.requested = ctx->compress; spin_lock_init(&tcp_ses->req_lock); spin_lock_init(&tcp_ses->srv_lock); spin_lock_init(&tcp_ses->mid_lock); @@ -1859,6 +1868,9 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) ctx->sectype != ses->sectype) return 0; + if (ctx->dfs_root_ses != ses->dfs_root_ses) + return 0; + /* * If an existing session is limited to less channels than * requested, it should not be reused @@ -1931,7 +1943,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) } /* no need to setup directory caching on IPC share, so pass in false */ - tcon = tcon_info_alloc(false); + tcon = tcon_info_alloc(false, netfs_trace_tcon_ref_new_ipc); if (tcon == NULL) return -ENOMEM; @@ -1948,7 +1960,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) if (rc) { cifs_server_dbg(VFS, "failed to connect to IPC (rc=%d)\n", rc); - tconInfoFree(tcon); + tconInfoFree(tcon, netfs_trace_tcon_ref_free_ipc_fail); goto out; } @@ -1962,31 +1974,6 @@ out: return rc; } -/** - * cifs_free_ipc - helper to release the session IPC tcon - * @ses: smb session to unmount the IPC from - * - * Needs to be called everytime a session is destroyed. - * - * On session close, the IPC is closed and the server must release all tcons of the session. - * No need to send a tree disconnect here. - * - * Besides, it will make the server to not close durable and resilient files on session close, as - * specified in MS-SMB2 3.3.5.6 Receiving an SMB2 LOGOFF Request. - */ -static int -cifs_free_ipc(struct cifs_ses *ses) -{ - struct cifs_tcon *tcon = ses->tcon_ipc; - - if (tcon == NULL) - return 0; - - tconInfoFree(tcon); - ses->tcon_ipc = NULL; - return 0; -} - static struct cifs_ses * cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) { @@ -2018,48 +2005,52 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) void __cifs_put_smb_ses(struct cifs_ses *ses) { struct TCP_Server_Info *server = ses->server; + struct cifs_tcon *tcon; unsigned int xid; size_t i; + bool do_logoff; int rc; + spin_lock(&cifs_tcp_ses_lock); spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_EXITING) { + cifs_dbg(FYI, "%s: id=0x%llx ses_count=%d ses_status=%u ipc=%s\n", + __func__, ses->Suid, ses->ses_count, ses->ses_status, + ses->tcon_ipc ? ses->tcon_ipc->tree_name : "none"); + if (ses->ses_status == SES_EXITING || --ses->ses_count > 0) { spin_unlock(&ses->ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return; } - spin_unlock(&ses->ses_lock); + /* ses_count can never go negative */ + WARN_ON(ses->ses_count < 0); - cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count); - cifs_dbg(FYI, - "%s: ses ipc: %s\n", __func__, ses->tcon_ipc ? ses->tcon_ipc->tree_name : "NONE"); + spin_lock(&ses->chan_lock); + cifs_chan_clear_need_reconnect(ses, server); + spin_unlock(&ses->chan_lock); - spin_lock(&cifs_tcp_ses_lock); - if (--ses->ses_count > 0) { - spin_unlock(&cifs_tcp_ses_lock); - return; - } - spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_GOOD) - ses->ses_status = SES_EXITING; + do_logoff = ses->ses_status == SES_GOOD && server->ops->logoff; + ses->ses_status = SES_EXITING; + tcon = ses->tcon_ipc; + ses->tcon_ipc = NULL; spin_unlock(&ses->ses_lock); spin_unlock(&cifs_tcp_ses_lock); - /* ses_count can never go negative */ - WARN_ON(ses->ses_count < 0); - - spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_EXITING && server->ops->logoff) { - spin_unlock(&ses->ses_lock); - cifs_free_ipc(ses); + /* + * On session close, the IPC is closed and the server must release all + * tcons of the session. No need to send a tree disconnect here. + * + * Besides, it will make the server to not close durable and resilient + * files on session close, as specified in MS-SMB2 3.3.5.6 Receiving an + * SMB2 LOGOFF Request. + */ + tconInfoFree(tcon, netfs_trace_tcon_ref_free_ipc); + if (do_logoff) { xid = get_xid(); rc = server->ops->logoff(xid, ses); if (rc) cifs_server_dbg(VFS, "%s: Session Logoff failure rc=%d\n", __func__, rc); _free_xid(xid); - } else { - spin_unlock(&ses->ses_lock); - cifs_free_ipc(ses); } spin_lock(&cifs_tcp_ses_lock); @@ -2192,6 +2183,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) } ++delim; + /* BB consider adding support for password2 (Key Rotation) for multiuser in future */ ctx->password = kstrndup(delim, len, GFP_KERNEL); if (!ctx->password) { cifs_dbg(FYI, "Unable to allocate %zd bytes for password\n", @@ -2215,6 +2207,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) kfree(ctx->username); ctx->username = NULL; kfree_sensitive(ctx->password); + /* no need to free ctx->password2 since not allocated in this path */ ctx->password = NULL; goto out_key_put; } @@ -2326,6 +2319,12 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) if (!ses->password) goto get_ses_fail; } + /* ctx->password freed at unmount */ + if (ctx->password2) { + ses->password2 = kstrdup(ctx->password2, GFP_KERNEL); + if (!ses->password2) + goto get_ses_fail; + } if (ctx->domainname) { ses->domainName = kstrdup(ctx->domainname, GFP_KERNEL); if (!ses->domainName) @@ -2372,9 +2371,9 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) * need to lock before changing something in the session. */ spin_lock(&cifs_tcp_ses_lock); + if (ctx->dfs_root_ses) + cifs_smb_ses_inc_refcount(ctx->dfs_root_ses); ses->dfs_root_ses = ctx->dfs_root_ses; - if (ses->dfs_root_ses) - ses->dfs_root_ses->ses_count++; list_add(&ses->smb_ses_list, &server->smb_ses_list); spin_unlock(&cifs_tcp_ses_lock); @@ -2433,6 +2432,8 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) continue; } ++tcon->tc_count; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_get_find); spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); return tcon; @@ -2442,7 +2443,7 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) } void -cifs_put_tcon(struct cifs_tcon *tcon) +cifs_put_tcon(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace) { unsigned int xid; struct cifs_ses *ses; @@ -2458,6 +2459,7 @@ cifs_put_tcon(struct cifs_tcon *tcon) cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count); spin_lock(&cifs_tcp_ses_lock); spin_lock(&tcon->tc_lock); + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count - 1, trace); if (--tcon->tc_count > 0) { spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); @@ -2494,7 +2496,7 @@ cifs_put_tcon(struct cifs_tcon *tcon) _free_xid(xid); cifs_fscache_release_super_cookie(tcon); - tconInfoFree(tcon); + tconInfoFree(tcon, netfs_trace_tcon_ref_free); cifs_put_smb_ses(ses); } @@ -2548,7 +2550,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) nohandlecache = ctx->nohandlecache; else nohandlecache = true; - tcon = tcon_info_alloc(!nohandlecache); + tcon = tcon_info_alloc(!nohandlecache, netfs_trace_tcon_ref_new); if (tcon == NULL) { rc = -ENOMEM; goto out_fail; @@ -2738,7 +2740,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) return tcon; out_fail: - tconInfoFree(tcon); + tconInfoFree(tcon, netfs_trace_tcon_ref_free_fail); return ERR_PTR(rc); } @@ -2755,7 +2757,7 @@ cifs_put_tlink(struct tcon_link *tlink) } if (!IS_ERR(tlink_tcon(tlink))) - cifs_put_tcon(tlink_tcon(tlink)); + cifs_put_tcon(tlink_tcon(tlink), netfs_trace_tcon_ref_put_tlink); kfree(tlink); } @@ -2803,6 +2805,8 @@ compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data) return 0; if (old->ctx->closetimeo != new->ctx->closetimeo) return 0; + if (old->ctx->reparse_type != new->ctx->reparse_type) + return 0; return 1; } @@ -3318,11 +3322,14 @@ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx) int rc = 0; if (mnt_ctx->tcon) - cifs_put_tcon(mnt_ctx->tcon); + cifs_put_tcon(mnt_ctx->tcon, netfs_trace_tcon_ref_put_mnt_ctx); else if (mnt_ctx->ses) cifs_put_smb_ses(mnt_ctx->ses); else if (mnt_ctx->server) cifs_put_tcp_session(mnt_ctx->server, 0); + mnt_ctx->ses = NULL; + mnt_ctx->tcon = NULL; + mnt_ctx->server = NULL; mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS; free_xid(mnt_ctx->xid); } @@ -3601,8 +3608,6 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) bool isdfs; int rc; - INIT_LIST_HEAD(&mnt_ctx.dfs_ses_list); - rc = dfs_mount_share(&mnt_ctx, &isdfs); if (rc) goto error; @@ -3633,7 +3638,6 @@ out: return rc; error: - dfs_put_root_smb_sessions(&mnt_ctx.dfs_ses_list); cifs_mount_put_conns(&mnt_ctx); return rc; } @@ -3648,6 +3652,18 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) goto error; rc = cifs_mount_get_tcon(&mnt_ctx); + if (!rc) { + /* + * Prevent superblock from being created with any missing + * connections. + */ + if (WARN_ON(!mnt_ctx.server)) + rc = -EHOSTDOWN; + else if (WARN_ON(!mnt_ctx.ses)) + rc = -EACCES; + else if (WARN_ON(!mnt_ctx.tcon)) + rc = -ENOENT; + } if (rc) goto error; @@ -3985,13 +4001,14 @@ cifs_set_vol_auth(struct smb3_fs_context *ctx, struct cifs_ses *ses) } static struct cifs_tcon * -cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) +__cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) { int rc; struct cifs_tcon *master_tcon = cifs_sb_master_tcon(cifs_sb); struct cifs_ses *ses; struct cifs_tcon *tcon = NULL; struct smb3_fs_context *ctx; + char *origin_fullpath = NULL; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (ctx == NULL) @@ -4015,6 +4032,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) ctx->sign = master_tcon->ses->sign; ctx->seal = master_tcon->seal; ctx->witness = master_tcon->use_witness; + ctx->dfs_root_ses = master_tcon->ses->dfs_root_ses; rc = cifs_set_vol_auth(ctx, master_tcon->ses); if (rc) { @@ -4034,12 +4052,39 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) goto out; } +#ifdef CONFIG_CIFS_DFS_UPCALL + spin_lock(&master_tcon->tc_lock); + if (master_tcon->origin_fullpath) { + spin_unlock(&master_tcon->tc_lock); + origin_fullpath = dfs_get_path(cifs_sb, cifs_sb->ctx->source); + if (IS_ERR(origin_fullpath)) { + tcon = ERR_CAST(origin_fullpath); + origin_fullpath = NULL; + cifs_put_smb_ses(ses); + goto out; + } + } else { + spin_unlock(&master_tcon->tc_lock); + } +#endif + tcon = cifs_get_tcon(ses, ctx); if (IS_ERR(tcon)) { cifs_put_smb_ses(ses); goto out; } +#ifdef CONFIG_CIFS_DFS_UPCALL + if (origin_fullpath) { + spin_lock(&tcon->tc_lock); + tcon->origin_fullpath = origin_fullpath; + spin_unlock(&tcon->tc_lock); + origin_fullpath = NULL; + queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, + dfs_cache_get_ttl() * HZ); + } +#endif + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(ses)) reset_cifs_unix_caps(0, tcon, NULL, ctx); @@ -4048,11 +4093,23 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) out: kfree(ctx->username); kfree_sensitive(ctx->password); + kfree(origin_fullpath); kfree(ctx); return tcon; } +static struct cifs_tcon * +cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) +{ + struct cifs_tcon *ret; + + cifs_mount_lock(); + ret = __cifs_construct_tcon(cifs_sb, fsuid); + cifs_mount_unlock(); + return ret; +} + struct cifs_tcon * cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb) { diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index 449c59830039..3ec965547e3d 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -66,33 +66,20 @@ static int get_session(struct cifs_mount_ctx *mnt_ctx, const char *full_path) } /* - * Track individual DFS referral servers used by new DFS mount. - * - * On success, their lifetime will be shared by final tcon (dfs_ses_list). - * Otherwise, they will be put by dfs_put_root_smb_sessions() in cifs_mount(). + * Get an active reference of @ses so that next call to cifs_put_tcon() won't + * release it as any new DFS referrals must go through its IPC tcon. */ -static int add_root_smb_session(struct cifs_mount_ctx *mnt_ctx) +static void add_root_smb_session(struct cifs_mount_ctx *mnt_ctx) { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; - struct dfs_root_ses *root_ses; struct cifs_ses *ses = mnt_ctx->ses; if (ses) { - root_ses = kmalloc(sizeof(*root_ses), GFP_KERNEL); - if (!root_ses) - return -ENOMEM; - - INIT_LIST_HEAD(&root_ses->list); - spin_lock(&cifs_tcp_ses_lock); cifs_smb_ses_inc_refcount(ses); spin_unlock(&cifs_tcp_ses_lock); - root_ses->ses = ses; - list_add_tail(&root_ses->list, &mnt_ctx->dfs_ses_list); } - /* Select new DFS referral server so that new referrals go through it */ ctx->dfs_root_ses = ses; - return 0; } static inline int parse_dfs_target(struct smb3_fs_context *ctx, @@ -185,11 +172,8 @@ again: continue; } - if (is_refsrv) { - rc = add_root_smb_session(mnt_ctx); - if (rc) - goto out; - } + if (is_refsrv) + add_root_smb_session(mnt_ctx); rc = ref_walk_advance(rw); if (!rc) { @@ -232,6 +216,7 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct cifs_tcon *tcon; char *origin_fullpath; + bool new_tcon = true; int rc; origin_fullpath = dfs_get_path(cifs_sb, ctx->source); @@ -239,6 +224,18 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) return PTR_ERR(origin_fullpath); rc = dfs_referral_walk(mnt_ctx); + if (!rc) { + /* + * Prevent superblock from being created with any missing + * connections. + */ + if (WARN_ON(!mnt_ctx->server)) + rc = -EHOSTDOWN; + else if (WARN_ON(!mnt_ctx->ses)) + rc = -EACCES; + else if (WARN_ON(!mnt_ctx->tcon)) + rc = -ENOENT; + } if (rc) goto out; @@ -247,15 +244,14 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) if (!tcon->origin_fullpath) { tcon->origin_fullpath = origin_fullpath; origin_fullpath = NULL; + } else { + new_tcon = false; } spin_unlock(&tcon->tc_lock); - if (list_empty(&tcon->dfs_ses_list)) { - list_replace_init(&mnt_ctx->dfs_ses_list, &tcon->dfs_ses_list); + if (new_tcon) { queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, dfs_cache_get_ttl() * HZ); - } else { - dfs_put_root_smb_sessions(&mnt_ctx->dfs_ses_list); } out: @@ -298,7 +294,6 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) if (rc) return rc; - ctx->dfs_root_ses = mnt_ctx->ses; /* * If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally * try to get an DFS referral (even cached) to determine whether it is an DFS mount. @@ -324,7 +319,9 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) *isdfs = true; add_root_smb_session(mnt_ctx); - return __dfs_mount_share(mnt_ctx); + rc = __dfs_mount_share(mnt_ctx); + dfs_put_root_smb_sessions(mnt_ctx); + return rc; } /* Update dfs referral path of superblock */ diff --git a/fs/smb/client/dfs.h b/fs/smb/client/dfs.h index 875ab7ae57fc..e5c4dcf83750 100644 --- a/fs/smb/client/dfs.h +++ b/fs/smb/client/dfs.h @@ -7,7 +7,9 @@ #define _CIFS_DFS_H #include "cifsglob.h" +#include "cifsproto.h" #include "fs_context.h" +#include "dfs_cache.h" #include "cifs_unicode.h" #include <linux/namei.h> @@ -114,11 +116,6 @@ static inline void ref_walk_set_tgt_hint(struct dfs_ref_walk *rw) ref_walk_tit(rw)); } -struct dfs_root_ses { - struct list_head list; - struct cifs_ses *ses; -}; - int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_param *ref, struct smb3_fs_context *ctx); int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs); @@ -133,20 +130,32 @@ static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, const char *p { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct cifs_ses *rses = ctx->dfs_root_ses ?: mnt_ctx->ses; - return dfs_cache_find(mnt_ctx->xid, ctx->dfs_root_ses, cifs_sb->local_nls, + return dfs_cache_find(mnt_ctx->xid, rses, cifs_sb->local_nls, cifs_remap(cifs_sb), path, ref, tl); } -static inline void dfs_put_root_smb_sessions(struct list_head *head) +/* + * cifs_get_smb_ses() already guarantees an active reference of + * @ses->dfs_root_ses when a new session is created, so we need to put extra + * references of all DFS root sessions that were used across the mount process + * in dfs_mount_share(). + */ +static inline void dfs_put_root_smb_sessions(struct cifs_mount_ctx *mnt_ctx) { - struct dfs_root_ses *root, *tmp; + const struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct cifs_ses *ses = ctx->dfs_root_ses; + struct cifs_ses *cur; + + if (!ses) + return; - list_for_each_entry_safe(root, tmp, head, list) { - list_del_init(&root->list); - cifs_put_smb_ses(root->ses); - kfree(root); + for (cur = ses; cur; cur = cur->dfs_root_ses) { + if (cur->dfs_root_ses) + cifs_put_smb_ses(cur->dfs_root_ses); } + cifs_put_smb_ses(ses); } #endif /* _CIFS_DFS_H */ diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 508d831fabe3..11c8efecf7aa 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -1172,8 +1172,8 @@ static bool is_ses_good(struct cifs_ses *ses) return ret; } -/* Refresh dfs referral of tcon and mark it for reconnect if needed */ -static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_refresh) +/* Refresh dfs referral of @ses and mark it for reconnect if needed */ +static void __refresh_ses_referral(struct cifs_ses *ses, bool force_refresh) { struct TCP_Server_Info *server = ses->server; DFS_CACHE_TGT_LIST(old_tl); @@ -1181,10 +1181,21 @@ static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_ref bool needs_refresh = false; struct cache_entry *ce; unsigned int xid; + char *path = NULL; int rc = 0; xid = get_xid(); + mutex_lock(&server->refpath_lock); + if (server->leaf_fullpath) { + path = kstrdup(server->leaf_fullpath + 1, GFP_ATOMIC); + if (!path) + rc = -ENOMEM; + } + mutex_unlock(&server->refpath_lock); + if (!path) + goto out; + down_read(&htable_rw_lock); ce = lookup_cache_entry(path); needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce); @@ -1218,19 +1229,17 @@ out: free_xid(xid); dfs_cache_free_tgts(&old_tl); dfs_cache_free_tgts(&new_tl); - return rc; + kfree(path); } -static int refresh_tcon(struct cifs_tcon *tcon, bool force_refresh) +static inline void refresh_ses_referral(struct cifs_ses *ses) { - struct TCP_Server_Info *server = tcon->ses->server; - struct cifs_ses *ses = tcon->ses; + __refresh_ses_referral(ses, false); +} - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, force_refresh); - mutex_unlock(&server->refpath_lock); - return 0; +static inline void force_refresh_ses_referral(struct cifs_ses *ses) +{ + __refresh_ses_referral(ses, true); } /** @@ -1271,34 +1280,20 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) */ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; - return refresh_tcon(tcon, true); + force_refresh_ses_referral(tcon->ses); + return 0; } /* Refresh all DFS referrals related to DFS tcon */ void dfs_cache_refresh(struct work_struct *work) { - struct TCP_Server_Info *server; - struct dfs_root_ses *rses; struct cifs_tcon *tcon; struct cifs_ses *ses; tcon = container_of(work, struct cifs_tcon, dfs_cache_work.work); - ses = tcon->ses; - server = ses->server; - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, false); - mutex_unlock(&server->refpath_lock); - - list_for_each_entry(rses, &tcon->dfs_ses_list, list) { - ses = rses->ses; - server = ses->server; - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, false); - mutex_unlock(&server->refpath_lock); - } + for (ses = tcon->ses; ses; ses = ses->dfs_root_ses) + refresh_ses_referral(ses); queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, atomic_read(&dfs_cache_ttl) * HZ); diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index 89333d9bce36..864b194dbaa0 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -189,6 +189,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int disposition; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; *oplock = 0; if (tcon->ses->server->oplocks) @@ -200,6 +201,10 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned return PTR_ERR(full_path); } + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (oflags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -276,6 +281,8 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned desired_access |= GENERIC_READ; /* is this too little? */ if (OPEN_FMODE(oflags) & FMODE_WRITE) desired_access |= GENERIC_WRITE; + if (rdwr_for_fscache == 1) + desired_access |= GENERIC_READ; disposition = FILE_OVERWRITE_IF; if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) @@ -304,6 +311,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned if (!tcon->unix_ext && (mode & S_IWUGO) == 0) create_options |= CREATE_OPTION_READONLY; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -317,8 +325,15 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned rc = server->ops->open(xid, &oparms, oplock, buf); if (rc) { cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc); + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access &= ~GENERIC_READ; + rdwr_for_fscache = 2; + goto retry_open; + } goto out; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* @@ -612,11 +627,18 @@ int cifs_mknod(struct mnt_idmap *idmap, struct inode *inode, goto mknod_out; } + trace_smb3_mknod_enter(xid, tcon->ses->Suid, tcon->tid, full_path); + rc = tcon->ses->server->ops->make_node(xid, inode, direntry, tcon, full_path, mode, device_number); mknod_out: + if (rc) + trace_smb3_mknod_err(xid, tcon->ses->Suid, tcon->tid, rc); + else + trace_smb3_mknod_done(xid, tcon->ses->Suid, tcon->tid); + free_dentry_path(page); free_xid(xid); cifs_put_tlink(tlink); diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index f391c9b803d8..9d5c2440abfc 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -36,132 +36,322 @@ #include "fs_context.h" #include "cifs_ioctl.h" #include "cached_dir.h" +#include <trace/events/netfs.h> + +static int cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush); /* - * Remove the dirty flags from a span of pages. + * Prepare a subrequest to upload to the server. We need to allocate credits + * so that we know the maximum amount of data that we can include in it. */ -static void cifs_undirty_folios(struct inode *inode, loff_t start, unsigned int len) +static void cifs_prepare_write(struct netfs_io_subrequest *subreq) { - struct address_space *mapping = inode->i_mapping; - struct folio *folio; - pgoff_t end; + struct cifs_io_subrequest *wdata = + container_of(subreq, struct cifs_io_subrequest, subreq); + struct cifs_io_request *req = wdata->req; + struct TCP_Server_Info *server; + struct cifsFileInfo *open_file = req->cfile; + size_t wsize = req->rreq.wsize; + int rc; - XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE); + if (!wdata->have_xid) { + wdata->xid = get_xid(); + wdata->have_xid = true; + } - rcu_read_lock(); + server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses); + wdata->server = server; - end = (start + len - 1) / PAGE_SIZE; - xas_for_each_marked(&xas, folio, end, PAGECACHE_TAG_DIRTY) { - if (xas_retry(&xas, folio)) - continue; - xas_pause(&xas); - rcu_read_unlock(); - folio_lock(folio); - folio_clear_dirty_for_io(folio); - folio_unlock(folio); - rcu_read_lock(); +retry: + if (open_file->invalidHandle) { + rc = cifs_reopen_file(open_file, false); + if (rc < 0) { + if (rc == -EAGAIN) + goto retry; + subreq->error = rc; + return netfs_prepare_write_failed(subreq); + } + } + + rc = server->ops->wait_mtu_credits(server, wsize, &wdata->subreq.max_len, + &wdata->credits); + if (rc < 0) { + subreq->error = rc; + return netfs_prepare_write_failed(subreq); } - rcu_read_unlock(); +#ifdef CONFIG_CIFS_SMB_DIRECT + if (server->smbd_conn) + subreq->max_nr_segs = server->smbd_conn->max_frmr_depth; +#endif } /* - * Completion of write to server. + * Issue a subrequest to upload to the server. */ -void cifs_pages_written_back(struct inode *inode, loff_t start, unsigned int len) +static void cifs_issue_write(struct netfs_io_subrequest *subreq) { - struct address_space *mapping = inode->i_mapping; - struct folio *folio; - pgoff_t end; + struct cifs_io_subrequest *wdata = + container_of(subreq, struct cifs_io_subrequest, subreq); + struct cifs_sb_info *sbi = CIFS_SB(subreq->rreq->inode->i_sb); + int rc; - XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE); + if (cifs_forced_shutdown(sbi)) { + rc = -EIO; + goto fail; + } - if (!len) - return; + rc = adjust_credits(wdata->server, &wdata->credits, wdata->subreq.len); + if (rc) + goto fail; - rcu_read_lock(); + rc = -EAGAIN; + if (wdata->req->cfile->invalidHandle) + goto fail; - end = (start + len - 1) / PAGE_SIZE; - xas_for_each(&xas, folio, end) { - if (xas_retry(&xas, folio)) - continue; - if (!folio_test_writeback(folio)) { - WARN_ONCE(1, "bad %x @%llx page %lx %lx\n", - len, start, folio->index, end); - continue; - } + wdata->server->ops->async_writev(wdata); +out: + return; + +fail: + if (rc == -EAGAIN) + trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + else + trace_netfs_sreq(subreq, netfs_sreq_trace_fail); + add_credits_and_wake_if(wdata->server, &wdata->credits, 0); + cifs_write_subrequest_terminated(wdata, rc, false); + goto out; +} + +/* + * Split the read up according to how many credits we can get for each piece. + * It's okay to sleep here if we need to wait for more credit to become + * available. + * + * We also choose the server and allocate an operation ID to be cleaned up + * later. + */ +static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) +{ + struct netfs_io_request *rreq = subreq->rreq; + struct TCP_Server_Info *server; + struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); + struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); + struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); + size_t rsize = 0; + int rc; - folio_detach_private(folio); - folio_end_writeback(folio); + rdata->xid = get_xid(); + rdata->have_xid = true; + + server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses); + rdata->server = server; + + if (cifs_sb->ctx->rsize == 0) + cifs_sb->ctx->rsize = + server->ops->negotiate_rsize(tlink_tcon(req->cfile->tlink), + cifs_sb->ctx); + + + rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, &rsize, + &rdata->credits); + if (rc) { + subreq->error = rc; + return false; } - rcu_read_unlock(); + subreq->len = min_t(size_t, subreq->len, rsize); +#ifdef CONFIG_CIFS_SMB_DIRECT + if (server->smbd_conn) + subreq->max_nr_segs = server->smbd_conn->max_frmr_depth; +#endif + return true; } /* - * Failure of write to server. + * Issue a read operation on behalf of the netfs helper functions. We're asked + * to make a read of a certain size at a point in the file. We are permitted + * to only read a portion of that, but as long as we read something, the netfs + * helper will call us again so that we can issue another read. */ -void cifs_pages_write_failed(struct inode *inode, loff_t start, unsigned int len) +static void cifs_req_issue_read(struct netfs_io_subrequest *subreq) { - struct address_space *mapping = inode->i_mapping; - struct folio *folio; - pgoff_t end; + struct netfs_io_request *rreq = subreq->rreq; + struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); + struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); + struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); + pid_t pid; + int rc = 0; - XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) + pid = req->cfile->pid; + else + pid = current->tgid; // Ummm... This may be a workqueue - if (!len) - return; + cifs_dbg(FYI, "%s: op=%08x[%x] mapping=%p len=%zu/%zu\n", + __func__, rreq->debug_id, subreq->debug_index, rreq->mapping, + subreq->transferred, subreq->len); - rcu_read_lock(); + if (req->cfile->invalidHandle) { + do { + rc = cifs_reopen_file(req->cfile, true); + } while (rc == -EAGAIN); + if (rc) + goto out; + } - end = (start + len - 1) / PAGE_SIZE; - xas_for_each(&xas, folio, end) { - if (xas_retry(&xas, folio)) - continue; - if (!folio_test_writeback(folio)) { - WARN_ONCE(1, "bad %x @%llx page %lx %lx\n", - len, start, folio->index, end); - continue; - } + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + rdata->pid = pid; - folio_set_error(folio); - folio_end_writeback(folio); + rc = adjust_credits(rdata->server, &rdata->credits, rdata->subreq.len); + if (!rc) { + if (rdata->req->cfile->invalidHandle) + rc = -EAGAIN; + else + rc = rdata->server->ops->async_readv(rdata); } - rcu_read_unlock(); +out: + if (rc) + netfs_subreq_terminated(subreq, rc, false); } /* - * Redirty pages after a temporary failure. + * Writeback calls this when it finds a folio that needs uploading. This isn't + * called if writeback only has copy-to-cache to deal with. */ -void cifs_pages_write_redirty(struct inode *inode, loff_t start, unsigned int len) +static void cifs_begin_writeback(struct netfs_io_request *wreq) { - struct address_space *mapping = inode->i_mapping; - struct folio *folio; - pgoff_t end; - - XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE); + struct cifs_io_request *req = container_of(wreq, struct cifs_io_request, rreq); + int ret; - if (!len) + ret = cifs_get_writable_file(CIFS_I(wreq->inode), FIND_WR_ANY, &req->cfile); + if (ret) { + cifs_dbg(VFS, "No writable handle in writepages ret=%d\n", ret); return; + } - rcu_read_lock(); + wreq->io_streams[0].avail = true; +} - end = (start + len - 1) / PAGE_SIZE; - xas_for_each(&xas, folio, end) { - if (!folio_test_writeback(folio)) { - WARN_ONCE(1, "bad %x @%llx page %lx %lx\n", - len, start, folio->index, end); - continue; - } +/* + * Initialise a request. + */ +static int cifs_init_request(struct netfs_io_request *rreq, struct file *file) +{ + struct cifs_io_request *req = container_of(rreq, struct cifs_io_request, rreq); + struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); + struct cifsFileInfo *open_file = NULL; + + rreq->rsize = cifs_sb->ctx->rsize; + rreq->wsize = cifs_sb->ctx->wsize; + + if (file) { + open_file = file->private_data; + rreq->netfs_priv = file->private_data; + req->cfile = cifsFileInfo_get(open_file); + } else if (rreq->origin != NETFS_WRITEBACK) { + WARN_ON_ONCE(1); + return -EIO; + } + + return 0; +} + +/* + * Expand the size of a readahead to the size of the rsize, if at least as + * large as a page, allowing for the possibility that rsize is not pow-2 + * aligned. + */ +static void cifs_expand_readahead(struct netfs_io_request *rreq) +{ + unsigned int rsize = rreq->rsize; + loff_t misalignment, i_size = i_size_read(rreq->inode); + + if (rsize < PAGE_SIZE) + return; - filemap_dirty_folio(folio->mapping, folio); - folio_end_writeback(folio); + if (rsize < INT_MAX) + rsize = roundup_pow_of_two(rsize); + else + rsize = ((unsigned int)INT_MAX + 1) / 2; + + misalignment = rreq->start & (rsize - 1); + if (misalignment) { + rreq->start -= misalignment; + rreq->len += misalignment; } - rcu_read_unlock(); + rreq->len = round_up(rreq->len, rsize); + if (rreq->start < i_size && rreq->len > i_size - rreq->start) + rreq->len = i_size - rreq->start; +} + +/* + * Completion of a request operation. + */ +static void cifs_rreq_done(struct netfs_io_request *rreq) +{ + struct timespec64 atime, mtime; + struct inode *inode = rreq->inode; + + /* we do not want atime to be less than mtime, it broke some apps */ + atime = inode_set_atime_to_ts(inode, current_time(inode)); + mtime = inode_get_mtime(inode); + if (timespec64_compare(&atime, &mtime)) + inode_set_atime_to_ts(inode, inode_get_mtime(inode)); +} + +static void cifs_post_modify(struct inode *inode) +{ + /* Indication to update ctime and mtime as close is deferred */ + set_bit(CIFS_INO_MODIFIED_ATTR, &CIFS_I(inode)->flags); +} + +static void cifs_free_request(struct netfs_io_request *rreq) +{ + struct cifs_io_request *req = container_of(rreq, struct cifs_io_request, rreq); + + if (req->cfile) + cifsFileInfo_put(req->cfile); } +static void cifs_free_subrequest(struct netfs_io_subrequest *subreq) +{ + struct cifs_io_subrequest *rdata = + container_of(subreq, struct cifs_io_subrequest, subreq); + int rc = subreq->error; + + if (rdata->subreq.source == NETFS_DOWNLOAD_FROM_SERVER) { +#ifdef CONFIG_CIFS_SMB_DIRECT + if (rdata->mr) { + smbd_deregister_mr(rdata->mr); + rdata->mr = NULL; + } +#endif + } + + add_credits_and_wake_if(rdata->server, &rdata->credits, 0); + if (rdata->have_xid) + free_xid(rdata->xid); +} + +const struct netfs_request_ops cifs_req_ops = { + .request_pool = &cifs_io_request_pool, + .subrequest_pool = &cifs_io_subrequest_pool, + .init_request = cifs_init_request, + .free_request = cifs_free_request, + .free_subrequest = cifs_free_subrequest, + .expand_readahead = cifs_expand_readahead, + .clamp_length = cifs_clamp_length, + .issue_read = cifs_req_issue_read, + .done = cifs_rreq_done, + .post_modify = cifs_post_modify, + .begin_writeback = cifs_begin_writeback, + .prepare_write = cifs_prepare_write, + .issue_write = cifs_issue_write, +}; + /* * Mark as invalid, all open files on tree connections since they * were closed when session to server was lost. @@ -206,12 +396,12 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) */ } -static inline int cifs_convert_flags(unsigned int flags) +static inline int cifs_convert_flags(unsigned int flags, int rdwr_for_fscache) { if ((flags & O_ACCMODE) == O_RDONLY) return GENERIC_READ; else if ((flags & O_ACCMODE) == O_WRONLY) - return GENERIC_WRITE; + return rdwr_for_fscache == 1 ? (GENERIC_READ | GENERIC_WRITE) : GENERIC_WRITE; else if ((flags & O_ACCMODE) == O_RDWR) { /* GENERIC_ALL is too much permission to request can cause unnecessary access denied on create */ @@ -329,7 +519,7 @@ int cifs_posix_open(const char *full_path, struct inode **pinode, } } else { cifs_revalidate_mapping(*pinode); - rc = cifs_fattr_to_inode(*pinode, &fattr); + rc = cifs_fattr_to_inode(*pinode, &fattr, false); } posix_open_ret: @@ -348,11 +538,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ int create_options = CREATE_NOT_DIR; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; if (!server->ops->open) return -ENOSYS; - desired_access = cifs_convert_flags(f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(f_flags, rdwr_for_fscache); /********************************************************************* * open flag mapping table: @@ -389,6 +584,7 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ if (f_flags & O_DIRECT) create_options |= CREATE_NO_BUFFER; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -400,8 +596,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ }; rc = server->ops->open(xid, &oparms, oplock, buf); - if (rc) + if (rc) { + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } return rc; + } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); /* TODO: Add support for calling posix query info but with passing in fid */ if (tcon->unix_ext) @@ -445,6 +649,7 @@ cifs_down_write(struct rw_semaphore *sem) } static void cifsFileInfo_put_work(struct work_struct *work); +void serverclose_work(struct work_struct *work); struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, __u32 oplock, @@ -491,6 +696,7 @@ struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, cfile->tlink = cifs_get_tlink(tlink); INIT_WORK(&cfile->oplock_break, cifs_oplock_break); INIT_WORK(&cfile->put, cifsFileInfo_put_work); + INIT_WORK(&cfile->serverclose, serverclose_work); INIT_DELAYED_WORK(&cfile->deferred, smb2_deferred_work_close); mutex_init(&cfile->fh_mutex); spin_lock_init(&cfile->file_info_lock); @@ -582,6 +788,40 @@ static void cifsFileInfo_put_work(struct work_struct *work) cifsFileInfo_put_final(cifs_file); } +void serverclose_work(struct work_struct *work) +{ + struct cifsFileInfo *cifs_file = container_of(work, + struct cifsFileInfo, serverclose); + + struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); + + struct TCP_Server_Info *server = tcon->ses->server; + int rc = 0; + int retries = 0; + int MAX_RETRIES = 4; + + do { + if (server->ops->close_getattr) + rc = server->ops->close_getattr(0, tcon, cifs_file); + else if (server->ops->close) + rc = server->ops->close(0, tcon, &cifs_file->fid); + + if (rc == -EBUSY || rc == -EAGAIN) { + retries++; + msleep(250); + } + } while ((rc == -EBUSY || rc == -EAGAIN) && (retries < MAX_RETRIES) + ); + + if (retries == MAX_RETRIES) + pr_warn("Serverclose failed %d times, giving up\n", MAX_RETRIES); + + if (cifs_file->offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); +} + /** * cifsFileInfo_put - release a reference of file priv data * @@ -622,10 +862,13 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, struct cifs_fid fid = {}; struct cifs_pending_open open; bool oplock_break_cancelled; + bool serverclose_offloaded = false; spin_lock(&tcon->open_file_lock); spin_lock(&cifsi->open_file_lock); spin_lock(&cifs_file->file_info_lock); + + cifs_file->offload = offload; if (--cifs_file->count > 0) { spin_unlock(&cifs_file->file_info_lock); spin_unlock(&cifsi->open_file_lock); @@ -667,13 +910,20 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; unsigned int xid; + int rc = 0; xid = get_xid(); if (server->ops->close_getattr) - server->ops->close_getattr(xid, tcon, cifs_file); + rc = server->ops->close_getattr(xid, tcon, cifs_file); else if (server->ops->close) - server->ops->close(xid, tcon, &cifs_file->fid); + rc = server->ops->close(xid, tcon, &cifs_file->fid); _free_xid(xid); + + if (rc == -EBUSY || rc == -EAGAIN) { + // Server close failed, hence offloading it as an async op + queue_work(serverclose_wq, &cifs_file->serverclose); + serverclose_offloaded = true; + } } if (oplock_break_cancelled) @@ -681,10 +931,15 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, cifs_del_pending_open(&open); - if (offload) - queue_work(fileinfo_put_wq, &cifs_file->put); - else - cifsFileInfo_put_final(cifs_file); + // if serverclose has been offloaded to wq (on failure), it will + // handle offloading put as well. If serverclose not offloaded, + // we need to handle offloading put here. + if (!serverclose_offloaded) { + if (offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); + } } int cifs_open(struct inode *inode, struct file *file) @@ -834,11 +1089,11 @@ int cifs_open(struct inode *inode, struct file *file) use_cache: fscache_use_cookie(cifs_inode_cookie(file_inode(file)), file->f_mode & FMODE_WRITE); - if (file->f_flags & O_DIRECT && - (!((file->f_flags & O_ACCMODE) != O_RDONLY) || - file->f_flags & O_APPEND)) - cifs_invalidate_cache(file_inode(file), - FSCACHE_INVAL_DIO_WRITE); + if (!(file->f_flags & O_DIRECT)) + goto out; + if ((file->f_flags & (O_ACCMODE | O_APPEND)) == O_RDONLY) + goto out; + cifs_invalidate_cache(file_inode(file), FSCACHE_INVAL_DIO_WRITE); out: free_dentry_path(page); @@ -903,6 +1158,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) int disposition = FILE_OPEN; int create_options = CREATE_NOT_DIR; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; xid = get_xid(); mutex_lock(&cfile->fh_mutex); @@ -966,7 +1222,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ - desired_access = cifs_convert_flags(cfile->f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (cfile->f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache); /* O_SYNC also has bit for O_DSYNC so following check picks up either */ if (cfile->f_flags & O_SYNC) @@ -978,6 +1238,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &cfile->fid); +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -1003,6 +1264,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) /* indicate that we need to relock the file */ oparms.reconnect = true; } + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(cfile->f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } if (rc) { mutex_unlock(&cfile->fh_mutex); @@ -1011,6 +1277,9 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) goto reopen_error_exit; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY reopen_success: #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ @@ -1072,6 +1341,19 @@ void smb2_deferred_work_close(struct work_struct *work) _cifsFileInfo_put(cfile, true, false); } +static bool +smb2_can_defer_close(struct inode *inode, struct cifs_deferred_close *dclose) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifsInodeInfo *cinode = CIFS_I(inode); + + return (cifs_sb->ctx->closetimeo && cinode->lease_granted && dclose && + (cinode->oplock == CIFS_CACHE_RHW_FLG || + cinode->oplock == CIFS_CACHE_RH_FLG) && + !test_bit(CIFS_INO_CLOSE_ON_LOCK, &cinode->flags)); + +} + int cifs_close(struct inode *inode, struct file *file) { struct cifsFileInfo *cfile; @@ -1085,10 +1367,8 @@ int cifs_close(struct inode *inode, struct file *file) cfile = file->private_data; file->private_data = NULL; dclose = kmalloc(sizeof(struct cifs_deferred_close), GFP_KERNEL); - if ((cifs_sb->ctx->closetimeo && cinode->oplock == CIFS_CACHE_RHW_FLG) - && cinode->lease_granted && - !test_bit(CIFS_INO_CLOSE_ON_LOCK, &cinode->flags) && - dclose) { + if ((cfile->status_file_deleted == false) && + (smb2_can_defer_close(inode, dclose))) { if (test_and_clear_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); @@ -1315,20 +1595,20 @@ cifs_lock_test(struct cifsFileInfo *cfile, __u64 offset, __u64 length, down_read(&cinode->lock_sem); exist = cifs_find_lock_conflict(cfile, offset, length, type, - flock->fl_flags, &conf_lock, + flock->c.flc_flags, &conf_lock, CIFS_LOCK_OP); if (exist) { flock->fl_start = conf_lock->offset; flock->fl_end = conf_lock->offset + conf_lock->length - 1; - flock->fl_pid = conf_lock->pid; + flock->c.flc_pid = conf_lock->pid; if (conf_lock->type & server->vals->shared_lock_type) - flock->fl_type = F_RDLCK; + flock->c.flc_type = F_RDLCK; else - flock->fl_type = F_WRLCK; + flock->c.flc_type = F_WRLCK; } else if (!cinode->can_cache_brlcks) rc = 1; else - flock->fl_type = F_UNLCK; + flock->c.flc_type = F_UNLCK; up_read(&cinode->lock_sem); return rc; @@ -1404,16 +1684,16 @@ cifs_posix_lock_test(struct file *file, struct file_lock *flock) { int rc = 0; struct cifsInodeInfo *cinode = CIFS_I(file_inode(file)); - unsigned char saved_type = flock->fl_type; + unsigned char saved_type = flock->c.flc_type; - if ((flock->fl_flags & FL_POSIX) == 0) + if ((flock->c.flc_flags & FL_POSIX) == 0) return 1; down_read(&cinode->lock_sem); posix_test_lock(file, flock); - if (flock->fl_type == F_UNLCK && !cinode->can_cache_brlcks) { - flock->fl_type = saved_type; + if (lock_is_unlock(flock) && !cinode->can_cache_brlcks) { + flock->c.flc_type = saved_type; rc = 1; } @@ -1434,7 +1714,7 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock) struct cifsInodeInfo *cinode = CIFS_I(file_inode(file)); int rc = FILE_LOCK_DEFERRED + 1; - if ((flock->fl_flags & FL_POSIX) == 0) + if ((flock->c.flc_flags & FL_POSIX) == 0) return rc; cifs_down_write(&cinode->lock_sem); @@ -1584,7 +1864,9 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) el = locks_to_send.next; spin_lock(&flctx->flc_lock); - list_for_each_entry(flock, &flctx->flc_posix, fl_list) { + for_each_file_lock(flock, &flctx->flc_posix) { + unsigned char ftype = flock->c.flc_type; + if (el == &locks_to_send) { /* * The list ended. We don't have enough allocated @@ -1594,12 +1876,12 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) break; } length = cifs_flock_len(flock); - if (flock->fl_type == F_RDLCK || flock->fl_type == F_SHLCK) + if (ftype == F_RDLCK || ftype == F_SHLCK) type = CIFS_RDLCK; else type = CIFS_WRLCK; lck = list_entry(el, struct lock_to_push, llist); - lck->pid = hash_lockowner(flock->fl_owner); + lck->pid = hash_lockowner(flock->c.flc_owner); lck->netfid = cfile->fid.netfid; lck->length = length; lck->type = type; @@ -1666,42 +1948,43 @@ static void cifs_read_flock(struct file_lock *flock, __u32 *type, int *lock, int *unlock, bool *wait_flag, struct TCP_Server_Info *server) { - if (flock->fl_flags & FL_POSIX) + if (flock->c.flc_flags & FL_POSIX) cifs_dbg(FYI, "Posix\n"); - if (flock->fl_flags & FL_FLOCK) + if (flock->c.flc_flags & FL_FLOCK) cifs_dbg(FYI, "Flock\n"); - if (flock->fl_flags & FL_SLEEP) { + if (flock->c.flc_flags & FL_SLEEP) { cifs_dbg(FYI, "Blocking lock\n"); *wait_flag = true; } - if (flock->fl_flags & FL_ACCESS) + if (flock->c.flc_flags & FL_ACCESS) cifs_dbg(FYI, "Process suspended by mandatory locking - not implemented yet\n"); - if (flock->fl_flags & FL_LEASE) + if (flock->c.flc_flags & FL_LEASE) cifs_dbg(FYI, "Lease on file - not implemented yet\n"); - if (flock->fl_flags & + if (flock->c.flc_flags & (~(FL_POSIX | FL_FLOCK | FL_SLEEP | FL_ACCESS | FL_LEASE | FL_CLOSE | FL_OFDLCK))) - cifs_dbg(FYI, "Unknown lock flags 0x%x\n", flock->fl_flags); + cifs_dbg(FYI, "Unknown lock flags 0x%x\n", + flock->c.flc_flags); *type = server->vals->large_lock_type; - if (flock->fl_type == F_WRLCK) { + if (lock_is_write(flock)) { cifs_dbg(FYI, "F_WRLCK\n"); *type |= server->vals->exclusive_lock_type; *lock = 1; - } else if (flock->fl_type == F_UNLCK) { + } else if (lock_is_unlock(flock)) { cifs_dbg(FYI, "F_UNLCK\n"); *type |= server->vals->unlock_lock_type; *unlock = 1; /* Check if unlock includes more than one lock range */ - } else if (flock->fl_type == F_RDLCK) { + } else if (lock_is_read(flock)) { cifs_dbg(FYI, "F_RDLCK\n"); *type |= server->vals->shared_lock_type; *lock = 1; - } else if (flock->fl_type == F_EXLCK) { + } else if (flock->c.flc_type == F_EXLCK) { cifs_dbg(FYI, "F_EXLCK\n"); *type |= server->vals->exclusive_lock_type; *lock = 1; - } else if (flock->fl_type == F_SHLCK) { + } else if (flock->c.flc_type == F_SHLCK) { cifs_dbg(FYI, "F_SHLCK\n"); *type |= server->vals->shared_lock_type; *lock = 1; @@ -1733,7 +2016,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type, else posix_lock_type = CIFS_WRLCK; rc = CIFSSMBPosixLock(xid, tcon, netfid, - hash_lockowner(flock->fl_owner), + hash_lockowner(flock->c.flc_owner), flock->fl_start, length, flock, posix_lock_type, wait_flag); return rc; @@ -1750,7 +2033,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type, if (rc == 0) { rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length, type, 0, 1, false); - flock->fl_type = F_UNLCK; + flock->c.flc_type = F_UNLCK; if (rc != 0) cifs_dbg(VFS, "Error unlocking previously locked range %d during test of lock\n", rc); @@ -1758,7 +2041,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type, } if (type & server->vals->shared_lock_type) { - flock->fl_type = F_WRLCK; + flock->c.flc_type = F_WRLCK; return 0; } @@ -1770,12 +2053,12 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type, if (rc == 0) { rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length, type | server->vals->shared_lock_type, 0, 1, false); - flock->fl_type = F_RDLCK; + flock->c.flc_type = F_RDLCK; if (rc != 0) cifs_dbg(VFS, "Error unlocking previously locked range %d during test of lock\n", rc); } else - flock->fl_type = F_WRLCK; + flock->c.flc_type = F_WRLCK; return 0; } @@ -1943,7 +2226,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, posix_lock_type = CIFS_UNLCK; rc = CIFSSMBPosixLock(xid, tcon, cfile->fid.netfid, - hash_lockowner(flock->fl_owner), + hash_lockowner(flock->c.flc_owner), flock->fl_start, length, NULL, posix_lock_type, wait_flag); goto out; @@ -1953,7 +2236,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, struct cifsLockInfo *lock; lock = cifs_lock_init(flock->fl_start, length, type, - flock->fl_flags); + flock->c.flc_flags); if (!lock) return -ENOMEM; @@ -1992,7 +2275,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, rc = server->ops->mand_unlock_range(cfile, flock, xid); out: - if ((flock->fl_flags & FL_POSIX) || (flock->fl_flags & FL_FLOCK)) { + if ((flock->c.flc_flags & FL_POSIX) || (flock->c.flc_flags & FL_FLOCK)) { /* * If this is a request to remove all locks because we * are closing the file, it doesn't matter if the @@ -2001,7 +2284,7 @@ out: */ if (rc) { cifs_dbg(VFS, "%s failed rc=%d\n", __func__, rc); - if (!(flock->fl_flags & FL_CLOSE)) + if (!(flock->c.flc_flags & FL_CLOSE)) return rc; } rc = locks_lock_file_wait(file, flock); @@ -2022,7 +2305,7 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl) xid = get_xid(); - if (!(fl->fl_flags & FL_FLOCK)) { + if (!(fl->c.flc_flags & FL_FLOCK)) { rc = -ENOLCK; free_xid(xid); return rc; @@ -2073,7 +2356,8 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock) xid = get_xid(); cifs_dbg(FYI, "%s: %pD2 cmd=0x%x type=0x%x flags=0x%x r=%lld:%lld\n", __func__, file, cmd, - flock->fl_flags, flock->fl_type, (long long)flock->fl_start, + flock->c.flc_flags, flock->c.flc_type, + (long long)flock->fl_start, (long long)flock->fl_end); cfile = (struct cifsFileInfo *)file->private_data; @@ -2113,102 +2397,20 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock) return rc; } -/* - * update the file size (if needed) after a write. Should be called with - * the inode->i_lock held - */ -void -cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset, - unsigned int bytes_written) -{ - loff_t end_of_write = offset + bytes_written; - - if (end_of_write > cifsi->netfs.remote_i_size) - netfs_resize_file(&cifsi->netfs, end_of_write, true); -} - -static ssize_t -cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data, - size_t write_size, loff_t *offset) +void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result, + bool was_async) { - int rc = 0; - unsigned int bytes_written = 0; - unsigned int total_written; - struct cifs_tcon *tcon; - struct TCP_Server_Info *server; - unsigned int xid; - struct dentry *dentry = open_file->dentry; - struct cifsInodeInfo *cifsi = CIFS_I(d_inode(dentry)); - struct cifs_io_parms io_parms = {0}; - - cifs_dbg(FYI, "write %zd bytes to offset %lld of %pd\n", - write_size, *offset, dentry); + struct netfs_io_request *wreq = wdata->rreq; + loff_t new_server_eof; - tcon = tlink_tcon(open_file->tlink); - server = tcon->ses->server; + if (result > 0) { + new_server_eof = wdata->subreq.start + wdata->subreq.transferred + result; - if (!server->ops->sync_write) - return -ENOSYS; - - xid = get_xid(); - - for (total_written = 0; write_size > total_written; - total_written += bytes_written) { - rc = -EAGAIN; - while (rc == -EAGAIN) { - struct kvec iov[2]; - unsigned int len; - - if (open_file->invalidHandle) { - /* we could deadlock if we called - filemap_fdatawait from here so tell - reopen_file not to flush data to - server now */ - rc = cifs_reopen_file(open_file, false); - if (rc != 0) - break; - } - - len = min(server->ops->wp_retry_size(d_inode(dentry)), - (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; - io_parms.pid = pid; - io_parms.tcon = tcon; - io_parms.offset = *offset; - io_parms.length = len; - rc = server->ops->sync_write(xid, &open_file->fid, - &io_parms, &bytes_written, iov, 1); - } - if (rc || (bytes_written == 0)) { - if (total_written) - break; - else { - free_xid(xid); - return rc; - } - } else { - spin_lock(&d_inode(dentry)->i_lock); - cifs_update_eof(cifsi, *offset, bytes_written); - spin_unlock(&d_inode(dentry)->i_lock); - *offset += bytes_written; - } + if (new_server_eof > netfs_inode(wreq->inode)->remote_i_size) + netfs_resize_file(netfs_inode(wreq->inode), new_server_eof, true); } - cifs_stats_bytes_written(tcon, total_written); - - if (total_written > 0) { - spin_lock(&d_inode(dentry)->i_lock); - if (*offset > d_inode(dentry)->i_size) { - i_size_write(d_inode(dentry), *offset); - d_inode(dentry)->i_blocks = (512 - 1 + *offset) >> 9; - } - spin_unlock(&d_inode(dentry)->i_lock); - } - mark_inode_dirty_sync(d_inode(dentry)); - free_xid(xid); - return total_written; + netfs_write_subrequest_terminated(&wdata->subreq, result, was_async); } struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, @@ -2415,699 +2617,9 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, return -ENOENT; } -void -cifs_writedata_release(struct kref *refcount) -{ - struct cifs_writedata *wdata = container_of(refcount, - struct cifs_writedata, refcount); -#ifdef CONFIG_CIFS_SMB_DIRECT - if (wdata->mr) { - smbd_deregister_mr(wdata->mr); - wdata->mr = NULL; - } -#endif - - if (wdata->cfile) - cifsFileInfo_put(wdata->cfile); - - kfree(wdata); -} - -/* - * Write failed with a retryable error. Resend the write request. It's also - * possible that the page was redirtied so re-clean the page. - */ -static void -cifs_writev_requeue(struct cifs_writedata *wdata) -{ - int rc = 0; - struct inode *inode = d_inode(wdata->cfile->dentry); - struct TCP_Server_Info *server; - unsigned int rest_len = wdata->bytes; - loff_t fpos = wdata->offset; - - server = tlink_tcon(wdata->cfile->tlink)->ses->server; - do { - struct cifs_writedata *wdata2; - unsigned int wsize, cur_len; - - wsize = server->ops->wp_retry_size(inode); - if (wsize < rest_len) { - if (wsize < PAGE_SIZE) { - rc = -EOPNOTSUPP; - break; - } - cur_len = min(round_down(wsize, PAGE_SIZE), rest_len); - } else { - cur_len = rest_len; - } - - wdata2 = cifs_writedata_alloc(cifs_writev_complete); - if (!wdata2) { - rc = -ENOMEM; - break; - } - - wdata2->sync_mode = wdata->sync_mode; - wdata2->offset = fpos; - wdata2->bytes = cur_len; - wdata2->iter = wdata->iter; - - iov_iter_advance(&wdata2->iter, fpos - wdata->offset); - iov_iter_truncate(&wdata2->iter, wdata2->bytes); - - if (iov_iter_is_xarray(&wdata2->iter)) - /* Check for pages having been redirtied and clean - * them. We can do this by walking the xarray. If - * it's not an xarray, then it's a DIO and we shouldn't - * be mucking around with the page bits. - */ - cifs_undirty_folios(inode, fpos, cur_len); - - rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, - &wdata2->cfile); - if (!wdata2->cfile) { - cifs_dbg(VFS, "No writable handle to retry writepages rc=%d\n", - rc); - if (!is_retryable_error(rc)) - rc = -EBADF; - } else { - wdata2->pid = wdata2->cfile->pid; - rc = server->ops->async_writev(wdata2, - cifs_writedata_release); - } - - kref_put(&wdata2->refcount, cifs_writedata_release); - if (rc) { - if (is_retryable_error(rc)) - continue; - fpos += cur_len; - rest_len -= cur_len; - break; - } - - fpos += cur_len; - rest_len -= cur_len; - } while (rest_len > 0); - - /* Clean up remaining pages from the original wdata */ - if (iov_iter_is_xarray(&wdata->iter)) - cifs_pages_write_failed(inode, fpos, rest_len); - - if (rc != 0 && !is_retryable_error(rc)) - mapping_set_error(inode->i_mapping, rc); - kref_put(&wdata->refcount, cifs_writedata_release); -} - -void -cifs_writev_complete(struct work_struct *work) -{ - struct cifs_writedata *wdata = container_of(work, - struct cifs_writedata, work); - struct inode *inode = d_inode(wdata->cfile->dentry); - - if (wdata->result == 0) { - spin_lock(&inode->i_lock); - cifs_update_eof(CIFS_I(inode), wdata->offset, wdata->bytes); - spin_unlock(&inode->i_lock); - cifs_stats_bytes_written(tlink_tcon(wdata->cfile->tlink), - wdata->bytes); - } else if (wdata->sync_mode == WB_SYNC_ALL && wdata->result == -EAGAIN) - return cifs_writev_requeue(wdata); - - if (wdata->result == -EAGAIN) - cifs_pages_write_redirty(inode, wdata->offset, wdata->bytes); - else if (wdata->result < 0) - cifs_pages_write_failed(inode, wdata->offset, wdata->bytes); - else - cifs_pages_written_back(inode, wdata->offset, wdata->bytes); - - if (wdata->result != -EAGAIN) - mapping_set_error(inode->i_mapping, wdata->result); - kref_put(&wdata->refcount, cifs_writedata_release); -} - -struct cifs_writedata *cifs_writedata_alloc(work_func_t complete) -{ - struct cifs_writedata *wdata; - - wdata = kzalloc(sizeof(*wdata), GFP_NOFS); - if (wdata != NULL) { - kref_init(&wdata->refcount); - INIT_LIST_HEAD(&wdata->list); - init_completion(&wdata->done); - INIT_WORK(&wdata->work, complete); - } - return wdata; -} - -static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) -{ - struct address_space *mapping = page->mapping; - loff_t offset = (loff_t)page->index << PAGE_SHIFT; - char *write_data; - int rc = -EFAULT; - int bytes_written = 0; - struct inode *inode; - struct cifsFileInfo *open_file; - - if (!mapping || !mapping->host) - return -EFAULT; - - inode = page->mapping->host; - - offset += (loff_t)from; - write_data = kmap(page); - write_data += from; - - if ((to > PAGE_SIZE) || (from > to)) { - kunmap(page); - return -EIO; - } - - /* racing with truncate? */ - if (offset > mapping->host->i_size) { - kunmap(page); - return 0; /* don't care */ - } - - /* check to make sure that we are not extending the file */ - if (mapping->host->i_size - offset < (loff_t)to) - to = (unsigned)(mapping->host->i_size - offset); - - rc = cifs_get_writable_file(CIFS_I(mapping->host), FIND_WR_ANY, - &open_file); - if (!rc) { - bytes_written = cifs_write(open_file, open_file->pid, - write_data, to - from, &offset); - cifsFileInfo_put(open_file); - /* Does mm or vfs already set times? */ - simple_inode_init_ts(inode); - if ((bytes_written > 0) && (offset)) - rc = 0; - else if (bytes_written < 0) - rc = bytes_written; - else - rc = -EFAULT; - } else { - cifs_dbg(FYI, "No writable handle for write page rc=%d\n", rc); - if (!is_retryable_error(rc)) - rc = -EIO; - } - - kunmap(page); - return rc; -} - -/* - * Extend the region to be written back to include subsequent contiguously - * dirty pages if possible, but don't sleep while doing so. - */ -static void cifs_extend_writeback(struct address_space *mapping, - long *_count, - loff_t start, - int max_pages, - size_t max_len, - unsigned int *_len) -{ - struct folio_batch batch; - struct folio *folio; - unsigned int psize, nr_pages; - size_t len = *_len; - pgoff_t index = (start + len) / PAGE_SIZE; - bool stop = true; - unsigned int i; - XA_STATE(xas, &mapping->i_pages, index); - - folio_batch_init(&batch); - - do { - /* Firstly, we gather up a batch of contiguous dirty pages - * under the RCU read lock - but we can't clear the dirty flags - * there if any of those pages are mapped. - */ - rcu_read_lock(); - - xas_for_each(&xas, folio, ULONG_MAX) { - stop = true; - if (xas_retry(&xas, folio)) - continue; - if (xa_is_value(folio)) - break; - if (folio->index != index) - break; - if (!folio_try_get_rcu(folio)) { - xas_reset(&xas); - continue; - } - nr_pages = folio_nr_pages(folio); - if (nr_pages > max_pages) - break; - - /* Has the page moved or been split? */ - if (unlikely(folio != xas_reload(&xas))) { - folio_put(folio); - break; - } - - if (!folio_trylock(folio)) { - folio_put(folio); - break; - } - if (!folio_test_dirty(folio) || folio_test_writeback(folio)) { - folio_unlock(folio); - folio_put(folio); - break; - } - - max_pages -= nr_pages; - psize = folio_size(folio); - len += psize; - stop = false; - if (max_pages <= 0 || len >= max_len || *_count <= 0) - stop = true; - - index += nr_pages; - if (!folio_batch_add(&batch, folio)) - break; - if (stop) - break; - } - - if (!stop) - xas_pause(&xas); - rcu_read_unlock(); - - /* Now, if we obtained any pages, we can shift them to being - * writable and mark them for caching. - */ - if (!folio_batch_count(&batch)) - break; - - for (i = 0; i < folio_batch_count(&batch); i++) { - folio = batch.folios[i]; - /* The folio should be locked, dirty and not undergoing - * writeback from the loop above. - */ - if (!folio_clear_dirty_for_io(folio)) - WARN_ON(1); - folio_start_writeback(folio); - - *_count -= folio_nr_pages(folio); - folio_unlock(folio); - } - - folio_batch_release(&batch); - cond_resched(); - } while (!stop); - - *_len = len; -} - /* - * Write back the locked page and any subsequent non-locked dirty pages. + * Flush data on a strict file. */ -static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, - struct writeback_control *wbc, - struct folio *folio, - loff_t start, loff_t end) -{ - struct inode *inode = mapping->host; - struct TCP_Server_Info *server; - struct cifs_writedata *wdata; - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct cifs_credits credits_on_stack; - struct cifs_credits *credits = &credits_on_stack; - struct cifsFileInfo *cfile = NULL; - unsigned int xid, wsize, len; - loff_t i_size = i_size_read(inode); - size_t max_len; - long count = wbc->nr_to_write; - int rc; - - /* The folio should be locked, dirty and not undergoing writeback. */ - folio_start_writeback(folio); - - count -= folio_nr_pages(folio); - len = folio_size(folio); - - xid = get_xid(); - server = cifs_pick_channel(cifs_sb_master_tcon(cifs_sb)->ses); - - rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile); - if (rc) { - cifs_dbg(VFS, "No writable handle in writepages rc=%d\n", rc); - goto err_xid; - } - - rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->wsize, - &wsize, credits); - if (rc != 0) - goto err_close; - - wdata = cifs_writedata_alloc(cifs_writev_complete); - if (!wdata) { - rc = -ENOMEM; - goto err_uncredit; - } - - wdata->sync_mode = wbc->sync_mode; - wdata->offset = folio_pos(folio); - wdata->pid = cfile->pid; - wdata->credits = credits_on_stack; - wdata->cfile = cfile; - wdata->server = server; - cfile = NULL; - - /* Find all consecutive lockable dirty pages, stopping when we find a - * page that is not immediately lockable, is not dirty or is missing, - * or we reach the end of the range. - */ - if (start < i_size) { - /* Trim the write to the EOF; the extra data is ignored. Also - * put an upper limit on the size of a single storedata op. - */ - max_len = wsize; - max_len = min_t(unsigned long long, max_len, end - start + 1); - max_len = min_t(unsigned long long, max_len, i_size - start); - - if (len < max_len) { - int max_pages = INT_MAX; - -#ifdef CONFIG_CIFS_SMB_DIRECT - if (server->smbd_conn) - max_pages = server->smbd_conn->max_frmr_depth; -#endif - max_pages -= folio_nr_pages(folio); - - if (max_pages > 0) - cifs_extend_writeback(mapping, &count, start, - max_pages, max_len, &len); - } - len = min_t(loff_t, len, max_len); - } - - wdata->bytes = len; - - /* We now have a contiguous set of dirty pages, each with writeback - * set; the first page is still locked at this point, but all the rest - * have been unlocked. - */ - folio_unlock(folio); - - if (start < i_size) { - iov_iter_xarray(&wdata->iter, ITER_SOURCE, &mapping->i_pages, - start, len); - - rc = adjust_credits(wdata->server, &wdata->credits, wdata->bytes); - if (rc) - goto err_wdata; - - if (wdata->cfile->invalidHandle) - rc = -EAGAIN; - else - rc = wdata->server->ops->async_writev(wdata, - cifs_writedata_release); - if (rc >= 0) { - kref_put(&wdata->refcount, cifs_writedata_release); - goto err_close; - } - } else { - /* The dirty region was entirely beyond the EOF. */ - cifs_pages_written_back(inode, start, len); - rc = 0; - } - -err_wdata: - kref_put(&wdata->refcount, cifs_writedata_release); -err_uncredit: - add_credits_and_wake_if(server, credits, 0); -err_close: - if (cfile) - cifsFileInfo_put(cfile); -err_xid: - free_xid(xid); - if (rc == 0) { - wbc->nr_to_write = count; - rc = len; - } else if (is_retryable_error(rc)) { - cifs_pages_write_redirty(inode, start, len); - } else { - cifs_pages_write_failed(inode, start, len); - mapping_set_error(mapping, rc); - } - /* Indication to update ctime and mtime as close is deferred */ - set_bit(CIFS_INO_MODIFIED_ATTR, &CIFS_I(inode)->flags); - return rc; -} - -/* - * write a region of pages back to the server - */ -static int cifs_writepages_region(struct address_space *mapping, - struct writeback_control *wbc, - loff_t start, loff_t end, loff_t *_next) -{ - struct folio_batch fbatch; - int skips = 0; - - folio_batch_init(&fbatch); - do { - int nr; - pgoff_t index = start / PAGE_SIZE; - - nr = filemap_get_folios_tag(mapping, &index, end / PAGE_SIZE, - PAGECACHE_TAG_DIRTY, &fbatch); - if (!nr) - break; - - for (int i = 0; i < nr; i++) { - ssize_t ret; - struct folio *folio = fbatch.folios[i]; - -redo_folio: - start = folio_pos(folio); /* May regress with THPs */ - - /* At this point we hold neither the i_pages lock nor the - * page lock: the page may be truncated or invalidated - * (changing page->mapping to NULL), or even swizzled - * back from swapper_space to tmpfs file mapping - */ - if (wbc->sync_mode != WB_SYNC_NONE) { - ret = folio_lock_killable(folio); - if (ret < 0) - goto write_error; - } else { - if (!folio_trylock(folio)) - goto skip_write; - } - - if (folio->mapping != mapping || - !folio_test_dirty(folio)) { - start += folio_size(folio); - folio_unlock(folio); - continue; - } - - if (folio_test_writeback(folio) || - folio_test_fscache(folio)) { - folio_unlock(folio); - if (wbc->sync_mode == WB_SYNC_NONE) - goto skip_write; - - folio_wait_writeback(folio); -#ifdef CONFIG_CIFS_FSCACHE - folio_wait_fscache(folio); -#endif - goto redo_folio; - } - - if (!folio_clear_dirty_for_io(folio)) - /* We hold the page lock - it should've been dirty. */ - WARN_ON(1); - - ret = cifs_write_back_from_locked_folio(mapping, wbc, folio, start, end); - if (ret < 0) - goto write_error; - - start += ret; - continue; - -write_error: - folio_batch_release(&fbatch); - *_next = start; - return ret; - -skip_write: - /* - * Too many skipped writes, or need to reschedule? - * Treat it as a write error without an error code. - */ - if (skips >= 5 || need_resched()) { - ret = 0; - goto write_error; - } - - /* Otherwise, just skip that folio and go on to the next */ - skips++; - start += folio_size(folio); - continue; - } - - folio_batch_release(&fbatch); - cond_resched(); - } while (wbc->nr_to_write > 0); - - *_next = start; - return 0; -} - -/* - * Write some of the pending data back to the server - */ -static int cifs_writepages(struct address_space *mapping, - struct writeback_control *wbc) -{ - loff_t start, next; - int ret; - - /* We have to be careful as we can end up racing with setattr() - * truncating the pagecache since the caller doesn't take a lock here - * to prevent it. - */ - - if (wbc->range_cyclic) { - start = mapping->writeback_index * PAGE_SIZE; - ret = cifs_writepages_region(mapping, wbc, start, LLONG_MAX, &next); - if (ret == 0) { - mapping->writeback_index = next / PAGE_SIZE; - if (start > 0 && wbc->nr_to_write > 0) { - ret = cifs_writepages_region(mapping, wbc, 0, - start, &next); - if (ret == 0) - mapping->writeback_index = - next / PAGE_SIZE; - } - } - } else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) { - ret = cifs_writepages_region(mapping, wbc, 0, LLONG_MAX, &next); - if (wbc->nr_to_write > 0 && ret == 0) - mapping->writeback_index = next / PAGE_SIZE; - } else { - ret = cifs_writepages_region(mapping, wbc, - wbc->range_start, wbc->range_end, &next); - } - - return ret; -} - -static int -cifs_writepage_locked(struct page *page, struct writeback_control *wbc) -{ - int rc; - unsigned int xid; - - xid = get_xid(); -/* BB add check for wbc flags */ - get_page(page); - if (!PageUptodate(page)) - cifs_dbg(FYI, "ppw - page not up to date\n"); - - /* - * Set the "writeback" flag, and clear "dirty" in the radix tree. - * - * A writepage() implementation always needs to do either this, - * or re-dirty the page with "redirty_page_for_writepage()" in - * the case of a failure. - * - * Just unlocking the page will cause the radix tree tag-bits - * to fail to update with the state of the page correctly. - */ - set_page_writeback(page); -retry_write: - rc = cifs_partialpagewrite(page, 0, PAGE_SIZE); - if (is_retryable_error(rc)) { - if (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN) - goto retry_write; - redirty_page_for_writepage(wbc, page); - } else if (rc != 0) { - SetPageError(page); - mapping_set_error(page->mapping, rc); - } else { - SetPageUptodate(page); - } - end_page_writeback(page); - put_page(page); - free_xid(xid); - return rc; -} - -static int cifs_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) -{ - int rc; - struct inode *inode = mapping->host; - struct cifsFileInfo *cfile = file->private_data; - struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb); - struct folio *folio = page_folio(page); - __u32 pid; - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) - pid = cfile->pid; - else - pid = current->tgid; - - cifs_dbg(FYI, "write_end for page %p from pos %lld with %d bytes\n", - page, pos, copied); - - if (folio_test_checked(folio)) { - if (copied == len) - folio_mark_uptodate(folio); - folio_clear_checked(folio); - } else if (!folio_test_uptodate(folio) && copied == PAGE_SIZE) - folio_mark_uptodate(folio); - - if (!folio_test_uptodate(folio)) { - char *page_data; - unsigned offset = pos & (PAGE_SIZE - 1); - unsigned int xid; - - xid = get_xid(); - /* this is probably better than directly calling - partialpage_write since in this function the file handle is - known which we might as well leverage */ - /* BB check if anything else missing out of ppw - such as updating last write time */ - page_data = kmap(page); - rc = cifs_write(cfile, pid, page_data + offset, copied, &pos); - /* if (rc < 0) should we set writebehind rc? */ - kunmap(page); - - free_xid(xid); - } else { - rc = copied; - pos += copied; - set_page_dirty(page); - } - - if (rc > 0) { - spin_lock(&inode->i_lock); - if (pos > inode->i_size) { - i_size_write(inode, pos); - inode->i_blocks = (512 - 1 + pos) >> 9; - } - spin_unlock(&inode->i_lock); - } - - unlock_page(page); - put_page(page); - /* Indication to update ctime and mtime as close is deferred */ - set_bit(CIFS_INO_MODIFIED_ATTR, &CIFS_I(inode)->flags); - - return rc; -} - int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, int datasync) { @@ -3162,6 +2674,9 @@ strict_fsync_exit: return rc; } +/* + * Flush data on a non-strict data. + */ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) { unsigned int xid; @@ -3228,481 +2743,6 @@ int cifs_flush(struct file *file, fl_owner_t id) return rc; } -static void -cifs_uncached_writedata_release(struct kref *refcount) -{ - struct cifs_writedata *wdata = container_of(refcount, - struct cifs_writedata, refcount); - - kref_put(&wdata->ctx->refcount, cifs_aio_ctx_release); - cifs_writedata_release(refcount); -} - -static void collect_uncached_write_data(struct cifs_aio_ctx *ctx); - -static void -cifs_uncached_writev_complete(struct work_struct *work) -{ - struct cifs_writedata *wdata = container_of(work, - struct cifs_writedata, work); - struct inode *inode = d_inode(wdata->cfile->dentry); - struct cifsInodeInfo *cifsi = CIFS_I(inode); - - spin_lock(&inode->i_lock); - cifs_update_eof(cifsi, wdata->offset, wdata->bytes); - if (cifsi->netfs.remote_i_size > inode->i_size) - i_size_write(inode, cifsi->netfs.remote_i_size); - spin_unlock(&inode->i_lock); - - complete(&wdata->done); - collect_uncached_write_data(wdata->ctx); - /* the below call can possibly free the last ref to aio ctx */ - kref_put(&wdata->refcount, cifs_uncached_writedata_release); -} - -static int -cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list, - struct cifs_aio_ctx *ctx) -{ - unsigned int wsize; - struct cifs_credits credits; - int rc; - struct TCP_Server_Info *server = wdata->server; - - do { - if (wdata->cfile->invalidHandle) { - rc = cifs_reopen_file(wdata->cfile, false); - if (rc == -EAGAIN) - continue; - else if (rc) - break; - } - - - /* - * Wait for credits to resend this wdata. - * Note: we are attempting to resend the whole wdata not in - * segments - */ - do { - rc = server->ops->wait_mtu_credits(server, wdata->bytes, - &wsize, &credits); - if (rc) - goto fail; - - if (wsize < wdata->bytes) { - add_credits_and_wake_if(server, &credits, 0); - msleep(1000); - } - } while (wsize < wdata->bytes); - wdata->credits = credits; - - rc = adjust_credits(server, &wdata->credits, wdata->bytes); - - if (!rc) { - if (wdata->cfile->invalidHandle) - rc = -EAGAIN; - else { - wdata->replay = true; -#ifdef CONFIG_CIFS_SMB_DIRECT - if (wdata->mr) { - wdata->mr->need_invalidate = true; - smbd_deregister_mr(wdata->mr); - wdata->mr = NULL; - } -#endif - rc = server->ops->async_writev(wdata, - cifs_uncached_writedata_release); - } - } - - /* If the write was successfully sent, we are done */ - if (!rc) { - list_add_tail(&wdata->list, wdata_list); - return 0; - } - - /* Roll back credits and retry if needed */ - add_credits_and_wake_if(server, &wdata->credits, 0); - } while (rc == -EAGAIN); - -fail: - kref_put(&wdata->refcount, cifs_uncached_writedata_release); - return rc; -} - -/* - * Select span of a bvec iterator we're going to use. Limit it by both maximum - * size and maximum number of segments. - */ -static size_t cifs_limit_bvec_subset(const struct iov_iter *iter, size_t max_size, - size_t max_segs, unsigned int *_nsegs) -{ - const struct bio_vec *bvecs = iter->bvec; - unsigned int nbv = iter->nr_segs, ix = 0, nsegs = 0; - size_t len, span = 0, n = iter->count; - size_t skip = iter->iov_offset; - - if (WARN_ON(!iov_iter_is_bvec(iter)) || n == 0) - return 0; - - while (n && ix < nbv && skip) { - len = bvecs[ix].bv_len; - if (skip < len) - break; - skip -= len; - n -= len; - ix++; - } - - while (n && ix < nbv) { - len = min3(n, bvecs[ix].bv_len - skip, max_size); - span += len; - max_size -= len; - nsegs++; - ix++; - if (max_size == 0 || nsegs >= max_segs) - break; - skip = 0; - n -= len; - } - - *_nsegs = nsegs; - return span; -} - -static int -cifs_write_from_iter(loff_t fpos, size_t len, struct iov_iter *from, - struct cifsFileInfo *open_file, - struct cifs_sb_info *cifs_sb, struct list_head *wdata_list, - struct cifs_aio_ctx *ctx) -{ - int rc = 0; - size_t cur_len, max_len; - struct cifs_writedata *wdata; - pid_t pid; - struct TCP_Server_Info *server; - unsigned int xid, max_segs = INT_MAX; - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) - pid = open_file->pid; - else - pid = current->tgid; - - server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses); - xid = get_xid(); - -#ifdef CONFIG_CIFS_SMB_DIRECT - if (server->smbd_conn) - max_segs = server->smbd_conn->max_frmr_depth; -#endif - - do { - struct cifs_credits credits_on_stack; - struct cifs_credits *credits = &credits_on_stack; - unsigned int wsize, nsegs = 0; - - if (signal_pending(current)) { - rc = -EINTR; - break; - } - - if (open_file->invalidHandle) { - rc = cifs_reopen_file(open_file, false); - if (rc == -EAGAIN) - continue; - else if (rc) - break; - } - - rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->wsize, - &wsize, credits); - if (rc) - break; - - max_len = min_t(const size_t, len, wsize); - if (!max_len) { - rc = -EAGAIN; - add_credits_and_wake_if(server, credits, 0); - break; - } - - cur_len = cifs_limit_bvec_subset(from, max_len, max_segs, &nsegs); - cifs_dbg(FYI, "write_from_iter len=%zx/%zx nsegs=%u/%lu/%u\n", - cur_len, max_len, nsegs, from->nr_segs, max_segs); - if (cur_len == 0) { - rc = -EIO; - add_credits_and_wake_if(server, credits, 0); - break; - } - - wdata = cifs_writedata_alloc(cifs_uncached_writev_complete); - if (!wdata) { - rc = -ENOMEM; - add_credits_and_wake_if(server, credits, 0); - break; - } - - wdata->sync_mode = WB_SYNC_ALL; - wdata->offset = (__u64)fpos; - wdata->cfile = cifsFileInfo_get(open_file); - wdata->server = server; - wdata->pid = pid; - wdata->bytes = cur_len; - wdata->credits = credits_on_stack; - wdata->iter = *from; - wdata->ctx = ctx; - kref_get(&ctx->refcount); - - iov_iter_truncate(&wdata->iter, cur_len); - - rc = adjust_credits(server, &wdata->credits, wdata->bytes); - - if (!rc) { - if (wdata->cfile->invalidHandle) - rc = -EAGAIN; - else - rc = server->ops->async_writev(wdata, - cifs_uncached_writedata_release); - } - - if (rc) { - add_credits_and_wake_if(server, &wdata->credits, 0); - kref_put(&wdata->refcount, - cifs_uncached_writedata_release); - if (rc == -EAGAIN) - continue; - break; - } - - list_add_tail(&wdata->list, wdata_list); - iov_iter_advance(from, cur_len); - fpos += cur_len; - len -= cur_len; - } while (len > 0); - - free_xid(xid); - return rc; -} - -static void collect_uncached_write_data(struct cifs_aio_ctx *ctx) -{ - struct cifs_writedata *wdata, *tmp; - struct cifs_tcon *tcon; - struct cifs_sb_info *cifs_sb; - struct dentry *dentry = ctx->cfile->dentry; - ssize_t rc; - - tcon = tlink_tcon(ctx->cfile->tlink); - cifs_sb = CIFS_SB(dentry->d_sb); - - mutex_lock(&ctx->aio_mutex); - - if (list_empty(&ctx->list)) { - mutex_unlock(&ctx->aio_mutex); - return; - } - - rc = ctx->rc; - /* - * Wait for and collect replies for any successful sends in order of - * increasing offset. Once an error is hit, then return without waiting - * for any more replies. - */ -restart_loop: - list_for_each_entry_safe(wdata, tmp, &ctx->list, list) { - if (!rc) { - if (!try_wait_for_completion(&wdata->done)) { - mutex_unlock(&ctx->aio_mutex); - return; - } - - if (wdata->result) - rc = wdata->result; - else - ctx->total_len += wdata->bytes; - - /* resend call if it's a retryable error */ - if (rc == -EAGAIN) { - struct list_head tmp_list; - struct iov_iter tmp_from = ctx->iter; - - INIT_LIST_HEAD(&tmp_list); - list_del_init(&wdata->list); - - if (ctx->direct_io) - rc = cifs_resend_wdata( - wdata, &tmp_list, ctx); - else { - iov_iter_advance(&tmp_from, - wdata->offset - ctx->pos); - - rc = cifs_write_from_iter(wdata->offset, - wdata->bytes, &tmp_from, - ctx->cfile, cifs_sb, &tmp_list, - ctx); - - kref_put(&wdata->refcount, - cifs_uncached_writedata_release); - } - - list_splice(&tmp_list, &ctx->list); - goto restart_loop; - } - } - list_del_init(&wdata->list); - kref_put(&wdata->refcount, cifs_uncached_writedata_release); - } - - cifs_stats_bytes_written(tcon, ctx->total_len); - set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags); - - ctx->rc = (rc == 0) ? ctx->total_len : rc; - - mutex_unlock(&ctx->aio_mutex); - - if (ctx->iocb && ctx->iocb->ki_complete) - ctx->iocb->ki_complete(ctx->iocb, ctx->rc); - else - complete(&ctx->done); -} - -static ssize_t __cifs_writev( - struct kiocb *iocb, struct iov_iter *from, bool direct) -{ - struct file *file = iocb->ki_filp; - ssize_t total_written = 0; - struct cifsFileInfo *cfile; - struct cifs_tcon *tcon; - struct cifs_sb_info *cifs_sb; - struct cifs_aio_ctx *ctx; - int rc; - - rc = generic_write_checks(iocb, from); - if (rc <= 0) - return rc; - - cifs_sb = CIFS_FILE_SB(file); - cfile = file->private_data; - tcon = tlink_tcon(cfile->tlink); - - if (!tcon->ses->server->ops->async_writev) - return -ENOSYS; - - ctx = cifs_aio_ctx_alloc(); - if (!ctx) - return -ENOMEM; - - ctx->cfile = cifsFileInfo_get(cfile); - - if (!is_sync_kiocb(iocb)) - ctx->iocb = iocb; - - ctx->pos = iocb->ki_pos; - ctx->direct_io = direct; - ctx->nr_pinned_pages = 0; - - if (user_backed_iter(from)) { - /* - * Extract IOVEC/UBUF-type iterators to a BVEC-type iterator as - * they contain references to the calling process's virtual - * memory layout which won't be available in an async worker - * thread. This also takes a pin on every folio involved. - */ - rc = netfs_extract_user_iter(from, iov_iter_count(from), - &ctx->iter, 0); - if (rc < 0) { - kref_put(&ctx->refcount, cifs_aio_ctx_release); - return rc; - } - - ctx->nr_pinned_pages = rc; - ctx->bv = (void *)ctx->iter.bvec; - ctx->bv_need_unpin = iov_iter_extract_will_pin(from); - } else if ((iov_iter_is_bvec(from) || iov_iter_is_kvec(from)) && - !is_sync_kiocb(iocb)) { - /* - * If the op is asynchronous, we need to copy the list attached - * to a BVEC/KVEC-type iterator, but we assume that the storage - * will be pinned by the caller; in any case, we may or may not - * be able to pin the pages, so we don't try. - */ - ctx->bv = (void *)dup_iter(&ctx->iter, from, GFP_KERNEL); - if (!ctx->bv) { - kref_put(&ctx->refcount, cifs_aio_ctx_release); - return -ENOMEM; - } - } else { - /* - * Otherwise, we just pass the iterator down as-is and rely on - * the caller to make sure the pages referred to by the - * iterator don't evaporate. - */ - ctx->iter = *from; - } - - ctx->len = iov_iter_count(&ctx->iter); - - /* grab a lock here due to read response handlers can access ctx */ - mutex_lock(&ctx->aio_mutex); - - rc = cifs_write_from_iter(iocb->ki_pos, ctx->len, &ctx->iter, - cfile, cifs_sb, &ctx->list, ctx); - - /* - * If at least one write was successfully sent, then discard any rc - * value from the later writes. If the other write succeeds, then - * we'll end up returning whatever was written. If it fails, then - * we'll get a new rc value from that. - */ - if (!list_empty(&ctx->list)) - rc = 0; - - mutex_unlock(&ctx->aio_mutex); - - if (rc) { - kref_put(&ctx->refcount, cifs_aio_ctx_release); - return rc; - } - - if (!is_sync_kiocb(iocb)) { - kref_put(&ctx->refcount, cifs_aio_ctx_release); - return -EIOCBQUEUED; - } - - rc = wait_for_completion_killable(&ctx->done); - if (rc) { - mutex_lock(&ctx->aio_mutex); - ctx->rc = rc = -EINTR; - total_written = ctx->total_len; - mutex_unlock(&ctx->aio_mutex); - } else { - rc = ctx->rc; - total_written = ctx->total_len; - } - - kref_put(&ctx->refcount, cifs_aio_ctx_release); - - if (unlikely(!total_written)) - return rc; - - iocb->ki_pos += total_written; - return total_written; -} - -ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from) -{ - struct file *file = iocb->ki_filp; - - cifs_revalidate_mapping(file->f_inode); - return __cifs_writev(iocb, from, true); -} - -ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from) -{ - return __cifs_writev(iocb, from, false); -} - static ssize_t cifs_writev(struct kiocb *iocb, struct iov_iter *from) { @@ -3713,7 +2753,10 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; ssize_t rc; - inode_lock(inode); + rc = netfs_start_io_write(inode); + if (rc < 0) + return rc; + /* * We need to hold the sem to be sure nobody modifies lock list * with a brlock that prevents writing. @@ -3727,13 +2770,12 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from), server->vals->exclusive_lock_type, 0, NULL, CIFS_WRITE_OP)) - rc = __generic_file_write_iter(iocb, from); + rc = netfs_buffered_write_iter_locked(iocb, from, NULL); else rc = -EACCES; out: up_read(&cinode->lock_sem); - inode_unlock(inode); - + netfs_end_io_write(inode); if (rc > 0) rc = generic_write_sync(iocb, rc); return rc; @@ -3756,9 +2798,9 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from) if (CIFS_CACHE_WRITE(cinode)) { if (cap_unix(tcon->ses) && - (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) - && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) { - written = generic_file_write_iter(iocb, from); + (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && + ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) { + written = netfs_file_write_iter(iocb, from); goto out; } written = cifs_writev(iocb, from); @@ -3770,7 +2812,7 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from) * affected pages because it may cause a error with mandatory locks on * these pages but not on the region from pos to ppos+len-1. */ - written = cifs_user_writev(iocb, from); + written = netfs_file_write_iter(iocb, from); if (CIFS_CACHE_READ(cinode)) { /* * We have read level caching and we have just sent a write @@ -3789,449 +2831,55 @@ out: return written; } -static struct cifs_readdata *cifs_readdata_alloc(work_func_t complete) -{ - struct cifs_readdata *rdata; - - rdata = kzalloc(sizeof(*rdata), GFP_KERNEL); - if (rdata) { - kref_init(&rdata->refcount); - INIT_LIST_HEAD(&rdata->list); - init_completion(&rdata->done); - INIT_WORK(&rdata->work, complete); - } - - return rdata; -} - -void -cifs_readdata_release(struct kref *refcount) -{ - struct cifs_readdata *rdata = container_of(refcount, - struct cifs_readdata, refcount); - - if (rdata->ctx) - kref_put(&rdata->ctx->refcount, cifs_aio_ctx_release); -#ifdef CONFIG_CIFS_SMB_DIRECT - if (rdata->mr) { - smbd_deregister_mr(rdata->mr); - rdata->mr = NULL; - } -#endif - if (rdata->cfile) - cifsFileInfo_put(rdata->cfile); - - kfree(rdata); -} - -static void collect_uncached_read_data(struct cifs_aio_ctx *ctx); - -static void -cifs_uncached_readv_complete(struct work_struct *work) +ssize_t cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct cifs_readdata *rdata = container_of(work, - struct cifs_readdata, work); - - complete(&rdata->done); - collect_uncached_read_data(rdata->ctx); - /* the below call can possibly free the last ref to aio ctx */ - kref_put(&rdata->refcount, cifs_readdata_release); -} - -static int cifs_resend_rdata(struct cifs_readdata *rdata, - struct list_head *rdata_list, - struct cifs_aio_ctx *ctx) -{ - unsigned int rsize; - struct cifs_credits credits; - int rc; - struct TCP_Server_Info *server; - - /* XXX: should we pick a new channel here? */ - server = rdata->server; - - do { - if (rdata->cfile->invalidHandle) { - rc = cifs_reopen_file(rdata->cfile, true); - if (rc == -EAGAIN) - continue; - else if (rc) - break; - } - - /* - * Wait for credits to resend this rdata. - * Note: we are attempting to resend the whole rdata not in - * segments - */ - do { - rc = server->ops->wait_mtu_credits(server, rdata->bytes, - &rsize, &credits); - - if (rc) - goto fail; - - if (rsize < rdata->bytes) { - add_credits_and_wake_if(server, &credits, 0); - msleep(1000); - } - } while (rsize < rdata->bytes); - rdata->credits = credits; - - rc = adjust_credits(server, &rdata->credits, rdata->bytes); - if (!rc) { - if (rdata->cfile->invalidHandle) - rc = -EAGAIN; - else { -#ifdef CONFIG_CIFS_SMB_DIRECT - if (rdata->mr) { - rdata->mr->need_invalidate = true; - smbd_deregister_mr(rdata->mr); - rdata->mr = NULL; - } -#endif - rc = server->ops->async_readv(rdata); - } - } - - /* If the read was successfully sent, we are done */ - if (!rc) { - /* Add to aio pending list */ - list_add_tail(&rdata->list, rdata_list); - return 0; - } - - /* Roll back credits and retry if needed */ - add_credits_and_wake_if(server, &rdata->credits, 0); - } while (rc == -EAGAIN); - -fail: - kref_put(&rdata->refcount, cifs_readdata_release); - return rc; -} - -static int -cifs_send_async_read(loff_t fpos, size_t len, struct cifsFileInfo *open_file, - struct cifs_sb_info *cifs_sb, struct list_head *rdata_list, - struct cifs_aio_ctx *ctx) -{ - struct cifs_readdata *rdata; - unsigned int rsize, nsegs, max_segs = INT_MAX; - struct cifs_credits credits_on_stack; - struct cifs_credits *credits = &credits_on_stack; - size_t cur_len, max_len; - int rc; - pid_t pid; - struct TCP_Server_Info *server; - - server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses); - -#ifdef CONFIG_CIFS_SMB_DIRECT - if (server->smbd_conn) - max_segs = server->smbd_conn->max_frmr_depth; -#endif - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) - pid = open_file->pid; - else - pid = current->tgid; - - do { - if (open_file->invalidHandle) { - rc = cifs_reopen_file(open_file, true); - if (rc == -EAGAIN) - continue; - else if (rc) - break; - } - - if (cifs_sb->ctx->rsize == 0) - cifs_sb->ctx->rsize = - server->ops->negotiate_rsize(tlink_tcon(open_file->tlink), - cifs_sb->ctx); - - rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, - &rsize, credits); - if (rc) - break; - - max_len = min_t(size_t, len, rsize); - - cur_len = cifs_limit_bvec_subset(&ctx->iter, max_len, - max_segs, &nsegs); - cifs_dbg(FYI, "read-to-iter len=%zx/%zx nsegs=%u/%lu/%u\n", - cur_len, max_len, nsegs, ctx->iter.nr_segs, max_segs); - if (cur_len == 0) { - rc = -EIO; - add_credits_and_wake_if(server, credits, 0); - break; - } - - rdata = cifs_readdata_alloc(cifs_uncached_readv_complete); - if (!rdata) { - add_credits_and_wake_if(server, credits, 0); - rc = -ENOMEM; - break; - } - - rdata->server = server; - rdata->cfile = cifsFileInfo_get(open_file); - rdata->offset = fpos; - rdata->bytes = cur_len; - rdata->pid = pid; - rdata->credits = credits_on_stack; - rdata->ctx = ctx; - kref_get(&ctx->refcount); - - rdata->iter = ctx->iter; - iov_iter_truncate(&rdata->iter, cur_len); - - rc = adjust_credits(server, &rdata->credits, rdata->bytes); - - if (!rc) { - if (rdata->cfile->invalidHandle) - rc = -EAGAIN; - else - rc = server->ops->async_readv(rdata); - } + ssize_t rc; + struct inode *inode = file_inode(iocb->ki_filp); - if (rc) { - add_credits_and_wake_if(server, &rdata->credits, 0); - kref_put(&rdata->refcount, cifs_readdata_release); - if (rc == -EAGAIN) - continue; - break; - } + if (iocb->ki_flags & IOCB_DIRECT) + return netfs_unbuffered_read_iter(iocb, iter); - list_add_tail(&rdata->list, rdata_list); - iov_iter_advance(&ctx->iter, cur_len); - fpos += cur_len; - len -= cur_len; - } while (len > 0); + rc = cifs_revalidate_mapping(inode); + if (rc) + return rc; - return rc; + return netfs_file_read_iter(iocb, iter); } -static void -collect_uncached_read_data(struct cifs_aio_ctx *ctx) +ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { - struct cifs_readdata *rdata, *tmp; - struct cifs_sb_info *cifs_sb; + struct inode *inode = file_inode(iocb->ki_filp); + struct cifsInodeInfo *cinode = CIFS_I(inode); + ssize_t written; int rc; - cifs_sb = CIFS_SB(ctx->cfile->dentry->d_sb); - - mutex_lock(&ctx->aio_mutex); - - if (list_empty(&ctx->list)) { - mutex_unlock(&ctx->aio_mutex); - return; - } - - rc = ctx->rc; - /* the loop below should proceed in the order of increasing offsets */ -again: - list_for_each_entry_safe(rdata, tmp, &ctx->list, list) { - if (!rc) { - if (!try_wait_for_completion(&rdata->done)) { - mutex_unlock(&ctx->aio_mutex); - return; - } - - if (rdata->result == -EAGAIN) { - /* resend call if it's a retryable error */ - struct list_head tmp_list; - unsigned int got_bytes = rdata->got_bytes; - - list_del_init(&rdata->list); - INIT_LIST_HEAD(&tmp_list); - - if (ctx->direct_io) { - /* - * Re-use rdata as this is a - * direct I/O - */ - rc = cifs_resend_rdata( - rdata, - &tmp_list, ctx); - } else { - rc = cifs_send_async_read( - rdata->offset + got_bytes, - rdata->bytes - got_bytes, - rdata->cfile, cifs_sb, - &tmp_list, ctx); - - kref_put(&rdata->refcount, - cifs_readdata_release); - } - - list_splice(&tmp_list, &ctx->list); - - goto again; - } else if (rdata->result) - rc = rdata->result; - - /* if there was a short read -- discard anything left */ - if (rdata->got_bytes && rdata->got_bytes < rdata->bytes) - rc = -ENODATA; - - ctx->total_len += rdata->got_bytes; - } - list_del_init(&rdata->list); - kref_put(&rdata->refcount, cifs_readdata_release); - } - - /* mask nodata case */ - if (rc == -ENODATA) - rc = 0; - - ctx->rc = (rc == 0) ? (ssize_t)ctx->total_len : rc; - - mutex_unlock(&ctx->aio_mutex); - - if (ctx->iocb && ctx->iocb->ki_complete) - ctx->iocb->ki_complete(ctx->iocb, ctx->rc); - else - complete(&ctx->done); -} - -static ssize_t __cifs_readv( - struct kiocb *iocb, struct iov_iter *to, bool direct) -{ - size_t len; - struct file *file = iocb->ki_filp; - struct cifs_sb_info *cifs_sb; - struct cifsFileInfo *cfile; - struct cifs_tcon *tcon; - ssize_t rc, total_read = 0; - loff_t offset = iocb->ki_pos; - struct cifs_aio_ctx *ctx; - - len = iov_iter_count(to); - if (!len) - return 0; - - cifs_sb = CIFS_FILE_SB(file); - cfile = file->private_data; - tcon = tlink_tcon(cfile->tlink); - - if (!tcon->ses->server->ops->async_readv) - return -ENOSYS; - - if ((file->f_flags & O_ACCMODE) == O_WRONLY) - cifs_dbg(FYI, "attempting read on write only file instance\n"); - - ctx = cifs_aio_ctx_alloc(); - if (!ctx) - return -ENOMEM; - - ctx->pos = offset; - ctx->direct_io = direct; - ctx->len = len; - ctx->cfile = cifsFileInfo_get(cfile); - ctx->nr_pinned_pages = 0; - - if (!is_sync_kiocb(iocb)) - ctx->iocb = iocb; - - if (user_backed_iter(to)) { - /* - * Extract IOVEC/UBUF-type iterators to a BVEC-type iterator as - * they contain references to the calling process's virtual - * memory layout which won't be available in an async worker - * thread. This also takes a pin on every folio involved. - */ - rc = netfs_extract_user_iter(to, iov_iter_count(to), - &ctx->iter, 0); - if (rc < 0) { - kref_put(&ctx->refcount, cifs_aio_ctx_release); - return rc; - } - - ctx->nr_pinned_pages = rc; - ctx->bv = (void *)ctx->iter.bvec; - ctx->bv_need_unpin = iov_iter_extract_will_pin(to); - ctx->should_dirty = true; - } else if ((iov_iter_is_bvec(to) || iov_iter_is_kvec(to)) && - !is_sync_kiocb(iocb)) { - /* - * If the op is asynchronous, we need to copy the list attached - * to a BVEC/KVEC-type iterator, but we assume that the storage - * will be retained by the caller; in any case, we may or may - * not be able to pin the pages, so we don't try. - */ - ctx->bv = (void *)dup_iter(&ctx->iter, to, GFP_KERNEL); - if (!ctx->bv) { - kref_put(&ctx->refcount, cifs_aio_ctx_release); - return -ENOMEM; - } - } else { - /* - * Otherwise, we just pass the iterator down as-is and rely on - * the caller to make sure the pages referred to by the - * iterator don't evaporate. - */ - ctx->iter = *to; - } - - if (direct) { - rc = filemap_write_and_wait_range(file->f_inode->i_mapping, - offset, offset + len - 1); - if (rc) { - kref_put(&ctx->refcount, cifs_aio_ctx_release); - return -EAGAIN; + if (iocb->ki_filp->f_flags & O_DIRECT) { + written = netfs_unbuffered_write_iter(iocb, from); + if (written > 0 && CIFS_CACHE_READ(cinode)) { + cifs_zap_mapping(inode); + cifs_dbg(FYI, + "Set no oplock for inode=%p after a write operation\n", + inode); + cinode->oplock = 0; } + return written; } - /* grab a lock here due to read response handlers can access ctx */ - mutex_lock(&ctx->aio_mutex); - - rc = cifs_send_async_read(offset, len, cfile, cifs_sb, &ctx->list, ctx); - - /* if at least one read request send succeeded, then reset rc */ - if (!list_empty(&ctx->list)) - rc = 0; - - mutex_unlock(&ctx->aio_mutex); - - if (rc) { - kref_put(&ctx->refcount, cifs_aio_ctx_release); - return rc; - } - - if (!is_sync_kiocb(iocb)) { - kref_put(&ctx->refcount, cifs_aio_ctx_release); - return -EIOCBQUEUED; - } - - rc = wait_for_completion_killable(&ctx->done); - if (rc) { - mutex_lock(&ctx->aio_mutex); - ctx->rc = rc = -EINTR; - total_read = ctx->total_len; - mutex_unlock(&ctx->aio_mutex); - } else { - rc = ctx->rc; - total_read = ctx->total_len; - } + written = cifs_get_writer(cinode); + if (written) + return written; - kref_put(&ctx->refcount, cifs_aio_ctx_release); + written = netfs_file_write_iter(iocb, from); - if (total_read) { - iocb->ki_pos += total_read; - return total_read; + if (!CIFS_CACHE_WRITE(CIFS_I(inode))) { + rc = filemap_fdatawrite(inode->i_mapping); + if (rc) + cifs_dbg(FYI, "cifs_file_write_iter: %d rc on %p inode\n", + rc, inode); } - return rc; -} -ssize_t cifs_direct_readv(struct kiocb *iocb, struct iov_iter *to) -{ - return __cifs_readv(iocb, to, true); -} - -ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to) -{ - return __cifs_readv(iocb, to, false); + cifs_put_writer(cinode); + return written; } ssize_t @@ -4254,140 +2902,52 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to) * pos+len-1. */ if (!CIFS_CACHE_READ(cinode)) - return cifs_user_readv(iocb, to); + return netfs_unbuffered_read_iter(iocb, to); if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && - ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) - return generic_file_read_iter(iocb, to); + ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) { + if (iocb->ki_flags & IOCB_DIRECT) + return netfs_unbuffered_read_iter(iocb, to); + return netfs_buffered_read_iter(iocb, to); + } /* * We need to hold the sem to be sure nobody modifies lock list * with a brlock that prevents reading. */ - down_read(&cinode->lock_sem); - if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(to), - tcon->ses->server->vals->shared_lock_type, - 0, NULL, CIFS_READ_OP)) - rc = generic_file_read_iter(iocb, to); - up_read(&cinode->lock_sem); - return rc; -} - -static ssize_t -cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset) -{ - int rc = -EACCES; - unsigned int bytes_read = 0; - unsigned int total_read; - unsigned int current_read_size; - unsigned int rsize; - struct cifs_sb_info *cifs_sb; - struct cifs_tcon *tcon; - struct TCP_Server_Info *server; - unsigned int xid; - char *cur_offset; - struct cifsFileInfo *open_file; - struct cifs_io_parms io_parms = {0}; - int buf_type = CIFS_NO_BUFFER; - __u32 pid; - - xid = get_xid(); - cifs_sb = CIFS_FILE_SB(file); - - /* FIXME: set up handlers for larger reads and/or convert to async */ - rsize = min_t(unsigned int, cifs_sb->ctx->rsize, CIFSMaxBufSize); - - if (file->private_data == NULL) { - rc = -EBADF; - free_xid(xid); - return rc; - } - open_file = file->private_data; - tcon = tlink_tcon(open_file->tlink); - server = cifs_pick_channel(tcon->ses); - - if (!server->ops->sync_read) { - free_xid(xid); - return -ENOSYS; - } - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) - pid = open_file->pid; - else - pid = current->tgid; - - if ((file->f_flags & O_ACCMODE) == O_WRONLY) - cifs_dbg(FYI, "attempting read on write only file instance\n"); - - for (total_read = 0, cur_offset = read_data; read_size > total_read; - total_read += bytes_read, cur_offset += bytes_read) { - do { - current_read_size = min_t(uint, read_size - total_read, - rsize); - /* - * For windows me and 9x we do not want to request more - * than it negotiated since it will refuse the read - * then. - */ - if (!(tcon->ses->capabilities & - tcon->ses->server->vals->cap_large_files)) { - current_read_size = min_t(uint, - current_read_size, CIFSMaxBufSize); - } - if (open_file->invalidHandle) { - rc = cifs_reopen_file(open_file, true); - if (rc != 0) - break; - } - io_parms.pid = pid; - io_parms.tcon = tcon; - io_parms.offset = *offset; - io_parms.length = current_read_size; - io_parms.server = server; - rc = server->ops->sync_read(xid, &open_file->fid, &io_parms, - &bytes_read, &cur_offset, - &buf_type); - } while (rc == -EAGAIN); - - if (rc || (bytes_read == 0)) { - if (total_read) { - break; - } else { - free_xid(xid); - return rc; - } - } else { - cifs_stats_bytes_read(tcon, total_read); - *offset += bytes_read; - } + if (iocb->ki_flags & IOCB_DIRECT) { + rc = netfs_start_io_direct(inode); + if (rc < 0) + goto out; + down_read(&cinode->lock_sem); + if (!cifs_find_lock_conflict( + cfile, iocb->ki_pos, iov_iter_count(to), + tcon->ses->server->vals->shared_lock_type, + 0, NULL, CIFS_READ_OP)) + rc = netfs_unbuffered_read_iter_locked(iocb, to); + up_read(&cinode->lock_sem); + netfs_end_io_direct(inode); + } else { + rc = netfs_start_io_read(inode); + if (rc < 0) + goto out; + down_read(&cinode->lock_sem); + if (!cifs_find_lock_conflict( + cfile, iocb->ki_pos, iov_iter_count(to), + tcon->ses->server->vals->shared_lock_type, + 0, NULL, CIFS_READ_OP)) + rc = filemap_read(iocb, to, 0); + up_read(&cinode->lock_sem); + netfs_end_io_read(inode); } - free_xid(xid); - return total_read; +out: + return rc; } -/* - * If the page is mmap'ed into a process' page tables, then we need to make - * sure that it doesn't change while being written back. - */ static vm_fault_t cifs_page_mkwrite(struct vm_fault *vmf) { - struct folio *folio = page_folio(vmf->page); - - /* Wait for the folio to be written to the cache before we allow it to - * be modified. We then assume the entire folio will need writing back. - */ -#ifdef CONFIG_CIFS_FSCACHE - if (folio_test_fscache(folio) && - folio_wait_fscache_killable(folio) < 0) - return VM_FAULT_RETRY; -#endif - - folio_wait_writeback(folio); - - if (folio_lock_killable(folio) < 0) - return VM_FAULT_RETRY; - return VM_FAULT_LOCKED; + return netfs_page_mkwrite(vmf, NULL); } static const struct vm_operations_struct cifs_file_vm_ops = { @@ -4433,290 +2993,6 @@ int cifs_file_mmap(struct file *file, struct vm_area_struct *vma) return rc; } -/* - * Unlock a bunch of folios in the pagecache. - */ -static void cifs_unlock_folios(struct address_space *mapping, pgoff_t first, pgoff_t last) -{ - struct folio *folio; - XA_STATE(xas, &mapping->i_pages, first); - - rcu_read_lock(); - xas_for_each(&xas, folio, last) { - folio_unlock(folio); - } - rcu_read_unlock(); -} - -static void cifs_readahead_complete(struct work_struct *work) -{ - struct cifs_readdata *rdata = container_of(work, - struct cifs_readdata, work); - struct folio *folio; - pgoff_t last; - bool good = rdata->result == 0 || (rdata->result == -EAGAIN && rdata->got_bytes); - - XA_STATE(xas, &rdata->mapping->i_pages, rdata->offset / PAGE_SIZE); - - if (good) - cifs_readahead_to_fscache(rdata->mapping->host, - rdata->offset, rdata->bytes); - - if (iov_iter_count(&rdata->iter) > 0) - iov_iter_zero(iov_iter_count(&rdata->iter), &rdata->iter); - - last = (rdata->offset + rdata->bytes - 1) / PAGE_SIZE; - - rcu_read_lock(); - xas_for_each(&xas, folio, last) { - if (good) { - flush_dcache_folio(folio); - folio_mark_uptodate(folio); - } - folio_unlock(folio); - } - rcu_read_unlock(); - - kref_put(&rdata->refcount, cifs_readdata_release); -} - -static void cifs_readahead(struct readahead_control *ractl) -{ - struct cifsFileInfo *open_file = ractl->file->private_data; - struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(ractl->file); - struct TCP_Server_Info *server; - unsigned int xid, nr_pages, cache_nr_pages = 0; - unsigned int ra_pages; - pgoff_t next_cached = ULONG_MAX, ra_index; - bool caching = fscache_cookie_enabled(cifs_inode_cookie(ractl->mapping->host)) && - cifs_inode_cookie(ractl->mapping->host)->cache_priv; - bool check_cache = caching; - pid_t pid; - int rc = 0; - - /* Note that readahead_count() lags behind our dequeuing of pages from - * the ractl, wo we have to keep track for ourselves. - */ - ra_pages = readahead_count(ractl); - ra_index = readahead_index(ractl); - - xid = get_xid(); - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) - pid = open_file->pid; - else - pid = current->tgid; - - server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses); - - cifs_dbg(FYI, "%s: file=%p mapping=%p num_pages=%u\n", - __func__, ractl->file, ractl->mapping, ra_pages); - - /* - * Chop the readahead request up into rsize-sized read requests. - */ - while ((nr_pages = ra_pages)) { - unsigned int i, rsize; - struct cifs_readdata *rdata; - struct cifs_credits credits_on_stack; - struct cifs_credits *credits = &credits_on_stack; - struct folio *folio; - pgoff_t fsize; - - /* - * Find out if we have anything cached in the range of - * interest, and if so, where the next chunk of cached data is. - */ - if (caching) { - if (check_cache) { - rc = cifs_fscache_query_occupancy( - ractl->mapping->host, ra_index, nr_pages, - &next_cached, &cache_nr_pages); - if (rc < 0) - caching = false; - check_cache = false; - } - - if (ra_index == next_cached) { - /* - * TODO: Send a whole batch of pages to be read - * by the cache. - */ - folio = readahead_folio(ractl); - fsize = folio_nr_pages(folio); - ra_pages -= fsize; - ra_index += fsize; - if (cifs_readpage_from_fscache(ractl->mapping->host, - &folio->page) < 0) { - /* - * TODO: Deal with cache read failure - * here, but for the moment, delegate - * that to readpage. - */ - caching = false; - } - folio_unlock(folio); - next_cached += fsize; - cache_nr_pages -= fsize; - if (cache_nr_pages == 0) - check_cache = true; - continue; - } - } - - if (open_file->invalidHandle) { - rc = cifs_reopen_file(open_file, true); - if (rc) { - if (rc == -EAGAIN) - continue; - break; - } - } - - if (cifs_sb->ctx->rsize == 0) - cifs_sb->ctx->rsize = - server->ops->negotiate_rsize(tlink_tcon(open_file->tlink), - cifs_sb->ctx); - - rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, - &rsize, credits); - if (rc) - break; - nr_pages = min_t(size_t, rsize / PAGE_SIZE, ra_pages); - if (next_cached != ULONG_MAX) - nr_pages = min_t(size_t, nr_pages, next_cached - ra_index); - - /* - * Give up immediately if rsize is too small to read an entire - * page. The VFS will fall back to readpage. We should never - * reach this point however since we set ra_pages to 0 when the - * rsize is smaller than a cache page. - */ - if (unlikely(!nr_pages)) { - add_credits_and_wake_if(server, credits, 0); - break; - } - - rdata = cifs_readdata_alloc(cifs_readahead_complete); - if (!rdata) { - /* best to give up if we're out of mem */ - add_credits_and_wake_if(server, credits, 0); - break; - } - - rdata->offset = ra_index * PAGE_SIZE; - rdata->bytes = nr_pages * PAGE_SIZE; - rdata->cfile = cifsFileInfo_get(open_file); - rdata->server = server; - rdata->mapping = ractl->mapping; - rdata->pid = pid; - rdata->credits = credits_on_stack; - - for (i = 0; i < nr_pages; i++) { - if (!readahead_folio(ractl)) - WARN_ON(1); - } - ra_pages -= nr_pages; - ra_index += nr_pages; - - iov_iter_xarray(&rdata->iter, ITER_DEST, &rdata->mapping->i_pages, - rdata->offset, rdata->bytes); - - rc = adjust_credits(server, &rdata->credits, rdata->bytes); - if (!rc) { - if (rdata->cfile->invalidHandle) - rc = -EAGAIN; - else - rc = server->ops->async_readv(rdata); - } - - if (rc) { - add_credits_and_wake_if(server, &rdata->credits, 0); - cifs_unlock_folios(rdata->mapping, - rdata->offset / PAGE_SIZE, - (rdata->offset + rdata->bytes - 1) / PAGE_SIZE); - /* Fallback to the readpage in error/reconnect cases */ - kref_put(&rdata->refcount, cifs_readdata_release); - break; - } - - kref_put(&rdata->refcount, cifs_readdata_release); - } - - free_xid(xid); -} - -/* - * cifs_readpage_worker must be called with the page pinned - */ -static int cifs_readpage_worker(struct file *file, struct page *page, - loff_t *poffset) -{ - struct inode *inode = file_inode(file); - struct timespec64 atime, mtime; - char *read_data; - int rc; - - /* Is the page cached? */ - rc = cifs_readpage_from_fscache(inode, page); - if (rc == 0) - goto read_complete; - - read_data = kmap(page); - /* for reads over a certain size could initiate async read ahead */ - - rc = cifs_read(file, read_data, PAGE_SIZE, poffset); - - if (rc < 0) - goto io_error; - else - cifs_dbg(FYI, "Bytes read %d\n", rc); - - /* we do not want atime to be less than mtime, it broke some apps */ - atime = inode_set_atime_to_ts(inode, current_time(inode)); - mtime = inode_get_mtime(inode); - if (timespec64_compare(&atime, &mtime) < 0) - inode_set_atime_to_ts(inode, inode_get_mtime(inode)); - - if (PAGE_SIZE > rc) - memset(read_data + rc, 0, PAGE_SIZE - rc); - - flush_dcache_page(page); - SetPageUptodate(page); - rc = 0; - -io_error: - kunmap(page); - -read_complete: - unlock_page(page); - return rc; -} - -static int cifs_read_folio(struct file *file, struct folio *folio) -{ - struct page *page = &folio->page; - loff_t offset = page_file_offset(page); - int rc = -EACCES; - unsigned int xid; - - xid = get_xid(); - - if (file->private_data == NULL) { - rc = -EBADF; - free_xid(xid); - return rc; - } - - cifs_dbg(FYI, "read_folio %p at offset %d 0x%x\n", - page, (int)offset, (int)offset); - - rc = cifs_readpage_worker(file, page, &offset); - - free_xid(xid); - return rc; -} - static int is_inode_writable(struct cifsInodeInfo *cifs_inode) { struct cifsFileInfo *open_file; @@ -4738,12 +3014,14 @@ static int is_inode_writable(struct cifsInodeInfo *cifs_inode) refreshing the inode only on increases in the file size but this is tricky to do without racing with writebehind page caching in the current Linux kernel design */ -bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file) +bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file, + bool from_readdir) { if (!cifsInode) return true; - if (is_inode_writable(cifsInode)) { + if (is_inode_writable(cifsInode) || + ((cifsInode->oplock & CIFS_CACHE_RW_FLG) != 0 && from_readdir)) { /* This inode is open for write at least once */ struct cifs_sb_info *cifs_sb; @@ -4762,123 +3040,6 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file) return true; } -static int cifs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, - struct page **pagep, void **fsdata) -{ - int oncethru = 0; - pgoff_t index = pos >> PAGE_SHIFT; - loff_t offset = pos & (PAGE_SIZE - 1); - loff_t page_start = pos & PAGE_MASK; - loff_t i_size; - struct page *page; - int rc = 0; - - cifs_dbg(FYI, "write_begin from %lld len %d\n", (long long)pos, len); - -start: - page = grab_cache_page_write_begin(mapping, index); - if (!page) { - rc = -ENOMEM; - goto out; - } - - if (PageUptodate(page)) - goto out; - - /* - * If we write a full page it will be up to date, no need to read from - * the server. If the write is short, we'll end up doing a sync write - * instead. - */ - if (len == PAGE_SIZE) - goto out; - - /* - * optimize away the read when we have an oplock, and we're not - * expecting to use any of the data we'd be reading in. That - * is, when the page lies beyond the EOF, or straddles the EOF - * and the write will cover all of the existing data. - */ - if (CIFS_CACHE_READ(CIFS_I(mapping->host))) { - i_size = i_size_read(mapping->host); - if (page_start >= i_size || - (offset == 0 && (pos + len) >= i_size)) { - zero_user_segments(page, 0, offset, - offset + len, - PAGE_SIZE); - /* - * PageChecked means that the parts of the page - * to which we're not writing are considered up - * to date. Once the data is copied to the - * page, it can be set uptodate. - */ - SetPageChecked(page); - goto out; - } - } - - if ((file->f_flags & O_ACCMODE) != O_WRONLY && !oncethru) { - /* - * might as well read a page, it is fast enough. If we get - * an error, we don't need to return it. cifs_write_end will - * do a sync write instead since PG_uptodate isn't set. - */ - cifs_readpage_worker(file, page, &page_start); - put_page(page); - oncethru = 1; - goto start; - } else { - /* we could try using another file handle if there is one - - but how would we lock it to prevent close of that handle - racing with this read? In any case - this will be written out by write_end so is fine */ - } -out: - *pagep = page; - return rc; -} - -static bool cifs_release_folio(struct folio *folio, gfp_t gfp) -{ - if (folio_test_private(folio)) - return 0; - if (folio_test_fscache(folio)) { - if (current_is_kswapd() || !(gfp & __GFP_FS)) - return false; - folio_wait_fscache(folio); - } - fscache_note_page_release(cifs_inode_cookie(folio->mapping->host)); - return true; -} - -static void cifs_invalidate_folio(struct folio *folio, size_t offset, - size_t length) -{ - folio_wait_fscache(folio); -} - -static int cifs_launder_folio(struct folio *folio) -{ - int rc = 0; - loff_t range_start = folio_pos(folio); - loff_t range_end = range_start + folio_size(folio); - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = 0, - .range_start = range_start, - .range_end = range_end, - }; - - cifs_dbg(FYI, "Launder page: %lu\n", folio->index); - - if (folio_clear_dirty_for_io(folio)) - rc = cifs_writepage_locked(&folio->page, &wbc); - - folio_wait_fscache(folio); - return rc; -} - void cifs_oplock_break(struct work_struct *work) { struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, @@ -4968,25 +3129,6 @@ out: cifs_done_oplock_break(cinode); } -/* - * The presence of cifs_direct_io() in the address space ops vector - * allowes open() O_DIRECT flags which would have failed otherwise. - * - * In the non-cached mode (mount with cache=none), we shunt off direct read and write requests - * so this method should never be called. - * - * Direct IO is not yet supported in the cached mode. - */ -static ssize_t -cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter) -{ - /* - * FIXME - * Eventually need to support direct IO for non forcedirectio mounts - */ - return -EINVAL; -} - static int cifs_swap_activate(struct swap_info_struct *sis, struct file *swap_file, sector_t *span) { @@ -5047,24 +3189,44 @@ static void cifs_swap_deactivate(struct file *file) /* do we need to unpin (or unlock) the file */ } +/** + * cifs_swap_rw - SMB3 address space operation for swap I/O + * @iocb: target I/O control block + * @iter: I/O buffer + * + * Perform IO to the swap-file. This is much like direct IO. + */ +static int cifs_swap_rw(struct kiocb *iocb, struct iov_iter *iter) +{ + ssize_t ret; + + WARN_ON_ONCE(iov_iter_count(iter) != PAGE_SIZE); + + if (iov_iter_rw(iter) == READ) + ret = netfs_unbuffered_read_iter_locked(iocb, iter); + else + ret = netfs_unbuffered_write_iter_locked(iocb, iter, NULL); + if (ret < 0) + return ret; + return 0; +} + const struct address_space_operations cifs_addr_ops = { - .read_folio = cifs_read_folio, - .readahead = cifs_readahead, - .writepages = cifs_writepages, - .write_begin = cifs_write_begin, - .write_end = cifs_write_end, - .dirty_folio = netfs_dirty_folio, - .release_folio = cifs_release_folio, - .direct_IO = cifs_direct_io, - .invalidate_folio = cifs_invalidate_folio, - .launder_folio = cifs_launder_folio, - .migrate_folio = filemap_migrate_folio, + .read_folio = netfs_read_folio, + .readahead = netfs_readahead, + .writepages = netfs_writepages, + .dirty_folio = netfs_dirty_folio, + .release_folio = netfs_release_folio, + .direct_IO = noop_direct_IO, + .invalidate_folio = netfs_invalidate_folio, + .migrate_folio = filemap_migrate_folio, /* * TODO: investigate and if useful we could add an is_dirty_writeback * helper if needed */ - .swap_activate = cifs_swap_activate, + .swap_activate = cifs_swap_activate, .swap_deactivate = cifs_swap_deactivate, + .swap_rw = cifs_swap_rw, }; /* @@ -5073,13 +3235,10 @@ const struct address_space_operations cifs_addr_ops = { * to leave cifs_readahead out of the address space operations. */ const struct address_space_operations cifs_addr_ops_smallbuf = { - .read_folio = cifs_read_folio, - .writepages = cifs_writepages, - .write_begin = cifs_write_begin, - .write_end = cifs_write_end, - .dirty_folio = netfs_dirty_folio, - .release_folio = cifs_release_folio, - .invalidate_folio = cifs_invalidate_folio, - .launder_folio = cifs_launder_folio, - .migrate_folio = filemap_migrate_folio, + .read_folio = netfs_read_folio, + .writepages = netfs_writepages, + .dirty_folio = netfs_dirty_folio, + .release_folio = netfs_release_folio, + .invalidate_folio = netfs_invalidate_folio, + .migrate_folio = filemap_migrate_folio, }; diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 4b2f5aa2ea0e..3bbac925d076 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -37,7 +37,7 @@ #include "rfc1002pdu.h" #include "fs_context.h" -static DEFINE_MUTEX(cifs_mount_mutex); +DEFINE_MUTEX(cifs_mount_mutex); static const match_table_t cifs_smb_version_tokens = { { Smb_1, SMB1_VERSION_STRING }, @@ -162,6 +162,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_string("username", Opt_user), fsparam_string("pass", Opt_pass), fsparam_string("password", Opt_pass), + fsparam_string("password2", Opt_pass2), fsparam_string("ip", Opt_ip), fsparam_string("addr", Opt_ip), fsparam_string("domain", Opt_domain), @@ -174,6 +175,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_string("vers", Opt_vers), fsparam_string("sec", Opt_sec), fsparam_string("cache", Opt_cache), + fsparam_string("reparse", Opt_reparse), /* Arguments that should be ignored */ fsparam_flag("guest", Opt_ignore), @@ -296,6 +298,35 @@ cifs_parse_cache_flavor(struct fs_context *fc, char *value, struct smb3_fs_conte return 0; } +static const match_table_t reparse_flavor_tokens = { + { Opt_reparse_default, "default" }, + { Opt_reparse_nfs, "nfs" }, + { Opt_reparse_wsl, "wsl" }, + { Opt_reparse_err, NULL }, +}; + +static int parse_reparse_flavor(struct fs_context *fc, char *value, + struct smb3_fs_context *ctx) +{ + substring_t args[MAX_OPT_ARGS]; + + switch (match_token(value, reparse_flavor_tokens, args)) { + case Opt_reparse_default: + ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT; + break; + case Opt_reparse_nfs: + ctx->reparse_type = CIFS_REPARSE_TYPE_NFS; + break; + case Opt_reparse_wsl: + ctx->reparse_type = CIFS_REPARSE_TYPE_WSL; + break; + default: + cifs_errorf(fc, "bad reparse= option: %s\n", value); + return 1; + } + return 0; +} + #define DUP_CTX_STR(field) \ do { \ if (ctx->field) { \ @@ -315,6 +346,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx new_ctx->nodename = NULL; new_ctx->username = NULL; new_ctx->password = NULL; + new_ctx->password2 = NULL; new_ctx->server_hostname = NULL; new_ctx->domainname = NULL; new_ctx->UNC = NULL; @@ -327,6 +359,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx DUP_CTX_STR(prepath); DUP_CTX_STR(username); DUP_CTX_STR(password); + DUP_CTX_STR(password2); DUP_CTX_STR(server_hostname); DUP_CTX_STR(UNC); DUP_CTX_STR(source); @@ -715,6 +748,16 @@ static int smb3_fs_context_validate(struct fs_context *fc) /* set the port that we got earlier */ cifs_set_port((struct sockaddr *)&ctx->dstaddr, ctx->port); + if (ctx->uid_specified && !ctx->forceuid_specified) { + ctx->override_uid = 1; + pr_notice("enabling forceuid mount option implicitly because uid= option is specified\n"); + } + + if (ctx->gid_specified && !ctx->forcegid_specified) { + ctx->override_gid = 1; + pr_notice("enabling forcegid mount option implicitly because gid= option is specified\n"); + } + if (ctx->override_uid && !ctx->uid_specified) { ctx->override_uid = 0; pr_notice("ignoring forceuid mount option specified with no uid= option\n"); @@ -753,9 +796,9 @@ static int smb3_get_tree(struct fs_context *fc) if (err) return err; - mutex_lock(&cifs_mount_mutex); + cifs_mount_lock(); ret = smb3_get_tree_common(fc); - mutex_unlock(&cifs_mount_mutex); + cifs_mount_unlock(); return ret; } @@ -772,7 +815,7 @@ static void smb3_fs_context_free(struct fs_context *fc) */ static int smb3_verify_reconfigure_ctx(struct fs_context *fc, struct smb3_fs_context *new_ctx, - struct smb3_fs_context *old_ctx) + struct smb3_fs_context *old_ctx, bool need_recon) { if (new_ctx->posix_paths != old_ctx->posix_paths) { cifs_errorf(fc, "can not change posixpaths during remount\n"); @@ -798,8 +841,15 @@ static int smb3_verify_reconfigure_ctx(struct fs_context *fc, } if (new_ctx->password && (!old_ctx->password || strcmp(new_ctx->password, old_ctx->password))) { - cifs_errorf(fc, "can not change password during remount\n"); - return -EINVAL; + if (need_recon == false) { + cifs_errorf(fc, + "can not change password of active session during remount\n"); + return -EINVAL; + } else if (old_ctx->sectype == Kerberos) { + cifs_errorf(fc, + "can not change password for Kerberos via remount\n"); + return -EINVAL; + } } if (new_ctx->domainname && (!old_ctx->domainname || strcmp(new_ctx->domainname, old_ctx->domainname))) { @@ -843,9 +893,14 @@ static int smb3_reconfigure(struct fs_context *fc) struct smb3_fs_context *ctx = smb3_fc2context(fc); struct dentry *root = fc->root; struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb); + struct cifs_ses *ses = cifs_sb_master_tcon(cifs_sb)->ses; + bool need_recon = false; int rc; - rc = smb3_verify_reconfigure_ctx(fc, ctx, cifs_sb->ctx); + if (ses->expired_pwd) + need_recon = true; + + rc = smb3_verify_reconfigure_ctx(fc, ctx, cifs_sb->ctx, need_recon); if (rc) return rc; @@ -858,7 +913,14 @@ static int smb3_reconfigure(struct fs_context *fc) STEAL_STRING(cifs_sb, ctx, UNC); STEAL_STRING(cifs_sb, ctx, source); STEAL_STRING(cifs_sb, ctx, username); - STEAL_STRING_SENSITIVE(cifs_sb, ctx, password); + if (need_recon == false) + STEAL_STRING_SENSITIVE(cifs_sb, ctx, password); + else { + kfree_sensitive(ses->password); + ses->password = kstrdup(ctx->password, GFP_KERNEL); + kfree_sensitive(ses->password2); + ses->password2 = kstrdup(ctx->password2, GFP_KERNEL); + } STEAL_STRING(cifs_sb, ctx, domainname); STEAL_STRING(cifs_sb, ctx, nodename); STEAL_STRING(cifs_sb, ctx, iocharset); @@ -916,7 +978,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, switch (opt) { case Opt_compress: - ctx->compression = UNKNOWN_TYPE; + ctx->compress = true; cifs_dbg(VFS, "SMB3 compression support is experimental\n"); break; @@ -967,12 +1029,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->override_uid = 0; else ctx->override_uid = 1; + ctx->forceuid_specified = true; break; case Opt_forcegid: if (result.negated) ctx->override_gid = 0; else ctx->override_gid = 1; + ctx->forcegid_specified = true; break; case Opt_perm: if (result.negated) @@ -1258,6 +1322,18 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, goto cifs_parse_mount_err; } break; + case Opt_pass2: + kfree_sensitive(ctx->password2); + ctx->password2 = NULL; + if (strlen(param->string) == 0) + break; + + ctx->password2 = kstrdup(param->string, GFP_KERNEL); + if (ctx->password2 == NULL) { + cifs_errorf(fc, "OOM when copying password2 string\n"); + goto cifs_parse_mount_err; + } + break; case Opt_ip: if (strlen(param->string) == 0) { ctx->got_ip = false; @@ -1549,6 +1625,10 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, case Opt_rdma: ctx->rdma = true; break; + case Opt_reparse: + if (parse_reparse_flavor(fc, param->string, ctx)) + goto cifs_parse_mount_err; + break; } /* case Opt_ignore: - is ignored as expected ... */ @@ -1557,6 +1637,8 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, cifs_parse_mount_err: kfree_sensitive(ctx->password); ctx->password = NULL; + kfree_sensitive(ctx->password2); + ctx->password2 = NULL; return -EINVAL; } @@ -1635,6 +1717,7 @@ int smb3_init_fs_context(struct fs_context *fc) ctx->backupgid_specified = false; /* no backup intent for a group */ ctx->retrans = 1; + ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT; /* * short int override_uid = -1; @@ -1661,6 +1744,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx) ctx->username = NULL; kfree_sensitive(ctx->password); ctx->password = NULL; + kfree_sensitive(ctx->password2); + ctx->password2 = NULL; kfree(ctx->server_hostname); ctx->server_hostname = NULL; kfree(ctx->UNC); diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index 182ce11cbe93..cf577ec0dd0a 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -41,6 +41,13 @@ enum { Opt_cache_err }; +enum cifs_reparse_parm { + Opt_reparse_default, + Opt_reparse_nfs, + Opt_reparse_wsl, + Opt_reparse_err +}; + enum cifs_sec_param { Opt_sec_krb5, Opt_sec_krb5i, @@ -138,6 +145,7 @@ enum cifs_param { Opt_source, Opt_user, Opt_pass, + Opt_pass2, Opt_ip, Opt_domain, Opt_srcaddr, @@ -148,6 +156,7 @@ enum cifs_param { Opt_vers, Opt_sec, Opt_cache, + Opt_reparse, /* Mount options to be ignored */ Opt_ignore, @@ -156,6 +165,8 @@ enum cifs_param { }; struct smb3_fs_context { + bool forceuid_specified; + bool forcegid_specified; bool uid_specified; bool cruid_specified; bool gid_specified; @@ -169,6 +180,7 @@ struct smb3_fs_context { char *username; char *password; + char *password2; char *domainname; char *source; char *server_hostname; @@ -265,12 +277,13 @@ struct smb3_fs_context { unsigned int max_credits; /* smb3 max_credits 10 < credits < 60000 */ unsigned int max_channels; unsigned int max_cached_dirs; - __u16 compression; /* compression algorithm 0xFFFF default 0=disabled */ + bool compress; /* enable SMB2 messages (READ/WRITE) de/compression */ bool rootfs:1; /* if it's a SMB root file system */ bool witness:1; /* use witness protocol */ char *leaf_fullpath; struct cifs_ses *dfs_root_ses; bool dfs_automount:1; /* set for dfs automount only */ + enum cifs_reparse_type reparse_type; }; extern const struct fs_parameter_spec smb3_fs_parameters[]; @@ -295,4 +308,16 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb); #define MAX_CACHED_FIDS 16 extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp); +extern struct mutex cifs_mount_mutex; + +static inline void cifs_mount_lock(void) +{ + mutex_lock(&cifs_mount_mutex); +} + +static inline void cifs_mount_unlock(void) +{ + mutex_unlock(&cifs_mount_mutex); +} + #endif diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c index c4a3cb736881..01424a5cdb99 100644 --- a/fs/smb/client/fscache.c +++ b/fs/smb/client/fscache.c @@ -12,6 +12,16 @@ #include "cifs_fs_sb.h" #include "cifsproto.h" +/* + * Key for fscache inode. [!] Contents must match comparisons in cifs_find_inode(). + */ +struct cifs_fscache_inode_key { + + __le64 uniqueid; /* server inode number */ + __le64 createtime; /* creation time on server */ + u8 type; /* S_IFMT file type */ +} __packed; + static void cifs_fscache_fill_volume_coherency( struct cifs_tcon *tcon, struct cifs_fscache_volume_coherency_data *cd) @@ -33,12 +43,23 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) char *key; int ret = -ENOMEM; + if (tcon->fscache_acquired) + return 0; + + mutex_lock(&tcon->fscache_lock); + if (tcon->fscache_acquired) { + mutex_unlock(&tcon->fscache_lock); + return 0; + } + tcon->fscache_acquired = true; + tcon->fscache = NULL; switch (sa->sa_family) { case AF_INET: case AF_INET6: break; default: + mutex_unlock(&tcon->fscache_lock); cifs_dbg(VFS, "Unknown network family '%d'\n", sa->sa_family); return -EINVAL; } @@ -47,6 +68,7 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) sharename = extract_sharename(tcon->tree_name); if (IS_ERR(sharename)) { + mutex_unlock(&tcon->fscache_lock); cifs_dbg(FYI, "%s: couldn't extract sharename\n", __func__); return PTR_ERR(sharename); } @@ -72,6 +94,11 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) } pr_err("Cache volume key already in use (%s)\n", key); vcookie = NULL; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_see_fscache_collision); + } else { + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_see_fscache_okay); } tcon->fscache = vcookie; @@ -80,6 +107,7 @@ out_2: kfree(key); out: kfree(sharename); + mutex_unlock(&tcon->fscache_lock); return ret; } @@ -92,20 +120,26 @@ void cifs_fscache_release_super_cookie(struct cifs_tcon *tcon) cifs_fscache_fill_volume_coherency(tcon, &cd); fscache_relinquish_volume(tcon->fscache, &cd, false); tcon->fscache = NULL; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_see_fscache_relinq); } void cifs_fscache_get_inode_cookie(struct inode *inode) { struct cifs_fscache_inode_coherency_data cd; + struct cifs_fscache_inode_key key; struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + key.uniqueid = cpu_to_le64(cifsi->uniqueid); + key.createtime = cpu_to_le64(cifsi->createtime); + key.type = (inode->i_mode & S_IFMT) >> 12; cifs_fscache_fill_coherency(&cifsi->netfs.inode, &cd); cifsi->netfs.cache = fscache_acquire_cookie(tcon->fscache, 0, - &cifsi->uniqueid, sizeof(cifsi->uniqueid), + &key, sizeof(key), &cd, sizeof(cd), i_size_read(&cifsi->netfs.inode)); if (cifsi->netfs.cache) @@ -136,112 +170,3 @@ void cifs_fscache_release_inode_cookie(struct inode *inode) cifsi->netfs.cache = NULL; } } - -/* - * Fallback page reading interface. - */ -static int fscache_fallback_read_page(struct inode *inode, struct page *page) -{ - struct netfs_cache_resources cres; - struct fscache_cookie *cookie = cifs_inode_cookie(inode); - struct iov_iter iter; - struct bio_vec bvec; - int ret; - - memset(&cres, 0, sizeof(cres)); - bvec_set_page(&bvec, page, PAGE_SIZE, 0); - iov_iter_bvec(&iter, ITER_DEST, &bvec, 1, PAGE_SIZE); - - ret = fscache_begin_read_operation(&cres, cookie); - if (ret < 0) - return ret; - - ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL, - NULL, NULL); - fscache_end_operation(&cres); - return ret; -} - -/* - * Fallback page writing interface. - */ -static int fscache_fallback_write_pages(struct inode *inode, loff_t start, size_t len, - bool no_space_allocated_yet) -{ - struct netfs_cache_resources cres; - struct fscache_cookie *cookie = cifs_inode_cookie(inode); - struct iov_iter iter; - int ret; - - memset(&cres, 0, sizeof(cres)); - iov_iter_xarray(&iter, ITER_SOURCE, &inode->i_mapping->i_pages, start, len); - - ret = fscache_begin_write_operation(&cres, cookie); - if (ret < 0) - return ret; - - ret = cres.ops->prepare_write(&cres, &start, &len, len, i_size_read(inode), - no_space_allocated_yet); - if (ret == 0) - ret = fscache_write(&cres, start, &iter, NULL, NULL); - fscache_end_operation(&cres); - return ret; -} - -/* - * Retrieve a page from FS-Cache - */ -int __cifs_readpage_from_fscache(struct inode *inode, struct page *page) -{ - int ret; - - cifs_dbg(FYI, "%s: (fsc:%p, p:%p, i:0x%p\n", - __func__, cifs_inode_cookie(inode), page, inode); - - ret = fscache_fallback_read_page(inode, page); - if (ret < 0) - return ret; - - /* Read completed synchronously */ - SetPageUptodate(page); - return 0; -} - -void __cifs_readahead_to_fscache(struct inode *inode, loff_t pos, size_t len) -{ - cifs_dbg(FYI, "%s: (fsc: %p, p: %llx, l: %zx, i: %p)\n", - __func__, cifs_inode_cookie(inode), pos, len, inode); - - fscache_fallback_write_pages(inode, pos, len, true); -} - -/* - * Query the cache occupancy. - */ -int __cifs_fscache_query_occupancy(struct inode *inode, - pgoff_t first, unsigned int nr_pages, - pgoff_t *_data_first, - unsigned int *_data_nr_pages) -{ - struct netfs_cache_resources cres; - struct fscache_cookie *cookie = cifs_inode_cookie(inode); - loff_t start, data_start; - size_t len, data_len; - int ret; - - ret = fscache_begin_read_operation(&cres, cookie); - if (ret < 0) - return ret; - - start = first * PAGE_SIZE; - len = nr_pages * PAGE_SIZE; - ret = cres.ops->query_occupancy(&cres, start, len, PAGE_SIZE, - &data_start, &data_len); - if (ret == 0) { - *_data_first = data_start / PAGE_SIZE; - *_data_nr_pages = len / PAGE_SIZE; - } - - fscache_end_operation(&cres); - return ret; -} diff --git a/fs/smb/client/fscache.h b/fs/smb/client/fscache.h index a3d73720914f..f06cb24f5f3c 100644 --- a/fs/smb/client/fscache.h +++ b/fs/smb/client/fscache.h @@ -74,39 +74,9 @@ static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags i_size_read(inode), flags); } -extern int __cifs_fscache_query_occupancy(struct inode *inode, - pgoff_t first, unsigned int nr_pages, - pgoff_t *_data_first, - unsigned int *_data_nr_pages); - -static inline int cifs_fscache_query_occupancy(struct inode *inode, - pgoff_t first, unsigned int nr_pages, - pgoff_t *_data_first, - unsigned int *_data_nr_pages) +static inline bool cifs_fscache_enabled(struct inode *inode) { - if (!cifs_inode_cookie(inode)) - return -ENOBUFS; - return __cifs_fscache_query_occupancy(inode, first, nr_pages, - _data_first, _data_nr_pages); -} - -extern int __cifs_readpage_from_fscache(struct inode *pinode, struct page *ppage); -extern void __cifs_readahead_to_fscache(struct inode *pinode, loff_t pos, size_t len); - - -static inline int cifs_readpage_from_fscache(struct inode *inode, - struct page *page) -{ - if (cifs_inode_cookie(inode)) - return __cifs_readpage_from_fscache(inode, page); - return -ENOBUFS; -} - -static inline void cifs_readahead_to_fscache(struct inode *inode, - loff_t pos, size_t len) -{ - if (cifs_inode_cookie(inode)) - __cifs_readahead_to_fscache(inode, pos, len); + return fscache_cookie_enabled(cifs_inode_cookie(inode)); } #else /* CONFIG_CIFS_FSCACHE */ @@ -124,25 +94,7 @@ static inline void cifs_fscache_release_inode_cookie(struct inode *inode) {} static inline void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) {} static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return NULL; } static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {} - -static inline int cifs_fscache_query_occupancy(struct inode *inode, - pgoff_t first, unsigned int nr_pages, - pgoff_t *_data_first, - unsigned int *_data_nr_pages) -{ - *_data_first = ULONG_MAX; - *_data_nr_pages = 0; - return -ENOBUFS; -} - -static inline int -cifs_readpage_from_fscache(struct inode *inode, struct page *page) -{ - return -ENOBUFS; -} - -static inline -void cifs_readahead_to_fscache(struct inode *inode, loff_t pos, size_t len) {} +static inline bool cifs_fscache_enabled(struct inode *inode) { return false; } #endif /* CONFIG_CIFS_FSCACHE */ diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index d02f8ba29cb5..262576573eb5 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -26,15 +26,28 @@ #include "fs_context.h" #include "cifs_ioctl.h" #include "cached_dir.h" +#include "reparse.h" + +/* + * Set parameters for the netfs library + */ +static void cifs_set_netfs_context(struct inode *inode) +{ + struct cifsInodeInfo *cifs_i = CIFS_I(inode); + + netfs_inode_init(&cifs_i->netfs, &cifs_req_ops, true); +} static void cifs_set_ops(struct inode *inode) { struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct netfs_inode *ictx = netfs_inode(inode); switch (inode->i_mode & S_IFMT) { case S_IFREG: inode->i_op = &cifs_file_inode_ops; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) { + set_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) inode->i_fop = &cifs_file_direct_nobrl_ops; else @@ -56,6 +69,7 @@ static void cifs_set_ops(struct inode *inode) inode->i_data.a_ops = &cifs_addr_ops_smallbuf; else inode->i_data.a_ops = &cifs_addr_ops; + mapping_set_large_folios(inode->i_mapping); break; case S_IFDIR: if (IS_AUTOMOUNT(inode)) { @@ -147,7 +161,8 @@ cifs_nlink_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) /* populate an inode with info from a cifs_fattr struct */ int -cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) +cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, + bool from_readdir) { struct cifsInodeInfo *cifs_i = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); @@ -199,7 +214,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) * Can't safely change the file size here if the client is writing to * it due to potential races. */ - if (is_size_safe_to_change(cifs_i, fattr->cf_eof)) { + if (is_size_safe_to_change(cifs_i, fattr->cf_eof, from_readdir)) { i_size_write(inode, fattr->cf_eof); /* @@ -219,8 +234,10 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) if (fattr->cf_flags & CIFS_FATTR_JUNCTION) inode->i_flags |= S_AUTOMOUNT; - if (inode->i_state & I_NEW) + if (inode->i_state & I_NEW) { + cifs_set_netfs_context(inode); cifs_set_ops(inode); + } return 0; } @@ -368,7 +385,7 @@ static int update_inode_info(struct super_block *sb, CIFS_I(*inode)->time = 0; /* force reval */ return -ESTALE; } - return cifs_fattr_to_inode(*inode, fattr); + return cifs_fattr_to_inode(*inode, fattr, false); } #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY @@ -399,11 +416,10 @@ cifs_get_file_info_unix(struct file *filp) cifs_unix_basic_to_fattr(&fattr, &find_data, cifs_sb); } else if (rc == -EREMOTE) { cifs_create_junction_fattr(&fattr, inode->i_sb); - rc = 0; } else goto cifs_gfiunix_out; - rc = cifs_fattr_to_inode(inode, &fattr); + rc = cifs_fattr_to_inode(inode, &fattr, false); cifs_gfiunix_out: free_xid(xid); @@ -727,84 +743,6 @@ out_reparse: fattr->cf_mode, fattr->cf_uniqueid, fattr->cf_nlink); } -static inline dev_t nfs_mkdev(struct reparse_posix_data *buf) -{ - u64 v = le64_to_cpu(*(__le64 *)buf->DataBuffer); - - return MKDEV(v >> 32, v & 0xffffffff); -} - -bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, - struct cifs_fattr *fattr, - struct cifs_open_info_data *data) -{ - struct reparse_posix_data *buf = data->reparse.posix; - u32 tag = data->reparse.tag; - - if (tag == IO_REPARSE_TAG_NFS && buf) { - switch (le64_to_cpu(buf->InodeType)) { - case NFS_SPECFILE_CHR: - fattr->cf_mode |= S_IFCHR; - fattr->cf_dtype = DT_CHR; - fattr->cf_rdev = nfs_mkdev(buf); - break; - case NFS_SPECFILE_BLK: - fattr->cf_mode |= S_IFBLK; - fattr->cf_dtype = DT_BLK; - fattr->cf_rdev = nfs_mkdev(buf); - break; - case NFS_SPECFILE_FIFO: - fattr->cf_mode |= S_IFIFO; - fattr->cf_dtype = DT_FIFO; - break; - case NFS_SPECFILE_SOCK: - fattr->cf_mode |= S_IFSOCK; - fattr->cf_dtype = DT_SOCK; - break; - case NFS_SPECFILE_LNK: - fattr->cf_mode |= S_IFLNK; - fattr->cf_dtype = DT_LNK; - break; - default: - WARN_ON_ONCE(1); - return false; - } - return true; - } - - switch (tag) { - case IO_REPARSE_TAG_LX_SYMLINK: - fattr->cf_mode |= S_IFLNK; - fattr->cf_dtype = DT_LNK; - break; - case IO_REPARSE_TAG_LX_FIFO: - fattr->cf_mode |= S_IFIFO; - fattr->cf_dtype = DT_FIFO; - break; - case IO_REPARSE_TAG_AF_UNIX: - fattr->cf_mode |= S_IFSOCK; - fattr->cf_dtype = DT_SOCK; - break; - case IO_REPARSE_TAG_LX_CHR: - fattr->cf_mode |= S_IFCHR; - fattr->cf_dtype = DT_CHR; - break; - case IO_REPARSE_TAG_LX_BLK: - fattr->cf_mode |= S_IFBLK; - fattr->cf_dtype = DT_BLK; - break; - case 0: /* SMB1 symlink */ - case IO_REPARSE_TAG_SYMLINK: - case IO_REPARSE_TAG_NFS: - fattr->cf_mode |= S_IFLNK; - fattr->cf_dtype = DT_LNK; - break; - default: - return false; - } - return true; -} - static void cifs_open_info_to_fattr(struct cifs_fattr *fattr, struct cifs_open_info_data *data, struct super_block *sb) @@ -835,6 +773,8 @@ static void cifs_open_info_to_fattr(struct cifs_fattr *fattr, fattr->cf_bytes = le64_to_cpu(info->AllocationSize); fattr->cf_createtime = le64_to_cpu(info->CreationTime); fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks); + fattr->cf_uid = cifs_sb->ctx->linux_uid; + fattr->cf_gid = cifs_sb->ctx->linux_gid; fattr->cf_mode = cifs_sb->ctx->file_mode; if (cifs_open_data_reparse(data) && @@ -877,9 +817,6 @@ out_reparse: fattr->cf_symlink_target = data->symlink_target; data->symlink_target = NULL; } - - fattr->cf_uid = cifs_sb->ctx->linux_uid; - fattr->cf_gid = cifs_sb->ctx->linux_gid; } static int @@ -893,9 +830,14 @@ cifs_get_file_info(struct file *filp) struct cifsFileInfo *cfile = filp->private_data; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; + struct dentry *dentry = filp->f_path.dentry; + void *page = alloc_dentry_path(); + const unsigned char *path; - if (!server->ops->query_file_info) + if (!server->ops->query_file_info) { + free_dentry_path(page); return -ENOSYS; + } xid = get_xid(); rc = server->ops->query_file_info(xid, tcon, cfile, &data); @@ -907,11 +849,17 @@ cifs_get_file_info(struct file *filp) data.symlink = true; data.reparse.tag = IO_REPARSE_TAG_SYMLINK; } + path = build_path_from_dentry(dentry, page); + if (IS_ERR(path)) { + rc = PTR_ERR(path); + goto cgfi_exit; + } cifs_open_info_to_fattr(&fattr, &data, inode->i_sb); + if (fattr.cf_flags & CIFS_FATTR_DELETE_PENDING) + cifs_mark_open_handles_for_deleted_file(inode, path); break; case -EREMOTE: cifs_create_junction_fattr(&fattr, inode->i_sb); - rc = 0; break; case -EOPNOTSUPP: case -EINVAL: @@ -934,9 +882,10 @@ cifs_get_file_info(struct file *filp) fattr.cf_uniqueid = CIFS_I(inode)->uniqueid; fattr.cf_flags |= CIFS_FATTR_NEED_REVAL; /* if filetype is different, return error */ - rc = cifs_fattr_to_inode(inode, &fattr); + rc = cifs_fattr_to_inode(inode, &fattr, false); cgfi_exit: cifs_free_open_info(&data); + free_dentry_path(page); free_xid(xid); return rc; } @@ -1171,6 +1120,9 @@ static int cifs_get_fattr(struct cifs_open_info_data *data, } else { cifs_open_info_to_fattr(fattr, data, sb); } + if (!rc && *inode && + (fattr->cf_flags & CIFS_FATTR_DELETE_PENDING)) + cifs_mark_open_handles_for_deleted_file(*inode, full_path); break; case -EREMOTE: /* DFS link, no metadata available on this server */ @@ -1399,6 +1351,8 @@ int smb311_posix_get_inode_info(struct inode **inode, goto out; rc = update_inode_info(sb, &fattr, inode); + if (!rc && fattr.cf_flags & CIFS_FATTR_DELETE_PENDING) + cifs_mark_open_handles_for_deleted_file(*inode, full_path); out: kfree(fattr.cf_symlink_target); return rc; @@ -1413,6 +1367,8 @@ cifs_find_inode(struct inode *inode, void *opaque) { struct cifs_fattr *fattr = opaque; + /* [!] The compared values must be the same in struct cifs_fscache_inode_key. */ + /* don't match inode with different uniqueid */ if (CIFS_I(inode)->uniqueid != fattr->cf_uniqueid) return 0; @@ -1491,7 +1447,7 @@ retry_iget5_locked: } /* can't fail - see cifs_find_inode() */ - cifs_fattr_to_inode(inode, fattr); + cifs_fattr_to_inode(inode, fattr, false); if (sb->s_flags & SB_NOATIME) inode->i_flags |= S_NOATIME | S_NOCMTIME; if (inode->i_state & I_NEW) { @@ -1560,6 +1516,9 @@ iget_root: goto out; } + if (!rc && fattr.cf_flags & CIFS_FATTR_DELETE_PENDING) + cifs_mark_open_handles_for_deleted_file(inode, path); + if (rc && tcon->pipe) { cifs_dbg(FYI, "ipc connection - fake read inode\n"); spin_lock(&inode->i_lock); @@ -1846,20 +1805,24 @@ retry_std_delete: goto psx_del_no_retry; } - rc = server->ops->unlink(xid, tcon, full_path, cifs_sb); + rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry); psx_del_no_retry: if (!rc) { - if (inode) + if (inode) { + cifs_mark_open_handles_for_deleted_file(inode, full_path); cifs_drop_nlink(inode); + } } else if (rc == -ENOENT) { d_drop(dentry); } else if (rc == -EBUSY) { if (server->ops->rename_pending_delete) { rc = server->ops->rename_pending_delete(full_path, dentry, xid); - if (rc == 0) + if (rc == 0) { + cifs_mark_open_handles_for_deleted_file(inode, full_path); cifs_drop_nlink(inode); + } } } else if ((rc == -EACCES) && (dosattr == 0) && inode) { attrs = kzalloc(sizeof(*attrs), GFP_KERNEL); @@ -2483,24 +2446,6 @@ cifs_dentry_needs_reval(struct dentry *dentry) return false; } -/* - * Zap the cache. Called when invalid_mapping flag is set. - */ -int -cifs_invalidate_mapping(struct inode *inode) -{ - int rc = 0; - - if (inode->i_mapping && inode->i_mapping->nrpages != 0) { - rc = invalidate_inode_pages2(inode->i_mapping); - if (rc) - cifs_dbg(VFS, "%s: invalidate inode %p failed with rc %d\n", - __func__, inode, rc); - } - - return rc; -} - /** * cifs_wait_bit_killable - helper for functions that are sleeping on bit locks * @@ -2520,7 +2465,8 @@ int cifs_revalidate_mapping(struct inode *inode) { int rc; - unsigned long *flags = &CIFS_I(inode)->flags; + struct cifsInodeInfo *cifs_inode = CIFS_I(inode); + unsigned long *flags = &cifs_inode->flags; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); /* swapfiles are not supposed to be shared */ @@ -2537,9 +2483,13 @@ cifs_revalidate_mapping(struct inode *inode) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE) goto skip_invalidate; - rc = cifs_invalidate_mapping(inode); - if (rc) + cifs_inode->netfs.zero_point = cifs_inode->netfs.remote_i_size; + rc = filemap_invalidate_inode(inode, true, 0, LLONG_MAX); + if (rc) { + cifs_dbg(VFS, "%s: invalidate inode %p failed with rc %d\n", + __func__, inode, rc); set_bit(CIFS_INO_INVALID_MAPPING, flags); + } } skip_invalidate: @@ -2797,7 +2747,7 @@ void cifs_setsize(struct inode *inode, loff_t offset) static int cifs_set_file_size(struct inode *inode, struct iattr *attrs, - unsigned int xid, const char *full_path) + unsigned int xid, const char *full_path, struct dentry *dentry) { int rc; struct cifsFileInfo *open_file; @@ -2848,7 +2798,7 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, */ if (server->ops->set_path_size) rc = server->ops->set_path_size(xid, tcon, full_path, - attrs->ia_size, cifs_sb, false); + attrs->ia_size, cifs_sb, false, dentry); else rc = -ENOSYS; cifs_dbg(FYI, "SetEOF by path (setattrs) rc = %d\n", rc); @@ -2938,7 +2888,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) rc = 0; if (attrs->ia_valid & ATTR_SIZE) { - rc = cifs_set_file_size(inode, attrs, xid, full_path); + rc = cifs_set_file_size(inode, attrs, xid, full_path, direntry); if (rc != 0) goto out; } @@ -3105,7 +3055,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) } if (attrs->ia_valid & ATTR_SIZE) { - rc = cifs_set_file_size(inode, attrs, xid, full_path); + rc = cifs_set_file_size(inode, attrs, xid, full_path, direntry); if (rc != 0) goto cifs_setattr_exit; } diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index e2f92c21fff5..855ac5a62edf 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -247,7 +247,9 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server_it, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses_it, &server_it->smb_ses_list, smb_ses_list) { - if (ses_it->Suid == out.session_id) { + spin_lock(&ses_it->ses_lock); + if (ses_it->ses_status != SES_EXITING && + ses_it->Suid == out.session_id) { ses = ses_it; /* * since we are using the session outside the crit @@ -255,9 +257,11 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug * so increment its refcount */ cifs_smb_ses_inc_refcount(ses); + spin_unlock(&ses_it->ses_lock); found = true; goto search_end; } + spin_unlock(&ses_it->ses_lock); } } search_end: @@ -345,6 +349,11 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) xid = get_xid(); cifs_dbg(FYI, "cifs ioctl 0x%x\n", command); + if (pSMBFile == NULL) + trace_smb3_ioctl(xid, 0, command); + else + trace_smb3_ioctl(xid, pSMBFile->fid.persistent_fid, command); + switch (command) { case FS_IOC_GETFLAGS: if (pSMBFile == NULL) diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 0748d7b757b9..07c468ddb88a 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -27,9 +27,6 @@ #include "fs_context.h" #include "cached_dir.h" -extern mempool_t *cifs_sm_req_poolp; -extern mempool_t *cifs_req_poolp; - /* The xid serves as a useful identifier for each incoming vfs request, in a similar way to the mid which is useful to track each sent smb, and CurrentXid can also provide a running counter (although it @@ -101,6 +98,7 @@ sesInfoFree(struct cifs_ses *buf_to_free) kfree(buf_to_free->serverDomain); kfree(buf_to_free->serverNOS); kfree_sensitive(buf_to_free->password); + kfree_sensitive(buf_to_free->password2); kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); kfree_sensitive(buf_to_free->auth_key.response); @@ -113,9 +111,10 @@ sesInfoFree(struct cifs_ses *buf_to_free) } struct cifs_tcon * -tcon_info_alloc(bool dir_leases_enabled) +tcon_info_alloc(bool dir_leases_enabled, enum smb3_tcon_ref_trace trace) { struct cifs_tcon *ret_buf; + static atomic_t tcon_debug_id; ret_buf = kzalloc(sizeof(*ret_buf), GFP_KERNEL); if (!ret_buf) @@ -132,7 +131,8 @@ tcon_info_alloc(bool dir_leases_enabled) atomic_inc(&tconInfoAllocCount); ret_buf->status = TID_NEW; - ++ret_buf->tc_count; + ret_buf->debug_id = atomic_inc_return(&tcon_debug_id); + ret_buf->tc_count = 1; spin_lock_init(&ret_buf->tc_lock); INIT_LIST_HEAD(&ret_buf->openFileList); INIT_LIST_HEAD(&ret_buf->tcon_list); @@ -141,27 +141,26 @@ tcon_info_alloc(bool dir_leases_enabled) atomic_set(&ret_buf->num_local_opens, 0); atomic_set(&ret_buf->num_remote_opens, 0); ret_buf->stats_from_time = ktime_get_real_seconds(); -#ifdef CONFIG_CIFS_DFS_UPCALL - INIT_LIST_HEAD(&ret_buf->dfs_ses_list); +#ifdef CONFIG_CIFS_FSCACHE + mutex_init(&ret_buf->fscache_lock); #endif + trace_smb3_tcon_ref(ret_buf->debug_id, ret_buf->tc_count, trace); return ret_buf; } void -tconInfoFree(struct cifs_tcon *tcon) +tconInfoFree(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace) { if (tcon == NULL) { cifs_dbg(FYI, "Null buffer passed to tconInfoFree\n"); return; } + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, trace); free_cached_dirs(tcon->cfids); atomic_dec(&tconInfoAllocCount); kfree(tcon->nativeFileSystem); kfree_sensitive(tcon->password); -#ifdef CONFIG_CIFS_DFS_UPCALL - dfs_put_root_smb_sessions(&tcon->dfs_ses_list); -#endif kfree(tcon->origin_fullpath); kfree(tcon); } @@ -490,6 +489,8 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid != buf->Tid) continue; @@ -853,6 +854,40 @@ cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path) free_dentry_path(page); } +/* + * If a dentry has been deleted, all corresponding open handles should know that + * so that we do not defer close them. + */ +void cifs_mark_open_handles_for_deleted_file(struct inode *inode, + const char *path) +{ + struct cifsFileInfo *cfile; + void *page; + const char *full_path; + struct cifsInodeInfo *cinode = CIFS_I(inode); + + page = alloc_dentry_path(); + spin_lock(&cinode->open_file_lock); + + /* + * note: we need to construct path from dentry and compare only if the + * inode has any hardlinks. When number of hardlinks is 1, we can just + * mark all open handles since they are going to be from the same file. + */ + if (inode->i_nlink > 1) { + list_for_each_entry(cfile, &cinode->openFileList, flist) { + full_path = build_path_from_dentry(cfile->dentry, page); + if (!IS_ERR(full_path) && strcmp(full_path, path) == 0) + cfile->status_file_deleted = true; + } + } else { + list_for_each_entry(cfile, &cinode->openFileList, flist) + cfile->status_file_deleted = true; + } + spin_unlock(&cinode->open_file_lock); + free_dentry_path(page); +} + /* parses DFS referral V3 structure * caller is responsible for freeing target_nodes * returns: diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index b520eea7bfce..ebe1cb30e18e 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -22,6 +22,7 @@ #include "smb2proto.h" #include "fs_context.h" #include "cached_dir.h" +#include "reparse.h" /* * To be safe - for UCS to UTF-8 with strings loaded with the rare long @@ -56,23 +57,6 @@ static inline void dump_cifs_file_struct(struct file *file, char *label) #endif /* DEBUG2 */ /* - * Match a reparse point inode if reparse tag and ctime haven't changed. - * - * Windows Server updates ctime of reparse points when their data have changed. - * The server doesn't allow changing reparse tags from existing reparse points, - * though it's worth checking. - */ -static inline bool reparse_inode_match(struct inode *inode, - struct cifs_fattr *fattr) -{ - struct timespec64 ctime = inode_get_ctime(inode); - - return (CIFS_I(inode)->cifsAttrs & ATTR_REPARSE) && - CIFS_I(inode)->reparse_tag == fattr->cf_cifstag && - timespec64_equal(&ctime, &fattr->cf_ctime); -} - -/* * Attempt to preload the dcache with the results from the FIND_FIRST/NEXT * * Find the dentry that matches "name". If there isn't one, create one. If it's @@ -141,6 +125,8 @@ retry: if (likely(reparse_inode_match(inode, fattr))) { fattr->cf_mode = inode->i_mode; fattr->cf_rdev = inode->i_rdev; + fattr->cf_uid = inode->i_uid; + fattr->cf_gid = inode->i_gid; fattr->cf_eof = CIFS_I(inode)->netfs.remote_i_size; fattr->cf_symlink_target = NULL; } else { @@ -148,7 +134,7 @@ retry: rc = -ESTALE; } } - if (!rc && !cifs_fattr_to_inode(inode, fattr)) { + if (!rc && !cifs_fattr_to_inode(inode, fattr, true)) { dput(dentry); return; } diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c new file mode 100644 index 000000000000..a0ffbda90733 --- /dev/null +++ b/fs/smb/client/reparse.c @@ -0,0 +1,532 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2024 Paulo Alcantara <pc@manguebit.com> + */ + +#include <linux/fs.h> +#include <linux/stat.h> +#include <linux/slab.h> +#include "cifsglob.h" +#include "smb2proto.h" +#include "cifsproto.h" +#include "cifs_unicode.h" +#include "cifs_debug.h" +#include "fs_context.h" +#include "reparse.h" + +int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, const char *symname) +{ + struct reparse_symlink_data_buffer *buf = NULL; + struct cifs_open_info_data data; + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct inode *new; + struct kvec iov; + __le16 *path; + char *sym, sep = CIFS_DIR_SEP(cifs_sb); + u16 len, plen; + int rc = 0; + + sym = kstrdup(symname, GFP_KERNEL); + if (!sym) + return -ENOMEM; + + data = (struct cifs_open_info_data) { + .reparse_point = true, + .reparse = { .tag = IO_REPARSE_TAG_SYMLINK, }, + .symlink_target = sym, + }; + + convert_delimiter(sym, sep); + path = cifs_convert_path_to_utf16(sym, cifs_sb); + if (!path) { + rc = -ENOMEM; + goto out; + } + + plen = 2 * UniStrnlen((wchar_t *)path, PATH_MAX); + len = sizeof(*buf) + plen * 2; + buf = kzalloc(len, GFP_KERNEL); + if (!buf) { + rc = -ENOMEM; + goto out; + } + + buf->ReparseTag = cpu_to_le32(IO_REPARSE_TAG_SYMLINK); + buf->ReparseDataLength = cpu_to_le16(len - sizeof(struct reparse_data_buffer)); + buf->SubstituteNameOffset = cpu_to_le16(plen); + buf->SubstituteNameLength = cpu_to_le16(plen); + memcpy(&buf->PathBuffer[plen], path, plen); + buf->PrintNameOffset = 0; + buf->PrintNameLength = cpu_to_le16(plen); + memcpy(buf->PathBuffer, path, plen); + buf->Flags = cpu_to_le32(*symname != '/' ? SYMLINK_FLAG_RELATIVE : 0); + if (*sym != sep) + buf->Flags = cpu_to_le32(SYMLINK_FLAG_RELATIVE); + + convert_delimiter(sym, '/'); + iov.iov_base = buf; + iov.iov_len = len; + new = smb2_get_reparse_inode(&data, inode->i_sb, xid, + tcon, full_path, &iov, NULL); + if (!IS_ERR(new)) + d_instantiate(dentry, new); + else + rc = PTR_ERR(new); +out: + kfree(path); + cifs_free_open_info(&data); + kfree(buf); + return rc; +} + +static int nfs_set_reparse_buf(struct reparse_posix_data *buf, + mode_t mode, dev_t dev, + struct kvec *iov) +{ + u64 type; + u16 len, dlen; + + len = sizeof(*buf); + + switch ((type = reparse_mode_nfs_type(mode))) { + case NFS_SPECFILE_BLK: + case NFS_SPECFILE_CHR: + dlen = sizeof(__le64); + break; + case NFS_SPECFILE_FIFO: + case NFS_SPECFILE_SOCK: + dlen = 0; + break; + default: + return -EOPNOTSUPP; + } + + buf->ReparseTag = cpu_to_le32(IO_REPARSE_TAG_NFS); + buf->Reserved = 0; + buf->InodeType = cpu_to_le64(type); + buf->ReparseDataLength = cpu_to_le16(len + dlen - + sizeof(struct reparse_data_buffer)); + *(__le64 *)buf->DataBuffer = cpu_to_le64(((u64)MAJOR(dev) << 32) | + MINOR(dev)); + iov->iov_base = buf; + iov->iov_len = len + dlen; + return 0; +} + +static int mknod_nfs(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev) +{ + struct cifs_open_info_data data; + struct reparse_posix_data *p; + struct inode *new; + struct kvec iov; + __u8 buf[sizeof(*p) + sizeof(__le64)]; + int rc; + + p = (struct reparse_posix_data *)buf; + rc = nfs_set_reparse_buf(p, mode, dev, &iov); + if (rc) + return rc; + + data = (struct cifs_open_info_data) { + .reparse_point = true, + .reparse = { .tag = IO_REPARSE_TAG_NFS, .posix = p, }, + }; + + new = smb2_get_reparse_inode(&data, inode->i_sb, xid, + tcon, full_path, &iov, NULL); + if (!IS_ERR(new)) + d_instantiate(dentry, new); + else + rc = PTR_ERR(new); + cifs_free_open_info(&data); + return rc; +} + +static int wsl_set_reparse_buf(struct reparse_data_buffer *buf, + mode_t mode, struct kvec *iov) +{ + u32 tag; + + switch ((tag = reparse_mode_wsl_tag(mode))) { + case IO_REPARSE_TAG_LX_BLK: + case IO_REPARSE_TAG_LX_CHR: + case IO_REPARSE_TAG_LX_FIFO: + case IO_REPARSE_TAG_AF_UNIX: + break; + default: + return -EOPNOTSUPP; + } + + buf->ReparseTag = cpu_to_le32(tag); + buf->Reserved = 0; + buf->ReparseDataLength = 0; + iov->iov_base = buf; + iov->iov_len = sizeof(*buf); + return 0; +} + +static struct smb2_create_ea_ctx *ea_create_context(u32 dlen, size_t *cc_len) +{ + struct smb2_create_ea_ctx *cc; + + *cc_len = round_up(sizeof(*cc) + dlen, 8); + cc = kzalloc(*cc_len, GFP_KERNEL); + if (!cc) + return ERR_PTR(-ENOMEM); + + cc->ctx.NameOffset = cpu_to_le16(offsetof(struct smb2_create_ea_ctx, + name)); + cc->ctx.NameLength = cpu_to_le16(4); + memcpy(cc->name, SMB2_CREATE_EA_BUFFER, strlen(SMB2_CREATE_EA_BUFFER)); + cc->ctx.DataOffset = cpu_to_le16(offsetof(struct smb2_create_ea_ctx, ea)); + cc->ctx.DataLength = cpu_to_le32(dlen); + return cc; +} + +struct wsl_xattr { + const char *name; + __le64 value; + u16 size; + u32 next; +}; + +static int wsl_set_xattrs(struct inode *inode, umode_t _mode, + dev_t _dev, struct kvec *iov) +{ + struct smb2_file_full_ea_info *ea; + struct smb2_create_ea_ctx *cc; + struct smb3_fs_context *ctx = CIFS_SB(inode->i_sb)->ctx; + __le64 uid = cpu_to_le64(from_kuid(current_user_ns(), ctx->linux_uid)); + __le64 gid = cpu_to_le64(from_kgid(current_user_ns(), ctx->linux_gid)); + __le64 dev = cpu_to_le64(((u64)MINOR(_dev) << 32) | MAJOR(_dev)); + __le64 mode = cpu_to_le64(_mode); + struct wsl_xattr xattrs[] = { + { .name = SMB2_WSL_XATTR_UID, .value = uid, .size = SMB2_WSL_XATTR_UID_SIZE, }, + { .name = SMB2_WSL_XATTR_GID, .value = gid, .size = SMB2_WSL_XATTR_GID_SIZE, }, + { .name = SMB2_WSL_XATTR_MODE, .value = mode, .size = SMB2_WSL_XATTR_MODE_SIZE, }, + { .name = SMB2_WSL_XATTR_DEV, .value = dev, .size = SMB2_WSL_XATTR_DEV_SIZE, }, + }; + size_t cc_len; + u32 dlen = 0, next = 0; + int i, num_xattrs; + u8 name_size = SMB2_WSL_XATTR_NAME_LEN + 1; + + memset(iov, 0, sizeof(*iov)); + + /* Exclude $LXDEV xattr for sockets and fifos */ + if (S_ISSOCK(_mode) || S_ISFIFO(_mode)) + num_xattrs = ARRAY_SIZE(xattrs) - 1; + else + num_xattrs = ARRAY_SIZE(xattrs); + + for (i = 0; i < num_xattrs; i++) { + xattrs[i].next = ALIGN(sizeof(*ea) + name_size + + xattrs[i].size, 4); + dlen += xattrs[i].next; + } + + cc = ea_create_context(dlen, &cc_len); + if (IS_ERR(cc)) + return PTR_ERR(cc); + + ea = &cc->ea; + for (i = 0; i < num_xattrs; i++) { + ea = (void *)((u8 *)ea + next); + next = xattrs[i].next; + ea->next_entry_offset = cpu_to_le32(next); + + ea->ea_name_length = name_size - 1; + ea->ea_value_length = cpu_to_le16(xattrs[i].size); + memcpy(ea->ea_data, xattrs[i].name, name_size); + memcpy(&ea->ea_data[name_size], + &xattrs[i].value, xattrs[i].size); + } + ea->next_entry_offset = 0; + + iov->iov_base = cc; + iov->iov_len = cc_len; + return 0; +} + +static int mknod_wsl(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev) +{ + struct cifs_open_info_data data; + struct reparse_data_buffer buf; + struct smb2_create_ea_ctx *cc; + struct inode *new; + unsigned int len; + struct kvec reparse_iov, xattr_iov; + int rc; + + rc = wsl_set_reparse_buf(&buf, mode, &reparse_iov); + if (rc) + return rc; + + rc = wsl_set_xattrs(inode, mode, dev, &xattr_iov); + if (rc) + return rc; + + data = (struct cifs_open_info_data) { + .reparse_point = true, + .reparse = { .tag = le32_to_cpu(buf.ReparseTag), .buf = &buf, }, + }; + + cc = xattr_iov.iov_base; + len = le32_to_cpu(cc->ctx.DataLength); + memcpy(data.wsl.eas, &cc->ea, len); + data.wsl.eas_len = len; + + new = smb2_get_reparse_inode(&data, inode->i_sb, + xid, tcon, full_path, + &reparse_iov, &xattr_iov); + if (!IS_ERR(new)) + d_instantiate(dentry, new); + else + rc = PTR_ERR(new); + cifs_free_open_info(&data); + kfree(xattr_iov.iov_base); + return rc; +} + +int smb2_mknod_reparse(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev) +{ + struct smb3_fs_context *ctx = CIFS_SB(inode->i_sb)->ctx; + int rc = -EOPNOTSUPP; + + switch (ctx->reparse_type) { + case CIFS_REPARSE_TYPE_NFS: + rc = mknod_nfs(xid, inode, dentry, tcon, full_path, mode, dev); + break; + case CIFS_REPARSE_TYPE_WSL: + rc = mknod_wsl(xid, inode, dentry, tcon, full_path, mode, dev); + break; + } + return rc; +} + +/* See MS-FSCC 2.1.2.6 for the 'NFS' style reparse tags */ +static int parse_reparse_posix(struct reparse_posix_data *buf, + struct cifs_sb_info *cifs_sb, + struct cifs_open_info_data *data) +{ + unsigned int len; + u64 type; + + switch ((type = le64_to_cpu(buf->InodeType))) { + case NFS_SPECFILE_LNK: + len = le16_to_cpu(buf->ReparseDataLength); + data->symlink_target = cifs_strndup_from_utf16(buf->DataBuffer, + len, true, + cifs_sb->local_nls); + if (!data->symlink_target) + return -ENOMEM; + convert_delimiter(data->symlink_target, '/'); + cifs_dbg(FYI, "%s: target path: %s\n", + __func__, data->symlink_target); + break; + case NFS_SPECFILE_CHR: + case NFS_SPECFILE_BLK: + case NFS_SPECFILE_FIFO: + case NFS_SPECFILE_SOCK: + break; + default: + cifs_dbg(VFS, "%s: unhandled inode type: 0x%llx\n", + __func__, type); + return -EOPNOTSUPP; + } + return 0; +} + +static int parse_reparse_symlink(struct reparse_symlink_data_buffer *sym, + u32 plen, bool unicode, + struct cifs_sb_info *cifs_sb, + struct cifs_open_info_data *data) +{ + unsigned int len; + unsigned int offs; + + /* We handle Symbolic Link reparse tag here. See: MS-FSCC 2.1.2.4 */ + + offs = le16_to_cpu(sym->SubstituteNameOffset); + len = le16_to_cpu(sym->SubstituteNameLength); + if (offs + 20 > plen || offs + len + 20 > plen) { + cifs_dbg(VFS, "srv returned malformed symlink buffer\n"); + return -EIO; + } + + data->symlink_target = cifs_strndup_from_utf16(sym->PathBuffer + offs, + len, unicode, + cifs_sb->local_nls); + if (!data->symlink_target) + return -ENOMEM; + + convert_delimiter(data->symlink_target, '/'); + cifs_dbg(FYI, "%s: target path: %s\n", __func__, data->symlink_target); + + return 0; +} + +int parse_reparse_point(struct reparse_data_buffer *buf, + u32 plen, struct cifs_sb_info *cifs_sb, + bool unicode, struct cifs_open_info_data *data) +{ + data->reparse.buf = buf; + + /* See MS-FSCC 2.1.2 */ + switch (le32_to_cpu(buf->ReparseTag)) { + case IO_REPARSE_TAG_NFS: + return parse_reparse_posix((struct reparse_posix_data *)buf, + cifs_sb, data); + case IO_REPARSE_TAG_SYMLINK: + return parse_reparse_symlink( + (struct reparse_symlink_data_buffer *)buf, + plen, unicode, cifs_sb, data); + case IO_REPARSE_TAG_LX_SYMLINK: + case IO_REPARSE_TAG_AF_UNIX: + case IO_REPARSE_TAG_LX_FIFO: + case IO_REPARSE_TAG_LX_CHR: + case IO_REPARSE_TAG_LX_BLK: + return 0; + default: + cifs_dbg(VFS, "%s: unhandled reparse tag: 0x%08x\n", + __func__, le32_to_cpu(buf->ReparseTag)); + return -EOPNOTSUPP; + } +} + +int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb, + struct kvec *rsp_iov, + struct cifs_open_info_data *data) +{ + struct reparse_data_buffer *buf; + struct smb2_ioctl_rsp *io = rsp_iov->iov_base; + u32 plen = le32_to_cpu(io->OutputCount); + + buf = (struct reparse_data_buffer *)((u8 *)io + + le32_to_cpu(io->OutputOffset)); + return parse_reparse_point(buf, plen, cifs_sb, true, data); +} + +static void wsl_to_fattr(struct cifs_open_info_data *data, + struct cifs_sb_info *cifs_sb, + u32 tag, struct cifs_fattr *fattr) +{ + struct smb2_file_full_ea_info *ea; + u32 next = 0; + + switch (tag) { + case IO_REPARSE_TAG_LX_SYMLINK: + fattr->cf_mode |= S_IFLNK; + break; + case IO_REPARSE_TAG_LX_FIFO: + fattr->cf_mode |= S_IFIFO; + break; + case IO_REPARSE_TAG_AF_UNIX: + fattr->cf_mode |= S_IFSOCK; + break; + case IO_REPARSE_TAG_LX_CHR: + fattr->cf_mode |= S_IFCHR; + break; + case IO_REPARSE_TAG_LX_BLK: + fattr->cf_mode |= S_IFBLK; + break; + } + + if (!data->wsl.eas_len) + goto out; + + ea = (struct smb2_file_full_ea_info *)data->wsl.eas; + do { + const char *name; + void *v; + u8 nlen; + + ea = (void *)((u8 *)ea + next); + next = le32_to_cpu(ea->next_entry_offset); + if (!le16_to_cpu(ea->ea_value_length)) + continue; + + name = ea->ea_data; + nlen = ea->ea_name_length; + v = (void *)((u8 *)ea->ea_data + ea->ea_name_length + 1); + + if (!strncmp(name, SMB2_WSL_XATTR_UID, nlen)) + fattr->cf_uid = wsl_make_kuid(cifs_sb, v); + else if (!strncmp(name, SMB2_WSL_XATTR_GID, nlen)) + fattr->cf_gid = wsl_make_kgid(cifs_sb, v); + else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) + fattr->cf_mode = (umode_t)le32_to_cpu(*(__le32 *)v); + else if (!strncmp(name, SMB2_WSL_XATTR_DEV, nlen)) + fattr->cf_rdev = wsl_mkdev(v); + } while (next); +out: + fattr->cf_dtype = S_DT(fattr->cf_mode); +} + +bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, + struct cifs_fattr *fattr, + struct cifs_open_info_data *data) +{ + struct reparse_posix_data *buf = data->reparse.posix; + u32 tag = data->reparse.tag; + + if (tag == IO_REPARSE_TAG_NFS && buf) { + switch (le64_to_cpu(buf->InodeType)) { + case NFS_SPECFILE_CHR: + fattr->cf_mode |= S_IFCHR; + fattr->cf_rdev = reparse_nfs_mkdev(buf); + break; + case NFS_SPECFILE_BLK: + fattr->cf_mode |= S_IFBLK; + fattr->cf_rdev = reparse_nfs_mkdev(buf); + break; + case NFS_SPECFILE_FIFO: + fattr->cf_mode |= S_IFIFO; + break; + case NFS_SPECFILE_SOCK: + fattr->cf_mode |= S_IFSOCK; + break; + case NFS_SPECFILE_LNK: + fattr->cf_mode |= S_IFLNK; + break; + default: + WARN_ON_ONCE(1); + return false; + } + goto out; + } + + switch (tag) { + case IO_REPARSE_TAG_DFS: + case IO_REPARSE_TAG_DFSR: + case IO_REPARSE_TAG_MOUNT_POINT: + /* See cifs_create_junction_fattr() */ + fattr->cf_mode = S_IFDIR | 0711; + break; + case IO_REPARSE_TAG_LX_SYMLINK: + case IO_REPARSE_TAG_LX_FIFO: + case IO_REPARSE_TAG_AF_UNIX: + case IO_REPARSE_TAG_LX_CHR: + case IO_REPARSE_TAG_LX_BLK: + wsl_to_fattr(data, cifs_sb, tag, fattr); + break; + case 0: /* SMB1 symlink */ + case IO_REPARSE_TAG_SYMLINK: + case IO_REPARSE_TAG_NFS: + fattr->cf_mode |= S_IFLNK; + break; + default: + return false; + } +out: + fattr->cf_dtype = S_DT(fattr->cf_mode); + return true; +} diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h new file mode 100644 index 000000000000..6b55d1df9e2f --- /dev/null +++ b/fs/smb/client/reparse.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024 Paulo Alcantara <pc@manguebit.com> + */ + +#ifndef _CIFS_REPARSE_H +#define _CIFS_REPARSE_H + +#include <linux/fs.h> +#include <linux/stat.h> +#include <linux/uidgid.h> +#include "fs_context.h" +#include "cifsglob.h" + +static inline dev_t reparse_nfs_mkdev(struct reparse_posix_data *buf) +{ + u64 v = le64_to_cpu(*(__le64 *)buf->DataBuffer); + + return MKDEV(v >> 32, v & 0xffffffff); +} + +static inline dev_t wsl_mkdev(void *ptr) +{ + u64 v = le64_to_cpu(*(__le64 *)ptr); + + return MKDEV(v & 0xffffffff, v >> 32); +} + +static inline kuid_t wsl_make_kuid(struct cifs_sb_info *cifs_sb, + void *ptr) +{ + u32 uid = le32_to_cpu(*(__le32 *)ptr); + + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) + return cifs_sb->ctx->linux_uid; + return make_kuid(current_user_ns(), uid); +} + +static inline kgid_t wsl_make_kgid(struct cifs_sb_info *cifs_sb, + void *ptr) +{ + u32 gid = le32_to_cpu(*(__le32 *)ptr); + + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) + return cifs_sb->ctx->linux_gid; + return make_kgid(current_user_ns(), gid); +} + +static inline u64 reparse_mode_nfs_type(mode_t mode) +{ + switch (mode & S_IFMT) { + case S_IFBLK: return NFS_SPECFILE_BLK; + case S_IFCHR: return NFS_SPECFILE_CHR; + case S_IFIFO: return NFS_SPECFILE_FIFO; + case S_IFSOCK: return NFS_SPECFILE_SOCK; + } + return 0; +} + +static inline u32 reparse_mode_wsl_tag(mode_t mode) +{ + switch (mode & S_IFMT) { + case S_IFBLK: return IO_REPARSE_TAG_LX_BLK; + case S_IFCHR: return IO_REPARSE_TAG_LX_CHR; + case S_IFIFO: return IO_REPARSE_TAG_LX_FIFO; + case S_IFSOCK: return IO_REPARSE_TAG_AF_UNIX; + } + return 0; +} + +/* + * Match a reparse point inode if reparse tag and ctime haven't changed. + * + * Windows Server updates ctime of reparse points when their data have changed. + * The server doesn't allow changing reparse tags from existing reparse points, + * though it's worth checking. + */ +static inline bool reparse_inode_match(struct inode *inode, + struct cifs_fattr *fattr) +{ + struct timespec64 ctime = inode_get_ctime(inode); + + return (CIFS_I(inode)->cifsAttrs & ATTR_REPARSE) && + CIFS_I(inode)->reparse_tag == fattr->cf_cifstag && + timespec64_equal(&ctime, &fattr->cf_ctime); +} + +static inline bool cifs_open_data_reparse(struct cifs_open_info_data *data) +{ + struct smb2_file_all_info *fi = &data->fi; + u32 attrs = le32_to_cpu(fi->Attributes); + bool ret; + + ret = data->reparse_point || (attrs & ATTR_REPARSE); + if (ret) + attrs |= ATTR_REPARSE; + fi->Attributes = cpu_to_le32(attrs); + return ret; +} + +bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, + struct cifs_fattr *fattr, + struct cifs_open_info_data *data); +int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, const char *symname); +int smb2_mknod_reparse(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev); +int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb, struct kvec *rsp_iov, + struct cifs_open_info_data *data); + +#endif /* _CIFS_REPARSE_H */ diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 8f37373fd333..3216f786908f 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -230,7 +230,7 @@ int cifs_try_adding_channels(struct cifs_ses *ses) spin_lock(&ses->iface_lock); if (!ses->iface_count) { spin_unlock(&ses->iface_lock); - cifs_dbg(VFS, "server %s does not advertise interfaces\n", + cifs_dbg(ONCE, "server %s does not advertise interfaces\n", ses->server->hostname); break; } @@ -396,7 +396,7 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) spin_lock(&ses->iface_lock); if (!ses->iface_count) { spin_unlock(&ses->iface_lock); - cifs_dbg(VFS, "server %s does not advertise interfaces\n", ses->server->hostname); + cifs_dbg(ONCE, "server %s does not advertise interfaces\n", ses->server->hostname); return; } diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index a9eaba8083b0..212ec6f66ec6 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -753,11 +753,11 @@ cifs_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode); } -static void +static int cifs_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - CIFSSMBClose(xid, tcon, fid->netfid); + return CIFSSMBClose(xid, tcon, fid->netfid); } static int diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index e0ee96d69d49..c23478ab1cf8 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -228,7 +228,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, * flock and OFD lock are associated with an open * file description, not the process. */ - if (!(flock->fl_flags & (FL_FLOCK | FL_OFDLCK))) + if (!(flock->c.flc_flags & (FL_FLOCK | FL_OFDLCK))) continue; if (cinode->can_cache_brlcks) { /* diff --git a/fs/smb/client/smb2glob.h b/fs/smb/client/smb2glob.h index a0c156996fc5..2466e6155136 100644 --- a/fs/smb/client/smb2glob.h +++ b/fs/smb/client/smb2glob.h @@ -36,7 +36,8 @@ enum smb2_compound_ops { SMB2_OP_RMDIR, SMB2_OP_POSIX_QUERY_INFO, SMB2_OP_SET_REPARSE, - SMB2_OP_GET_REPARSE + SMB2_OP_GET_REPARSE, + SMB2_OP_QUERY_WSL_EA, }; /* Used when constructing chained read requests. */ diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 05818cd6d932..5c02a12251c8 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -85,6 +85,82 @@ static int parse_posix_sids(struct cifs_open_info_data *data, return 0; } +struct wsl_query_ea { + __le32 next; + __u8 name_len; + __u8 name[SMB2_WSL_XATTR_NAME_LEN + 1]; +} __packed; + +#define NEXT_OFF cpu_to_le32(sizeof(struct wsl_query_ea)) + +static const struct wsl_query_ea wsl_query_eas[] = { + { .next = NEXT_OFF, .name_len = SMB2_WSL_XATTR_NAME_LEN, .name = SMB2_WSL_XATTR_UID, }, + { .next = NEXT_OFF, .name_len = SMB2_WSL_XATTR_NAME_LEN, .name = SMB2_WSL_XATTR_GID, }, + { .next = NEXT_OFF, .name_len = SMB2_WSL_XATTR_NAME_LEN, .name = SMB2_WSL_XATTR_MODE, }, + { .next = 0, .name_len = SMB2_WSL_XATTR_NAME_LEN, .name = SMB2_WSL_XATTR_DEV, }, +}; + +static int check_wsl_eas(struct kvec *rsp_iov) +{ + struct smb2_file_full_ea_info *ea; + struct smb2_query_info_rsp *rsp = rsp_iov->iov_base; + unsigned long addr; + u32 outlen, next; + u16 vlen; + u8 nlen; + u8 *end; + + outlen = le32_to_cpu(rsp->OutputBufferLength); + if (outlen < SMB2_WSL_MIN_QUERY_EA_RESP_SIZE || + outlen > SMB2_WSL_MAX_QUERY_EA_RESP_SIZE) + return -EINVAL; + + ea = (void *)((u8 *)rsp_iov->iov_base + + le16_to_cpu(rsp->OutputBufferOffset)); + end = (u8 *)rsp_iov->iov_base + rsp_iov->iov_len; + for (;;) { + if ((u8 *)ea > end - sizeof(*ea)) + return -EINVAL; + + nlen = ea->ea_name_length; + vlen = le16_to_cpu(ea->ea_value_length); + if (nlen != SMB2_WSL_XATTR_NAME_LEN || + (u8 *)ea + nlen + 1 + vlen > end) + return -EINVAL; + + switch (vlen) { + case 4: + if (strncmp(ea->ea_data, SMB2_WSL_XATTR_UID, nlen) && + strncmp(ea->ea_data, SMB2_WSL_XATTR_GID, nlen) && + strncmp(ea->ea_data, SMB2_WSL_XATTR_MODE, nlen)) + return -EINVAL; + break; + case 8: + if (strncmp(ea->ea_data, SMB2_WSL_XATTR_DEV, nlen)) + return -EINVAL; + break; + case 0: + if (!strncmp(ea->ea_data, SMB2_WSL_XATTR_UID, nlen) || + !strncmp(ea->ea_data, SMB2_WSL_XATTR_GID, nlen) || + !strncmp(ea->ea_data, SMB2_WSL_XATTR_MODE, nlen) || + !strncmp(ea->ea_data, SMB2_WSL_XATTR_DEV, nlen)) + break; + fallthrough; + default: + return -EINVAL; + } + + next = le32_to_cpu(ea->next_entry_offset); + if (!next) + break; + if (!IS_ALIGNED(next, 4) || + check_add_overflow((unsigned long)ea, next, &addr)) + return -EINVAL; + ea = (void *)addr; + } + return 0; +} + /* * note: If cfile is passed, the reference to it is dropped here. * So make sure that you do not reuse cfile after return from this func. @@ -95,10 +171,9 @@ static int parse_posix_sids(struct cifs_open_info_data *data, */ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, - __u32 desired_access, __u32 create_disposition, - __u32 create_options, umode_t mode, struct kvec *in_iov, + struct cifs_open_parms *oparms, struct kvec *in_iov, int *cmds, int num_cmds, struct cifsFileInfo *cfile, - struct kvec *out_iov, int *out_buftype) + struct kvec *out_iov, int *out_buftype, struct dentry *dentry) { struct reparse_data_buffer *rbuf; @@ -115,11 +190,12 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, int resp_buftype[MAX_COMPOUND]; struct smb2_query_info_rsp *qi_rsp = NULL; struct cifs_open_info_data *idata; + struct inode *inode = NULL; int flags = 0; __u8 delete_pending[8] = {1, 0, 0, 0, 0, 0, 0, 0}; unsigned int size[2]; void *data[2]; - int len; + unsigned int len; int retries = 0, cur_sleep = 1; replay_again: @@ -152,16 +228,28 @@ replay_again: goto finished; } - vars->oparms = (struct cifs_open_parms) { - .tcon = tcon, - .path = full_path, - .desired_access = desired_access, - .disposition = create_disposition, - .create_options = cifs_create_options(cifs_sb, create_options), - .fid = &fid, - .mode = mode, - .cifs_sb = cifs_sb, - }; + /* if there is an existing lease, reuse it */ + + /* + * note: files with hardlinks cause unexpected behaviour. As per MS-SMB2, + * lease keys are associated with the filepath. We are maintaining lease keys + * with the inode on the client. If the file has hardlinks, it is possible + * that the lease for a file be reused for an operation on its hardlink or + * vice versa. + * As a workaround, send request using an existing lease key and if the server + * returns STATUS_INVALID_PARAMETER, which maps to EINVAL, send the request + * again without the lease. + */ + if (dentry) { + inode = d_inode(dentry); + if (CIFS_I(inode)->lease_granted && server->ops->get_lease_key) { + oplock = SMB2_OPLOCK_LEVEL_LEASE; + server->ops->get_lease_key(inode, &fid); + } + } + + vars->oparms = *oparms; + vars->oparms.fid = &fid; rqst[num_rqst].rq_iov = &vars->open_iov[0]; rqst[num_rqst].rq_nvec = SMB2_CREATE_IOV_SIZE; @@ -202,14 +290,13 @@ replay_again: SMB2_O_INFO_FILE, 0, sizeof(struct smb2_file_all_info) + PATH_MAX * 2, 0, NULL); - if (!rc) { - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst]); - } } - - if (rc) + if (!rc && (!cfile || num_rqst > 1)) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } else if (rc) { goto finished; + } num_rqst++; trace_smb3_query_info_compound_enter(xid, ses->Suid, tcon->tid, full_path); @@ -239,14 +326,13 @@ replay_again: sizeof(struct smb311_posix_qinfo *) + (PATH_MAX * 2) + (sizeof(struct cifs_sid) * 2), 0, NULL); - if (!rc) { - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst]); - } } - - if (rc) + if (!rc && (!cfile || num_rqst > 1)) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } else if (rc) { goto finished; + } num_rqst++; trace_smb3_posix_query_info_compound_enter(xid, ses->Suid, tcon->tid, full_path); @@ -304,13 +390,13 @@ replay_again: FILE_END_OF_FILE_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); - if (!rc) { - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst]); - } } - if (rc) + if (!rc && (!cfile || num_rqst > 1)) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } else if (rc) { goto finished; + } num_rqst++; trace_smb3_set_eof_enter(xid, ses->Suid, tcon->tid, full_path); break; @@ -335,14 +421,13 @@ replay_again: COMPOUND_FID, current->tgid, FILE_BASIC_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); - if (!rc) { - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst]); - } } - - if (rc) + if (!rc && (!cfile || num_rqst > 1)) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } else if (rc) { goto finished; + } num_rqst++; trace_smb3_set_info_compound_enter(xid, ses->Suid, tcon->tid, full_path); @@ -376,13 +461,13 @@ replay_again: COMPOUND_FID, COMPOUND_FID, current->tgid, FILE_RENAME_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); - if (!rc) { - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst]); - } } - if (rc) + if (!rc && (!cfile || num_rqst > 1)) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } else if (rc) { goto finished; + } num_rqst++; trace_smb3_rename_enter(xid, ses->Suid, tcon->tid, full_path); break; @@ -417,15 +502,27 @@ replay_again: rqst[num_rqst].rq_iov = vars->io_iov; rqst[num_rqst].rq_nvec = ARRAY_SIZE(vars->io_iov); - rc = SMB2_ioctl_init(tcon, server, &rqst[num_rqst], - COMPOUND_FID, COMPOUND_FID, - FSCTL_SET_REPARSE_POINT, - in_iov[i].iov_base, - in_iov[i].iov_len, 0); - if (rc) + if (cfile) { + rc = SMB2_ioctl_init(tcon, server, &rqst[num_rqst], + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + FSCTL_SET_REPARSE_POINT, + in_iov[i].iov_base, + in_iov[i].iov_len, 0); + } else { + rc = SMB2_ioctl_init(tcon, server, &rqst[num_rqst], + COMPOUND_FID, COMPOUND_FID, + FSCTL_SET_REPARSE_POINT, + in_iov[i].iov_base, + in_iov[i].iov_len, 0); + } + if (!rc && (!cfile || num_rqst > 1)) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } else if (rc) { goto finished; - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst++]); + } + num_rqst++; trace_smb3_set_reparse_compound_enter(xid, ses->Suid, tcon->tid, full_path); break; @@ -433,17 +530,61 @@ replay_again: rqst[num_rqst].rq_iov = vars->io_iov; rqst[num_rqst].rq_nvec = ARRAY_SIZE(vars->io_iov); - rc = SMB2_ioctl_init(tcon, server, &rqst[num_rqst], - COMPOUND_FID, COMPOUND_FID, - FSCTL_GET_REPARSE_POINT, - NULL, 0, CIFSMaxBufSize); - if (rc) + if (cfile) { + rc = SMB2_ioctl_init(tcon, server, &rqst[num_rqst], + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + FSCTL_GET_REPARSE_POINT, + NULL, 0, CIFSMaxBufSize); + } else { + rc = SMB2_ioctl_init(tcon, server, &rqst[num_rqst], + COMPOUND_FID, COMPOUND_FID, + FSCTL_GET_REPARSE_POINT, + NULL, 0, CIFSMaxBufSize); + } + if (!rc && (!cfile || num_rqst > 1)) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } else if (rc) { goto finished; - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst++]); + } + num_rqst++; trace_smb3_get_reparse_compound_enter(xid, ses->Suid, tcon->tid, full_path); break; + case SMB2_OP_QUERY_WSL_EA: + rqst[num_rqst].rq_iov = &vars->ea_iov; + rqst[num_rqst].rq_nvec = 1; + + if (cfile) { + rc = SMB2_query_info_init(tcon, server, + &rqst[num_rqst], + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + FILE_FULL_EA_INFORMATION, + SMB2_O_INFO_FILE, 0, + SMB2_WSL_MAX_QUERY_EA_RESP_SIZE, + sizeof(wsl_query_eas), + (void *)wsl_query_eas); + } else { + rc = SMB2_query_info_init(tcon, server, + &rqst[num_rqst], + COMPOUND_FID, + COMPOUND_FID, + FILE_FULL_EA_INFORMATION, + SMB2_O_INFO_FILE, 0, + SMB2_WSL_MAX_QUERY_EA_RESP_SIZE, + sizeof(wsl_query_eas), + (void *)wsl_query_eas); + } + if (!rc && (!cfile || num_rqst > 1)) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } else if (rc) { + goto finished; + } + num_rqst++; + break; default: cifs_dbg(VFS, "Invalid command\n"); rc = -EINVAL; @@ -551,8 +692,15 @@ finished: case SMB2_OP_DELETE: if (rc) trace_smb3_delete_err(xid, ses->Suid, tcon->tid, rc); - else + else { + /* + * If dentry (hence, inode) is NULL, lease break is going to + * take care of degrading leases on handles for deleted files. + */ + if (inode) + cifs_mark_open_handles_for_deleted_file(inode, full_path); trace_smb3_delete_done(xid, ses->Suid, tcon->tid); + } break; case SMB2_OP_MKDIR: if (rc) @@ -626,11 +774,32 @@ finished: memset(iov, 0, sizeof(*iov)); resp_buftype[i + 1] = CIFS_NO_BUFFER; } else { - trace_smb3_set_reparse_compound_err(xid, ses->Suid, + trace_smb3_set_reparse_compound_err(xid, ses->Suid, tcon->tid, rc); } SMB2_ioctl_free(&rqst[num_rqst++]); break; + case SMB2_OP_QUERY_WSL_EA: + if (!rc) { + idata = in_iov[i].iov_base; + qi_rsp = rsp_iov[i + 1].iov_base; + data[0] = (u8 *)qi_rsp + le16_to_cpu(qi_rsp->OutputBufferOffset); + size[0] = le32_to_cpu(qi_rsp->OutputBufferLength); + rc = check_wsl_eas(&rsp_iov[i + 1]); + if (!rc) { + memcpy(idata->wsl.eas, data[0], size[0]); + idata->wsl.eas_len = size[0]; + } + } + if (!rc) { + trace_smb3_query_wsl_ea_compound_done(xid, ses->Suid, + tcon->tid); + } else { + trace_smb3_query_wsl_ea_compound_err(xid, ses->Suid, + tcon->tid, rc); + } + SMB2_query_info_free(&rqst[num_rqst++]); + break; } } SMB2_close_free(&rqst[num_rqst]); @@ -693,15 +862,16 @@ int smb2_query_path_info(const unsigned int xid, const char *full_path, struct cifs_open_info_data *data) { + struct cifs_open_parms oparms; __u32 create_options = 0; struct cifsFileInfo *cfile; struct cached_fid *cfid = NULL; struct smb2_hdr *hdr; - struct kvec in_iov[2], out_iov[3] = {}; + struct kvec in_iov[3], out_iov[3] = {}; int out_buftype[3] = {}; - int cmds[2]; + int cmds[3]; bool islink; - int i, num_cmds; + int i, num_cmds = 0; int rc, rc2; data->adjust_tz = false; @@ -734,20 +904,22 @@ int smb2_query_path_info(const unsigned int xid, close_cached_dir(cfid); return rc; } - cmds[0] = SMB2_OP_QUERY_INFO; + cmds[num_cmds++] = SMB2_OP_QUERY_INFO; } else { - cmds[0] = SMB2_OP_POSIX_QUERY_INFO; + cmds[num_cmds++] = SMB2_OP_POSIX_QUERY_INFO; } in_iov[0].iov_base = data; in_iov[0].iov_len = sizeof(*data); in_iov[1] = in_iov[0]; + in_iov[2] = in_iov[0]; cifs_get_readable_path(tcon, full_path, &cfile); + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_READ_ATTRIBUTES, + FILE_OPEN, create_options, ACL_NO_MODE); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, - create_options, ACL_NO_MODE, in_iov, - cmds, 1, cfile, out_iov, out_buftype); + &oparms, in_iov, cmds, num_cmds, + cfile, out_iov, out_buftype, NULL); hdr = out_iov[0].iov_base; /* * If first iov is unset, then SMB session was dropped or we've got a @@ -767,19 +939,22 @@ int smb2_query_path_info(const unsigned int xid, if (rc || !data->reparse_point) goto out; - if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK) { - /* symlink already parsed in create response */ - num_cmds = 1; - } else { - cmds[1] = SMB2_OP_GET_REPARSE; - num_cmds = 2; - } - create_options |= OPEN_REPARSE_POINT; + cmds[num_cmds++] = SMB2_OP_QUERY_WSL_EA; + /* + * Skip SMB2_OP_GET_REPARSE if symlink already parsed in create + * response. + */ + if (data->reparse.tag != IO_REPARSE_TAG_SYMLINK) + cmds[num_cmds++] = SMB2_OP_GET_REPARSE; + + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, + FILE_READ_ATTRIBUTES | FILE_READ_EA, + FILE_OPEN, create_options | + OPEN_REPARSE_POINT, ACL_NO_MODE); cifs_get_readable_path(tcon, full_path, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, - create_options, ACL_NO_MODE, in_iov, - cmds, num_cmds, cfile, NULL, NULL); + &oparms, in_iov, cmds, num_cmds, + cfile, NULL, NULL, NULL); break; case -EREMOTE: break; @@ -807,11 +982,14 @@ smb2_mkdir(const unsigned int xid, struct inode *parent_inode, umode_t mode, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb) { - return smb2_compound_op(xid, tcon, cifs_sb, name, - FILE_WRITE_ATTRIBUTES, FILE_CREATE, - CREATE_NOT_FILE, mode, - NULL, &(int){SMB2_OP_MKDIR}, 1, - NULL, NULL, NULL); + struct cifs_open_parms oparms; + + oparms = CIFS_OPARMS(cifs_sb, tcon, name, FILE_WRITE_ATTRIBUTES, + FILE_CREATE, CREATE_NOT_FILE, mode); + return smb2_compound_op(xid, tcon, cifs_sb, + name, &oparms, NULL, + &(int){SMB2_OP_MKDIR}, 1, + NULL, NULL, NULL, NULL); } void @@ -819,6 +997,7 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name, struct cifs_sb_info *cifs_sb, struct cifs_tcon *tcon, const unsigned int xid) { + struct cifs_open_parms oparms; FILE_BASIC_INFO data = {}; struct cifsInodeInfo *cifs_i; struct cifsFileInfo *cfile; @@ -832,11 +1011,12 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name, dosattrs = cifs_i->cifsAttrs | ATTR_READONLY; data.Attributes = cpu_to_le32(dosattrs); cifs_get_writable_path(tcon, name, FIND_WR_ANY, &cfile); + oparms = CIFS_OPARMS(cifs_sb, tcon, name, FILE_WRITE_ATTRIBUTES, + FILE_CREATE, CREATE_NOT_FILE, ACL_NO_MODE); tmprc = smb2_compound_op(xid, tcon, cifs_sb, name, - FILE_WRITE_ATTRIBUTES, FILE_CREATE, - CREATE_NOT_FILE, ACL_NO_MODE, &in_iov, + &oparms, &in_iov, &(int){SMB2_OP_SET_INFO}, 1, - cfile, NULL, NULL); + cfile, NULL, NULL, NULL); if (tmprc == 0) cifs_i->cifsAttrs = dosattrs; } @@ -845,31 +1025,47 @@ int smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb) { + struct cifs_open_parms oparms; + drop_cached_dir_by_name(xid, tcon, name, cifs_sb); - return smb2_compound_op(xid, tcon, cifs_sb, name, - DELETE, FILE_OPEN, CREATE_NOT_FILE, - ACL_NO_MODE, NULL, + oparms = CIFS_OPARMS(cifs_sb, tcon, name, DELETE, + FILE_OPEN, CREATE_NOT_FILE, ACL_NO_MODE); + return smb2_compound_op(xid, tcon, cifs_sb, + name, &oparms, NULL, &(int){SMB2_OP_RMDIR}, 1, - NULL, NULL, NULL); + NULL, NULL, NULL, NULL); } int smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name, - struct cifs_sb_info *cifs_sb) + struct cifs_sb_info *cifs_sb, struct dentry *dentry) { - return smb2_compound_op(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN, - CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT, - ACL_NO_MODE, NULL, - &(int){SMB2_OP_DELETE}, 1, - NULL, NULL, NULL); + struct cifs_open_parms oparms; + + oparms = CIFS_OPARMS(cifs_sb, tcon, name, + DELETE, FILE_OPEN, + CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT, + ACL_NO_MODE); + int rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, + NULL, &(int){SMB2_OP_DELETE}, 1, + NULL, NULL, NULL, dentry); + if (rc == -EINVAL) { + cifs_dbg(FYI, "invalid lease key, resending request without lease"); + rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, + NULL, &(int){SMB2_OP_DELETE}, 1, + NULL, NULL, NULL, NULL); + } + return rc; } static int smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon, const char *from_name, const char *to_name, struct cifs_sb_info *cifs_sb, __u32 create_options, __u32 access, - int command, struct cifsFileInfo *cfile) + int command, struct cifsFileInfo *cfile, + struct dentry *dentry) { + struct cifs_open_parms oparms; struct kvec in_iov; __le16 *smb2_to_name = NULL; int rc; @@ -881,9 +1077,11 @@ static int smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon, } in_iov.iov_base = smb2_to_name; in_iov.iov_len = 2 * UniStrnlen((wchar_t *)smb2_to_name, PATH_MAX); - rc = smb2_compound_op(xid, tcon, cifs_sb, from_name, access, - FILE_OPEN, create_options, ACL_NO_MODE, - &in_iov, &command, 1, cfile, NULL, NULL); + oparms = CIFS_OPARMS(cifs_sb, tcon, from_name, access, FILE_OPEN, + create_options, ACL_NO_MODE); + rc = smb2_compound_op(xid, tcon, cifs_sb, from_name, + &oparms, &in_iov, &command, 1, + cfile, NULL, NULL, dentry); smb2_rename_path: kfree(smb2_to_name); return rc; @@ -901,8 +1099,14 @@ int smb2_rename_path(const unsigned int xid, drop_cached_dir_by_name(xid, tcon, from_name, cifs_sb); cifs_get_writable_path(tcon, from_name, FIND_WR_WITH_DELETE, &cfile); - return smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb, - co, DELETE, SMB2_OP_RENAME, cfile); + int rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb, + co, DELETE, SMB2_OP_RENAME, cfile, source_dentry); + if (rc == -EINVAL) { + cifs_dbg(FYI, "invalid lease key, resending request without lease"); + rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb, + co, DELETE, SMB2_OP_RENAME, cfile, NULL); + } + return rc; } int smb2_create_hardlink(const unsigned int xid, @@ -915,32 +1119,46 @@ int smb2_create_hardlink(const unsigned int xid, return smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb, co, FILE_READ_ATTRIBUTES, - SMB2_OP_HARDLINK, NULL); + SMB2_OP_HARDLINK, NULL, NULL); } int smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, const char *full_path, __u64 size, - struct cifs_sb_info *cifs_sb, bool set_alloc) + struct cifs_sb_info *cifs_sb, bool set_alloc, + struct dentry *dentry) { + struct cifs_open_parms oparms; struct cifsFileInfo *cfile; struct kvec in_iov; __le64 eof = cpu_to_le64(size); + int rc; in_iov.iov_base = &eof; in_iov.iov_len = sizeof(eof); cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); - return smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_WRITE_DATA, FILE_OPEN, - 0, ACL_NO_MODE, &in_iov, - &(int){SMB2_OP_SET_EOF}, 1, - cfile, NULL, NULL); + + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_DATA, + FILE_OPEN, 0, ACL_NO_MODE); + rc = smb2_compound_op(xid, tcon, cifs_sb, + full_path, &oparms, &in_iov, + &(int){SMB2_OP_SET_EOF}, 1, + cfile, NULL, NULL, dentry); + if (rc == -EINVAL) { + cifs_dbg(FYI, "invalid lease key, resending request without lease"); + rc = smb2_compound_op(xid, tcon, cifs_sb, + full_path, &oparms, &in_iov, + &(int){SMB2_OP_SET_EOF}, 1, + cfile, NULL, NULL, NULL); + } + return rc; } int smb2_set_file_info(struct inode *inode, const char *full_path, FILE_BASIC_INFO *buf, const unsigned int xid) { + struct cifs_open_parms oparms; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct tcon_link *tlink; struct cifs_tcon *tcon; @@ -959,11 +1177,12 @@ smb2_set_file_info(struct inode *inode, const char *full_path, tcon = tlink_tcon(tlink); cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_WRITE_ATTRIBUTES, FILE_OPEN, - 0, ACL_NO_MODE, &in_iov, + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_ATTRIBUTES, + FILE_OPEN, 0, ACL_NO_MODE); + rc = smb2_compound_op(xid, tcon, cifs_sb, + full_path, &oparms, &in_iov, &(int){SMB2_OP_SET_INFO}, 1, - cfile, NULL, NULL); + cfile, NULL, NULL, NULL); cifs_put_tlink(tlink); return rc; } @@ -973,32 +1192,37 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data, const unsigned int xid, struct cifs_tcon *tcon, const char *full_path, - struct kvec *iov) + struct kvec *reparse_iov, + struct kvec *xattr_iov) { + struct cifs_open_parms oparms; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifsFileInfo *cfile; struct inode *new = NULL; struct kvec in_iov[2]; int cmds[2]; - int da, co, cd; int rc; - da = SYNCHRONIZE | DELETE | - FILE_READ_ATTRIBUTES | - FILE_WRITE_ATTRIBUTES; - co = CREATE_NOT_DIR | OPEN_REPARSE_POINT; - cd = FILE_CREATE; + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, + SYNCHRONIZE | DELETE | + FILE_READ_ATTRIBUTES | + FILE_WRITE_ATTRIBUTES, + FILE_CREATE, + CREATE_NOT_DIR | OPEN_REPARSE_POINT, + ACL_NO_MODE); + if (xattr_iov) + oparms.ea_cctx = xattr_iov; + cmds[0] = SMB2_OP_SET_REPARSE; - in_iov[0] = *iov; + in_iov[0] = *reparse_iov; in_iov[1].iov_base = data; in_iov[1].iov_len = sizeof(*data); if (tcon->posix_extensions) { cmds[1] = SMB2_OP_POSIX_QUERY_INFO; cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - da, cd, co, ACL_NO_MODE, in_iov, - cmds, 2, cfile, NULL, NULL); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, + in_iov, cmds, 2, cfile, NULL, NULL, NULL); if (!rc) { rc = smb311_posix_get_inode_info(&new, full_path, data, sb, xid); @@ -1006,9 +1230,8 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data, } else { cmds[1] = SMB2_OP_QUERY_INFO; cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - da, cd, co, ACL_NO_MODE, in_iov, - cmds, 2, cfile, NULL, NULL); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, + in_iov, cmds, 2, cfile, NULL, NULL, NULL); if (!rc) { rc = cifs_get_inode_info(&new, full_path, data, sb, xid, NULL); @@ -1024,6 +1247,7 @@ int smb2_query_reparse_point(const unsigned int xid, u32 *tag, struct kvec *rsp, int *rsp_buftype) { + struct cifs_open_parms oparms; struct cifs_open_info_data data = {}; struct cifsFileInfo *cfile; struct kvec in_iov = { .iov_base = &data, .iov_len = sizeof(data), }; @@ -1032,11 +1256,12 @@ int smb2_query_reparse_point(const unsigned int xid, cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); cifs_get_readable_path(tcon, full_path, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, - OPEN_REPARSE_POINT, ACL_NO_MODE, &in_iov, + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_READ_ATTRIBUTES, + FILE_OPEN, OPEN_REPARSE_POINT, ACL_NO_MODE); + rc = smb2_compound_op(xid, tcon, cifs_sb, + full_path, &oparms, &in_iov, &(int){SMB2_OP_GET_REPARSE}, 1, - cfile, NULL, NULL); + cfile, NULL, NULL, NULL); if (rc) goto out; diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 82b84a4941dd..677ef6f99a5b 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -622,6 +622,8 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); cifs_stats_inc( @@ -697,6 +699,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); @@ -763,7 +767,7 @@ smb2_cancelled_close_fid(struct work_struct *work) if (rc) cifs_tcon_dbg(VFS, "Close cancelled mid failed rc:%d\n", rc); - cifs_put_tcon(tcon); + cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cancelled_close_fid); kfree(cancelled); } @@ -807,6 +811,8 @@ smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid, if (tcon->tc_count <= 0) { struct TCP_Server_Info *server = NULL; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_see_cancelled_close); WARN_ONCE(tcon->tc_count < 0, "tcon refcount is negative"); spin_unlock(&cifs_tcp_ses_lock); @@ -819,12 +825,14 @@ smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid, return 0; } tcon->tc_count++; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_get_cancelled_close); spin_unlock(&cifs_tcp_ses_lock); rc = __smb2_handle_cancelled_cmd(tcon, SMB2_CLOSE_HE, 0, persistent_fid, volatile_fid); if (rc) - cifs_put_tcon(tcon); + cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cancelled_close); return rc; } @@ -852,7 +860,7 @@ smb2_handle_cancelled_mid(struct mid_q_entry *mid, struct TCP_Server_Info *serve rsp->PersistentFileId, rsp->VolatileFileId); if (rc) - cifs_put_tcon(tcon); + cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cancelled_mid); return rc; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 4695433fcf39..4ce6c3121a7e 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -28,6 +28,7 @@ #include "fscache.h" #include "fs_context.h" #include "cached_dir.h" +#include "reparse.h" /* Change credits for different ops and return the total number of credits */ static int @@ -216,8 +217,8 @@ smb2_get_credits(struct mid_q_entry *mid) } static int -smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, - unsigned int *num, struct cifs_credits *credits) +smb2_wait_mtu_credits(struct TCP_Server_Info *server, size_t size, + size_t *num, struct cifs_credits *credits) { int rc = 0; unsigned int scredits, in_flight; @@ -1411,14 +1412,14 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) memcpy(cfile->fid.create_guid, fid->create_guid, 16); } -static void +static int smb2_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); + return SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); } -static void +static int smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *cfile) { @@ -1429,7 +1430,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, rc = __SMB2_close(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, &file_inf); if (rc) - return; + return rc; inode = d_inode(cfile->dentry); @@ -1458,6 +1459,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, /* End of file and Attributes should not have to be updated on close */ spin_unlock(&inode->i_lock); + return rc; } static int @@ -2026,6 +2028,7 @@ smb2_duplicate_extents(const unsigned int xid, * size will be queried on next revalidate, but it is important * to make sure that file's cached size is updated immediately */ + netfs_resize_file(netfs_inode(inode), dest_off + len, true); cifs_setsize(inode, dest_off + len); } rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, @@ -2479,6 +2482,8 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) { spin_lock(&tcon->tc_lock); @@ -2911,8 +2916,11 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, tcon = list_first_entry_or_null(&ses->tcon_list, struct cifs_tcon, tcon_list); - if (tcon) + if (tcon) { tcon->tc_count++; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_get_dfs_refer); + } spin_unlock(&cifs_tcp_ses_lock); } @@ -2976,6 +2984,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, /* ipc tcons are not refcounted */ spin_lock(&cifs_tcp_ses_lock); tcon->tc_count--; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_dec_dfs_refer); /* tc_count can never go negative */ WARN_ON(tcon->tc_count < 0); spin_unlock(&cifs_tcp_ses_lock); @@ -2986,109 +2996,6 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, return rc; } -/* See MS-FSCC 2.1.2.6 for the 'NFS' style reparse tags */ -static int parse_reparse_posix(struct reparse_posix_data *buf, - struct cifs_sb_info *cifs_sb, - struct cifs_open_info_data *data) -{ - unsigned int len; - u64 type; - - switch ((type = le64_to_cpu(buf->InodeType))) { - case NFS_SPECFILE_LNK: - len = le16_to_cpu(buf->ReparseDataLength); - data->symlink_target = cifs_strndup_from_utf16(buf->DataBuffer, - len, true, - cifs_sb->local_nls); - if (!data->symlink_target) - return -ENOMEM; - convert_delimiter(data->symlink_target, '/'); - cifs_dbg(FYI, "%s: target path: %s\n", - __func__, data->symlink_target); - break; - case NFS_SPECFILE_CHR: - case NFS_SPECFILE_BLK: - case NFS_SPECFILE_FIFO: - case NFS_SPECFILE_SOCK: - break; - default: - cifs_dbg(VFS, "%s: unhandled inode type: 0x%llx\n", - __func__, type); - return -EOPNOTSUPP; - } - return 0; -} - -static int parse_reparse_symlink(struct reparse_symlink_data_buffer *sym, - u32 plen, bool unicode, - struct cifs_sb_info *cifs_sb, - struct cifs_open_info_data *data) -{ - unsigned int len; - unsigned int offs; - - /* We handle Symbolic Link reparse tag here. See: MS-FSCC 2.1.2.4 */ - - offs = le16_to_cpu(sym->SubstituteNameOffset); - len = le16_to_cpu(sym->SubstituteNameLength); - if (offs + 20 > plen || offs + len + 20 > plen) { - cifs_dbg(VFS, "srv returned malformed symlink buffer\n"); - return -EIO; - } - - data->symlink_target = cifs_strndup_from_utf16(sym->PathBuffer + offs, - len, unicode, - cifs_sb->local_nls); - if (!data->symlink_target) - return -ENOMEM; - - convert_delimiter(data->symlink_target, '/'); - cifs_dbg(FYI, "%s: target path: %s\n", __func__, data->symlink_target); - - return 0; -} - -int parse_reparse_point(struct reparse_data_buffer *buf, - u32 plen, struct cifs_sb_info *cifs_sb, - bool unicode, struct cifs_open_info_data *data) -{ - data->reparse.buf = buf; - - /* See MS-FSCC 2.1.2 */ - switch (le32_to_cpu(buf->ReparseTag)) { - case IO_REPARSE_TAG_NFS: - return parse_reparse_posix((struct reparse_posix_data *)buf, - cifs_sb, data); - case IO_REPARSE_TAG_SYMLINK: - return parse_reparse_symlink( - (struct reparse_symlink_data_buffer *)buf, - plen, unicode, cifs_sb, data); - case IO_REPARSE_TAG_LX_SYMLINK: - case IO_REPARSE_TAG_AF_UNIX: - case IO_REPARSE_TAG_LX_FIFO: - case IO_REPARSE_TAG_LX_CHR: - case IO_REPARSE_TAG_LX_BLK: - return 0; - default: - cifs_dbg(VFS, "%s: unhandled reparse tag: 0x%08x\n", - __func__, le32_to_cpu(buf->ReparseTag)); - return -EOPNOTSUPP; - } -} - -static int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb, - struct kvec *rsp_iov, - struct cifs_open_info_data *data) -{ - struct reparse_data_buffer *buf; - struct smb2_ioctl_rsp *io = rsp_iov->iov_base; - u32 plen = le32_to_cpu(io->OutputCount); - - buf = (struct reparse_data_buffer *)((u8 *)io + - le32_to_cpu(io->OutputOffset)); - return parse_reparse_point(buf, plen, cifs_sb, true, data); -} - static struct cifs_ntsd * get_smb2_acl_by_fid(struct cifs_sb_info *cifs_sb, const struct cifs_fid *cifsfid, u32 *pacllen, u32 info) @@ -3730,6 +3637,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); if (rc < 0) goto out_2; + cifsi->netfs.zero_point = new_eof; rc = smb3_zero_data(file, tcon, off, len, xid); if (rc < 0) @@ -4015,7 +3923,7 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, strcat(message, "W"); } if (!new_oplock) - strncpy(message, "None", sizeof(message)); + strscpy(message, "None"); cinode->oplock = new_oplock; cifs_dbg(FYI, "%s Lease granted on inode %p\n", message, @@ -4584,7 +4492,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, unsigned int cur_off; unsigned int cur_page_idx; unsigned int pad_len; - struct cifs_readdata *rdata = mid->callback_data; + struct cifs_io_subrequest *rdata = mid->callback_data; struct smb2_hdr *shdr = (struct smb2_hdr *)buf; int length; bool use_rdma_mr = false; @@ -4686,7 +4594,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, /* Copy the data to the output I/O iterator. */ rdata->result = cifs_copy_pages_to_iter(pages, pages_len, - cur_off, &rdata->iter); + cur_off, &rdata->subreq.io_iter); if (rdata->result != 0) { if (is_offloaded) mid->mid_state = MID_RESPONSE_MALFORMED; @@ -4700,7 +4608,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, /* read response payload is in buf */ WARN_ONCE(pages && !xa_empty(pages), "read data can be either in buf or in pages"); - length = copy_to_iter(buf + data_offset, data_len, &rdata->iter); + length = copy_to_iter(buf + data_offset, data_len, &rdata->subreq.io_iter); if (length < 0) return length; rdata->got_bytes = data_len; @@ -5063,214 +4971,84 @@ static int smb2_next_header(struct TCP_Server_Info *server, char *buf, return 0; } -int cifs_sfu_make_node(unsigned int xid, struct inode *inode, - struct dentry *dentry, struct cifs_tcon *tcon, - const char *full_path, umode_t mode, dev_t dev) +static int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev) { - struct cifs_open_info_data buf = {}; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; struct cifs_io_parms io_parms = {}; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_fid fid; unsigned int bytes_written; - struct win_dev *pdev; + struct win_dev pdev = {}; struct kvec iov[2]; __u32 oplock = server->oplocks ? REQ_OPLOCK : 0; int rc; - if (!S_ISCHR(mode) && !S_ISBLK(mode) && !S_ISFIFO(mode)) + switch (mode & S_IFMT) { + case S_IFCHR: + strscpy(pdev.type, "IntxCHR"); + pdev.major = cpu_to_le64(MAJOR(dev)); + pdev.minor = cpu_to_le64(MINOR(dev)); + break; + case S_IFBLK: + strscpy(pdev.type, "IntxBLK"); + pdev.major = cpu_to_le64(MAJOR(dev)); + pdev.minor = cpu_to_le64(MINOR(dev)); + break; + case S_IFIFO: + strscpy(pdev.type, "LnxFIFO"); + break; + default: return -EPERM; + } - oparms = (struct cifs_open_parms) { - .tcon = tcon, - .cifs_sb = cifs_sb, - .desired_access = GENERIC_WRITE, - .create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR | - CREATE_OPTION_SPECIAL), - .disposition = FILE_CREATE, - .path = full_path, - .fid = &fid, - }; + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, GENERIC_WRITE, + FILE_CREATE, CREATE_NOT_DIR | + CREATE_OPTION_SPECIAL, ACL_NO_MODE); + oparms.fid = &fid; - rc = server->ops->open(xid, &oparms, &oplock, &buf); + rc = server->ops->open(xid, &oparms, &oplock, NULL); if (rc) return rc; - /* - * BB Do not bother to decode buf since no local inode yet to put - * timestamps in, but we can reuse it safely. - */ - pdev = (struct win_dev *)&buf.fi; io_parms.pid = current->tgid; io_parms.tcon = tcon; - io_parms.length = sizeof(*pdev); - iov[1].iov_base = pdev; - iov[1].iov_len = sizeof(*pdev); - if (S_ISCHR(mode)) { - memcpy(pdev->type, "IntxCHR", 8); - pdev->major = cpu_to_le64(MAJOR(dev)); - pdev->minor = cpu_to_le64(MINOR(dev)); - } else if (S_ISBLK(mode)) { - memcpy(pdev->type, "IntxBLK", 8); - pdev->major = cpu_to_le64(MAJOR(dev)); - pdev->minor = cpu_to_le64(MINOR(dev)); - } else if (S_ISFIFO(mode)) { - memcpy(pdev->type, "LnxFIFO", 8); - } + io_parms.length = sizeof(pdev); + iov[1].iov_base = &pdev; + iov[1].iov_len = sizeof(pdev); rc = server->ops->sync_write(xid, &fid, &io_parms, &bytes_written, iov, 1); server->ops->close(xid, tcon, &fid); - d_drop(dentry); - /* FIXME: add code here to set EAs */ - cifs_free_open_info(&buf); return rc; } -static inline u64 mode_nfs_type(mode_t mode) -{ - switch (mode & S_IFMT) { - case S_IFBLK: return NFS_SPECFILE_BLK; - case S_IFCHR: return NFS_SPECFILE_CHR; - case S_IFIFO: return NFS_SPECFILE_FIFO; - case S_IFSOCK: return NFS_SPECFILE_SOCK; - } - return 0; -} - -static int nfs_set_reparse_buf(struct reparse_posix_data *buf, - mode_t mode, dev_t dev, - struct kvec *iov) -{ - u64 type; - u16 len, dlen; - - len = sizeof(*buf); - - switch ((type = mode_nfs_type(mode))) { - case NFS_SPECFILE_BLK: - case NFS_SPECFILE_CHR: - dlen = sizeof(__le64); - break; - case NFS_SPECFILE_FIFO: - case NFS_SPECFILE_SOCK: - dlen = 0; - break; - default: - return -EOPNOTSUPP; - } - - buf->ReparseTag = cpu_to_le32(IO_REPARSE_TAG_NFS); - buf->Reserved = 0; - buf->InodeType = cpu_to_le64(type); - buf->ReparseDataLength = cpu_to_le16(len + dlen - - sizeof(struct reparse_data_buffer)); - *(__le64 *)buf->DataBuffer = cpu_to_le64(((u64)MAJOR(dev) << 32) | - MINOR(dev)); - iov->iov_base = buf; - iov->iov_len = len + dlen; - return 0; -} - -static int nfs_make_node(unsigned int xid, struct inode *inode, - struct dentry *dentry, struct cifs_tcon *tcon, - const char *full_path, umode_t mode, dev_t dev) +int cifs_sfu_make_node(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev) { - struct cifs_open_info_data data; - struct reparse_posix_data *p; - struct inode *new; - struct kvec iov; - __u8 buf[sizeof(*p) + sizeof(__le64)]; + struct inode *new = NULL; int rc; - p = (struct reparse_posix_data *)buf; - rc = nfs_set_reparse_buf(p, mode, dev, &iov); + rc = __cifs_sfu_make_node(xid, inode, dentry, tcon, + full_path, mode, dev); if (rc) return rc; - data = (struct cifs_open_info_data) { - .reparse_point = true, - .reparse = { .tag = IO_REPARSE_TAG_NFS, .posix = p, }, - }; - - new = smb2_get_reparse_inode(&data, inode->i_sb, xid, - tcon, full_path, &iov); - if (!IS_ERR(new)) - d_instantiate(dentry, new); - else - rc = PTR_ERR(new); - cifs_free_open_info(&data); - return rc; -} - -static int smb2_create_reparse_symlink(const unsigned int xid, - struct inode *inode, - struct dentry *dentry, - struct cifs_tcon *tcon, - const char *full_path, - const char *symname) -{ - struct reparse_symlink_data_buffer *buf = NULL; - struct cifs_open_info_data data; - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct inode *new; - struct kvec iov; - __le16 *path; - char *sym, sep = CIFS_DIR_SEP(cifs_sb); - u16 len, plen; - int rc = 0; - - sym = kstrdup(symname, GFP_KERNEL); - if (!sym) - return -ENOMEM; - - data = (struct cifs_open_info_data) { - .reparse_point = true, - .reparse = { .tag = IO_REPARSE_TAG_SYMLINK, }, - .symlink_target = sym, - }; - - convert_delimiter(sym, sep); - path = cifs_convert_path_to_utf16(sym, cifs_sb); - if (!path) { - rc = -ENOMEM; - goto out; - } - - plen = 2 * UniStrnlen((wchar_t *)path, PATH_MAX); - len = sizeof(*buf) + plen * 2; - buf = kzalloc(len, GFP_KERNEL); - if (!buf) { - rc = -ENOMEM; - goto out; + if (tcon->posix_extensions) { + rc = smb311_posix_get_inode_info(&new, full_path, NULL, + inode->i_sb, xid); + } else if (tcon->unix_ext) { + rc = cifs_get_inode_info_unix(&new, full_path, + inode->i_sb, xid); + } else { + rc = cifs_get_inode_info(&new, full_path, NULL, + inode->i_sb, xid, NULL); } - - buf->ReparseTag = cpu_to_le32(IO_REPARSE_TAG_SYMLINK); - buf->ReparseDataLength = cpu_to_le16(len - sizeof(struct reparse_data_buffer)); - buf->SubstituteNameOffset = cpu_to_le16(plen); - buf->SubstituteNameLength = cpu_to_le16(plen); - memcpy(&buf->PathBuffer[plen], path, plen); - buf->PrintNameOffset = 0; - buf->PrintNameLength = cpu_to_le16(plen); - memcpy(buf->PathBuffer, path, plen); - buf->Flags = cpu_to_le32(*symname != '/' ? SYMLINK_FLAG_RELATIVE : 0); - if (*sym != sep) - buf->Flags = cpu_to_le32(SYMLINK_FLAG_RELATIVE); - - convert_delimiter(sym, '/'); - iov.iov_base = buf; - iov.iov_len = len; - new = smb2_get_reparse_inode(&data, inode->i_sb, xid, - tcon, full_path, &iov); - if (!IS_ERR(new)) + if (!rc) d_instantiate(dentry, new); - else - rc = PTR_ERR(new); -out: - kfree(path); - cifs_free_open_info(&data); - kfree(buf); return rc; } @@ -5291,8 +5069,8 @@ static int smb2_make_node(unsigned int xid, struct inode *inode, rc = cifs_sfu_make_node(xid, inode, dentry, tcon, full_path, mode, dev); } else { - rc = nfs_make_node(xid, inode, dentry, tcon, - full_path, mode, dev); + rc = smb2_mknod_reparse(xid, inode, dentry, tcon, + full_path, mode, dev); } return rc; } @@ -5538,6 +5316,7 @@ struct smb_version_operations smb30_operations = { .tree_connect = SMB2_tcon, .tree_disconnect = SMB2_tdis, .qfs_tcon = smb3_qfs_tcon, + .query_server_interfaces = SMB3_request_interfaces, .is_path_accessible = smb2_is_path_accessible, .can_echo = smb2_can_echo, .echo = SMB2_echo, @@ -5653,6 +5432,7 @@ struct smb_version_operations smb311_operations = { .tree_connect = SMB2_tcon, .tree_disconnect = SMB2_tdis, .qfs_tcon = smb3_qfs_tcon, + .query_server_interfaces = SMB3_request_interfaces, .is_path_accessible = smb2_is_path_accessible, .can_echo = smb2_can_echo, .echo = SMB2_echo, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 608ee05491e2..993ac36c3d58 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -23,6 +23,8 @@ #include <linux/uuid.h> #include <linux/pagemap.h> #include <linux/xattr.h> +#include <linux/netfs.h> +#include <trace/events/netfs.h> #include "cifsglob.h" #include "cifsacl.h" #include "cifsproto.h" @@ -367,6 +369,17 @@ again: } rc = cifs_setup_session(0, ses, server, nls_codepage); + if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED)) { + /* + * Try alternate password for next reconnect (key rotation + * could be enabled on the server e.g.) if an alternate + * password is available and the current password is expired, + * but do not swap on non pwd related errors like host down + */ + if (ses->password2) + swap(ses->password2, ses->password); + } + if ((rc == -EACCES) && !tcon->retry) { mutex_unlock(&ses->session_mutex); rc = -EHOSTDOWN; @@ -409,14 +422,15 @@ skip_sess_setup: spin_unlock(&ses->ses_lock); if (!rc && - (server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { + (server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL) && + server->ops->query_server_interfaces) { mutex_unlock(&ses->session_mutex); /* * query server network interfaces, in case they change */ xid = get_xid(); - rc = SMB3_request_interfaces(xid, tcon, false); + rc = server->ops->query_server_interfaces(xid, tcon, false); free_xid(xid); if (rc == -EOPNOTSUPP && ses->chan_count > 1) { @@ -731,7 +745,7 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, pneg_ctxt += sizeof(struct smb2_posix_neg_context); neg_context_count++; - if (server->compress_algorithm) { + if (server->compression.requested) { build_compression_ctxt((struct smb2_compression_capabilities_context *) pneg_ctxt); ctxt_len = ALIGN(sizeof(struct smb2_compression_capabilities_context), 8); @@ -779,6 +793,9 @@ static void decode_compress_ctx(struct TCP_Server_Info *server, struct smb2_compression_capabilities_context *ctxt) { unsigned int len = le16_to_cpu(ctxt->DataLength); + __le16 alg; + + server->compression.enabled = false; /* * Caller checked that DataLength remains within SMB boundary. We still @@ -789,15 +806,22 @@ static void decode_compress_ctx(struct TCP_Server_Info *server, pr_warn_once("server sent bad compression cntxt\n"); return; } + if (le16_to_cpu(ctxt->CompressionAlgorithmCount) != 1) { - pr_warn_once("Invalid SMB3 compress algorithm count\n"); + pr_warn_once("invalid SMB3 compress algorithm count\n"); return; } - if (le16_to_cpu(ctxt->CompressionAlgorithms[0]) > 3) { - pr_warn_once("unknown compression algorithm\n"); + + alg = ctxt->CompressionAlgorithms[0]; + + /* 'NONE' (0) compressor type is never negotiated */ + if (alg == 0 || le16_to_cpu(alg) > 3) { + pr_warn_once("invalid compression algorithm '%u'\n", alg); return; } - server->compress_algorithm = ctxt->CompressionAlgorithms[0]; + + server->compression.alg = alg; + server->compression.enabled = true; } static int decode_encrypt_ctx(struct TCP_Server_Info *server, @@ -1536,6 +1560,11 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data) &sess_data->buf0_type, CIFS_LOG_ERROR | CIFS_SESS_OP, &rsp_iov); cifs_small_buf_release(sess_data->iov[0].iov_base); + if (rc == 0) + sess_data->ses->expired_pwd = false; + else if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED)) + sess_data->ses->expired_pwd = true; + memcpy(&sess_data->iov[0], &rsp_iov, sizeof(struct kvec)); return rc; @@ -2715,6 +2744,17 @@ add_query_id_context(struct kvec *iov, unsigned int *num_iovec) return 0; } +static void add_ea_context(struct cifs_open_parms *oparms, + struct kvec *rq_iov, unsigned int *num_iovs) +{ + struct kvec *iov = oparms->ea_cctx; + + if (iov && iov->iov_base && iov->iov_len) { + rq_iov[(*num_iovs)++] = *iov; + memset(iov, 0, sizeof(*iov)); + } +} + static int alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len, const char *treename, const __le16 *path) @@ -3081,6 +3121,7 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, } add_query_id_context(iov, &n_iov); + add_ea_context(oparms, iov, &n_iov); if (n_iov > 2) { /* @@ -3600,9 +3641,9 @@ replay_again: memcpy(&pbuf->network_open_info, &rsp->network_open_info, sizeof(pbuf->network_open_info)); + atomic_dec(&tcon->num_remote_opens); } - atomic_dec(&tcon->num_remote_opens); close_exit: SMB2_close_free(&rqst); free_rsp_buf(resp_buftype, rsp); @@ -4099,6 +4140,8 @@ void smb2_reconnect_server(struct work_struct *work) list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->need_reconnect || tcon->need_reopen_files) { tcon->tc_count++; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_get_reconnect_server); list_add_tail(&tcon->rlist, &tmp_list); tcon_selected = true; } @@ -4137,14 +4180,14 @@ void smb2_reconnect_server(struct work_struct *work) if (tcon->ipc) cifs_put_smb_ses(tcon->ses); else - cifs_put_tcon(tcon); + cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_reconnect_server); } if (!ses_exist) goto done; /* allocate a dummy tcon struct used for reconnect */ - tcon = tcon_info_alloc(false); + tcon = tcon_info_alloc(false, netfs_trace_tcon_ref_new_reconnect_server); if (!tcon) { resched = true; list_for_each_entry_safe(ses, ses2, &tmp_ses_list, rlist) { @@ -4167,7 +4210,7 @@ void smb2_reconnect_server(struct work_struct *work) list_del_init(&ses->rlist); cifs_put_smb_ses(ses); } - tconInfoFree(tcon); + tconInfoFree(tcon, netfs_trace_tcon_ref_free_reconnect_server); done: cifs_dbg(FYI, "Reconnecting tcons and channels finished\n"); @@ -4350,7 +4393,7 @@ static inline bool smb3_use_rdma_offload(struct cifs_io_parms *io_parms) */ static int smb2_new_read_req(void **buf, unsigned int *total_len, - struct cifs_io_parms *io_parms, struct cifs_readdata *rdata, + struct cifs_io_parms *io_parms, struct cifs_io_subrequest *rdata, unsigned int remaining_bytes, int request_type) { int rc = -EACCES; @@ -4378,10 +4421,12 @@ smb2_new_read_req(void **buf, unsigned int *total_len, req->Length = cpu_to_le32(io_parms->length); req->Offset = cpu_to_le64(io_parms->offset); - trace_smb3_read_enter(0 /* xid */, - io_parms->persistent_fid, - io_parms->tcon->tid, io_parms->tcon->ses->Suid, - io_parms->offset, io_parms->length); + trace_smb3_read_enter(rdata ? rdata->rreq->debug_id : 0, + rdata ? rdata->subreq.debug_index : 0, + rdata ? rdata->xid : 0, + io_parms->persistent_fid, + io_parms->tcon->tid, io_parms->tcon->ses->Suid, + io_parms->offset, io_parms->length); #ifdef CONFIG_CIFS_SMB_DIRECT /* * If we want to do a RDMA write, fill in and append @@ -4391,7 +4436,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len, struct smbd_buffer_descriptor_v1 *v1; bool need_invalidate = server->dialect == SMB30_PROT_ID; - rdata->mr = smbd_register_mr(server->smbd_conn, &rdata->iter, + rdata->mr = smbd_register_mr(server->smbd_conn, &rdata->subreq.io_iter, true, need_invalidate); if (!rdata->mr) return -EAGAIN; @@ -4442,8 +4487,8 @@ smb2_new_read_req(void **buf, unsigned int *total_len, static void smb2_readv_callback(struct mid_q_entry *mid) { - struct cifs_readdata *rdata = mid->callback_data; - struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink); + struct cifs_io_subrequest *rdata = mid->callback_data; + struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); struct TCP_Server_Info *server = rdata->server; struct smb2_hdr *shdr = (struct smb2_hdr *)rdata->iov[0].iov_base; @@ -4451,17 +4496,17 @@ smb2_readv_callback(struct mid_q_entry *mid) struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], .rq_nvec = 1 }; if (rdata->got_bytes) { - rqst.rq_iter = rdata->iter; - rqst.rq_iter_size = iov_iter_count(&rdata->iter); + rqst.rq_iter = rdata->subreq.io_iter; + rqst.rq_iter_size = iov_iter_count(&rdata->subreq.io_iter); } WARN_ONCE(rdata->server != mid->server, "rdata server %p != mid server %p", rdata->server, mid->server); - cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%u\n", + cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n", __func__, mid->mid, mid->mid_state, rdata->result, - rdata->bytes); + rdata->subreq.len); switch (mid->mid_state) { case MID_RESPONSE_RECEIVED: @@ -4471,7 +4516,6 @@ smb2_readv_callback(struct mid_q_entry *mid) if (server->sign && !mid->decrypted) { int rc; - iov_iter_revert(&rqst.rq_iter, rdata->got_bytes); iov_iter_truncate(&rqst.rq_iter, rdata->got_bytes); rc = smb2_verify_signature(&rqst, server); if (rc) @@ -4512,24 +4556,40 @@ smb2_readv_callback(struct mid_q_entry *mid) #endif if (rdata->result && rdata->result != -ENODATA) { cifs_stats_fail_inc(tcon, SMB2_READ_HE); - trace_smb3_read_err(0 /* xid */, - rdata->cfile->fid.persistent_fid, - tcon->tid, tcon->ses->Suid, rdata->offset, - rdata->bytes, rdata->result); + trace_smb3_read_err(rdata->rreq->debug_id, + rdata->subreq.debug_index, + rdata->xid, + rdata->req->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, rdata->subreq.start, + rdata->subreq.len, rdata->result); } else - trace_smb3_read_done(0 /* xid */, - rdata->cfile->fid.persistent_fid, + trace_smb3_read_done(rdata->rreq->debug_id, + rdata->subreq.debug_index, + rdata->xid, + rdata->req->cfile->fid.persistent_fid, tcon->tid, tcon->ses->Suid, - rdata->offset, rdata->got_bytes); + rdata->subreq.start, rdata->got_bytes); - queue_work(cifsiod_wq, &rdata->work); + if (rdata->result == -ENODATA) { + /* We may have got an EOF error because fallocate + * failed to enlarge the file. + */ + if (rdata->subreq.start < rdata->subreq.rreq->i_size) + rdata->result = 0; + } + if (rdata->result == 0 || rdata->result == -EAGAIN) + iov_iter_advance(&rdata->subreq.io_iter, rdata->got_bytes); + rdata->credits.value = 0; + netfs_subreq_terminated(&rdata->subreq, + (rdata->result == 0 || rdata->result == -EAGAIN) ? + rdata->got_bytes : rdata->result, true); release_mid(mid); add_credits(server, &credits, 0); } /* smb2_async_readv - send an async read, and set up mid to handle result */ int -smb2_async_readv(struct cifs_readdata *rdata) +smb2_async_readv(struct cifs_io_subrequest *rdata) { int rc, flags = 0; char *buf; @@ -4538,22 +4598,22 @@ smb2_async_readv(struct cifs_readdata *rdata) struct smb_rqst rqst = { .rq_iov = rdata->iov, .rq_nvec = 1 }; struct TCP_Server_Info *server; - struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink); + struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); unsigned int total_len; int credit_request; - cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n", - __func__, rdata->offset, rdata->bytes); + cifs_dbg(FYI, "%s: offset=%llu bytes=%zu\n", + __func__, rdata->subreq.start, rdata->subreq.len); if (!rdata->server) rdata->server = cifs_pick_channel(tcon->ses); - io_parms.tcon = tlink_tcon(rdata->cfile->tlink); + io_parms.tcon = tlink_tcon(rdata->req->cfile->tlink); io_parms.server = server = rdata->server; - io_parms.offset = rdata->offset; - io_parms.length = rdata->bytes; - io_parms.persistent_fid = rdata->cfile->fid.persistent_fid; - io_parms.volatile_fid = rdata->cfile->fid.volatile_fid; + io_parms.offset = rdata->subreq.start; + io_parms.length = rdata->subreq.len; + io_parms.persistent_fid = rdata->req->cfile->fid.persistent_fid; + io_parms.volatile_fid = rdata->req->cfile->fid.volatile_fid; io_parms.pid = rdata->pid; rc = smb2_new_read_req( @@ -4570,7 +4630,7 @@ smb2_async_readv(struct cifs_readdata *rdata) shdr = (struct smb2_hdr *)buf; if (rdata->credits.value > 0) { - shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes, + shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->subreq.len, SMB2_MAX_BUFFER_SIZE)); credit_request = le16_to_cpu(shdr->CreditCharge) + 8; if (server->credits >= server->max_credits) @@ -4580,22 +4640,22 @@ smb2_async_readv(struct cifs_readdata *rdata) min_t(int, server->max_credits - server->credits, credit_request)); - rc = adjust_credits(server, &rdata->credits, rdata->bytes); + rc = adjust_credits(server, &rdata->credits, rdata->subreq.len); if (rc) goto async_readv_out; flags |= CIFS_HAS_CREDITS; } - kref_get(&rdata->refcount); rc = cifs_call_async(server, &rqst, cifs_readv_receive, smb2_readv_callback, smb3_handle_read_data, rdata, flags, &rdata->credits); if (rc) { - kref_put(&rdata->refcount, cifs_readdata_release); cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE); - trace_smb3_read_err(0 /* xid */, io_parms.persistent_fid, + trace_smb3_read_err(rdata->rreq->debug_id, + rdata->subreq.debug_index, + rdata->xid, io_parms.persistent_fid, io_parms.tcon->tid, io_parms.tcon->ses->Suid, io_parms.offset, io_parms.length, rc); @@ -4646,22 +4706,23 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, if (rc != -ENODATA) { cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE); cifs_dbg(VFS, "Send error in read = %d\n", rc); - trace_smb3_read_err(xid, + trace_smb3_read_err(0, 0, xid, req->PersistentFileId, io_parms->tcon->tid, ses->Suid, io_parms->offset, io_parms->length, rc); } else - trace_smb3_read_done(xid, req->PersistentFileId, io_parms->tcon->tid, + trace_smb3_read_done(0, 0, xid, + req->PersistentFileId, io_parms->tcon->tid, ses->Suid, io_parms->offset, 0); free_rsp_buf(resp_buftype, rsp_iov.iov_base); cifs_small_buf_release(req); return rc == -ENODATA ? 0 : rc; } else - trace_smb3_read_done(xid, - req->PersistentFileId, - io_parms->tcon->tid, ses->Suid, - io_parms->offset, io_parms->length); + trace_smb3_read_done(0, 0, xid, + req->PersistentFileId, + io_parms->tcon->tid, ses->Suid, + io_parms->offset, io_parms->length); cifs_small_buf_release(req); @@ -4694,12 +4755,13 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, static void smb2_writev_callback(struct mid_q_entry *mid) { - struct cifs_writedata *wdata = mid->callback_data; - struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink); + struct cifs_io_subrequest *wdata = mid->callback_data; + struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink); struct TCP_Server_Info *server = wdata->server; - unsigned int written; struct smb2_write_rsp *rsp = (struct smb2_write_rsp *)mid->resp_buf; struct cifs_credits credits = { .value = 0, .instance = 0 }; + ssize_t result = 0; + size_t written; WARN_ONCE(wdata->server != mid->server, "wdata server %p != mid server %p", @@ -4709,8 +4771,8 @@ smb2_writev_callback(struct mid_q_entry *mid) case MID_RESPONSE_RECEIVED: credits.value = le16_to_cpu(rsp->hdr.CreditRequest); credits.instance = server->reconnect_instance; - wdata->result = smb2_check_receive(mid, server, 0); - if (wdata->result != 0) + result = smb2_check_receive(mid, server, 0); + if (result != 0) break; written = le32_to_cpu(rsp->DataLength); @@ -4720,24 +4782,25 @@ smb2_writev_callback(struct mid_q_entry *mid) * client. OS/2 servers are known to set incorrect * CountHigh values. */ - if (written > wdata->bytes) + if (written > wdata->subreq.len) written &= 0xFFFF; - if (written < wdata->bytes) + if (written < wdata->subreq.len) wdata->result = -ENOSPC; else - wdata->bytes = written; + wdata->subreq.len = written; + iov_iter_advance(&wdata->subreq.io_iter, written); break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: - wdata->result = -EAGAIN; + result = -EAGAIN; break; case MID_RESPONSE_MALFORMED: credits.value = le16_to_cpu(rsp->hdr.CreditRequest); credits.instance = server->reconnect_instance; fallthrough; default: - wdata->result = -EIO; + result = -EIO; break; } #ifdef CONFIG_CIFS_SMB_DIRECT @@ -4753,44 +4816,44 @@ smb2_writev_callback(struct mid_q_entry *mid) wdata->mr = NULL; } #endif - if (wdata->result) { + if (result) { cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); - trace_smb3_write_err(0 /* no xid */, - wdata->cfile->fid.persistent_fid, - tcon->tid, tcon->ses->Suid, wdata->offset, - wdata->bytes, wdata->result); + trace_smb3_write_err(wdata->xid, + wdata->req->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, wdata->subreq.start, + wdata->subreq.len, wdata->result); if (wdata->result == -ENOSPC) pr_warn_once("Out of space writing to %s\n", tcon->tree_name); } else trace_smb3_write_done(0 /* no xid */, - wdata->cfile->fid.persistent_fid, + wdata->req->cfile->fid.persistent_fid, tcon->tid, tcon->ses->Suid, - wdata->offset, wdata->bytes); + wdata->subreq.start, wdata->subreq.len); - queue_work(cifsiod_wq, &wdata->work); + wdata->credits.value = 0; + cifs_write_subrequest_terminated(wdata, result ?: written, true); release_mid(mid); add_credits(server, &credits, 0); } /* smb2_async_writev - send an async write, and set up mid to handle result */ -int -smb2_async_writev(struct cifs_writedata *wdata, - void (*release)(struct kref *kref)) +void +smb2_async_writev(struct cifs_io_subrequest *wdata) { int rc = -EACCES, flags = 0; struct smb2_write_req *req = NULL; struct smb2_hdr *shdr; - struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink); + struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink); struct TCP_Server_Info *server = wdata->server; struct kvec iov[1]; struct smb_rqst rqst = { }; - unsigned int total_len; + unsigned int total_len, xid = wdata->xid; struct cifs_io_parms _io_parms; struct cifs_io_parms *io_parms = NULL; int credit_request; - if (!wdata->server || wdata->replay) + if (!wdata->server || test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags)) server = wdata->server = cifs_pick_channel(tcon->ses); /* @@ -4800,10 +4863,10 @@ smb2_async_writev(struct cifs_writedata *wdata, _io_parms = (struct cifs_io_parms) { .tcon = tcon, .server = server, - .offset = wdata->offset, - .length = wdata->bytes, - .persistent_fid = wdata->cfile->fid.persistent_fid, - .volatile_fid = wdata->cfile->fid.volatile_fid, + .offset = wdata->subreq.start, + .length = wdata->subreq.len, + .persistent_fid = wdata->req->cfile->fid.persistent_fid, + .volatile_fid = wdata->req->cfile->fid.volatile_fid, .pid = wdata->pid, }; io_parms = &_io_parms; @@ -4811,7 +4874,7 @@ smb2_async_writev(struct cifs_writedata *wdata, rc = smb2_plain_req_init(SMB2_WRITE, tcon, server, (void **) &req, &total_len); if (rc) - return rc; + goto out; if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; @@ -4829,7 +4892,7 @@ smb2_async_writev(struct cifs_writedata *wdata, offsetof(struct smb2_write_req, Buffer)); req->RemainingBytes = 0; - trace_smb3_write_enter(0 /* xid */, + trace_smb3_write_enter(wdata->xid, io_parms->persistent_fid, io_parms->tcon->tid, io_parms->tcon->ses->Suid, @@ -4843,10 +4906,10 @@ smb2_async_writev(struct cifs_writedata *wdata, */ if (smb3_use_rdma_offload(io_parms)) { struct smbd_buffer_descriptor_v1 *v1; - size_t data_size = iov_iter_count(&wdata->iter); + size_t data_size = iov_iter_count(&wdata->subreq.io_iter); bool need_invalidate = server->dialect == SMB30_PROT_ID; - wdata->mr = smbd_register_mr(server->smbd_conn, &wdata->iter, + wdata->mr = smbd_register_mr(server->smbd_conn, &wdata->subreq.io_iter, false, need_invalidate); if (!wdata->mr) { rc = -EAGAIN; @@ -4873,9 +4936,9 @@ smb2_async_writev(struct cifs_writedata *wdata, rqst.rq_iov = iov; rqst.rq_nvec = 1; - rqst.rq_iter = wdata->iter; + rqst.rq_iter = wdata->subreq.io_iter; rqst.rq_iter_size = iov_iter_count(&rqst.rq_iter); - if (wdata->replay) + if (test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags)) smb2_set_replay(server, &rqst); #ifdef CONFIG_CIFS_SMB_DIRECT if (wdata->mr) @@ -4893,7 +4956,7 @@ smb2_async_writev(struct cifs_writedata *wdata, #endif if (wdata->credits.value > 0) { - shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes, + shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->subreq.len, SMB2_MAX_BUFFER_SIZE)); credit_request = le16_to_cpu(shdr->CreditCharge) + 8; if (server->credits >= server->max_credits) @@ -4910,25 +4973,27 @@ smb2_async_writev(struct cifs_writedata *wdata, flags |= CIFS_HAS_CREDITS; } - kref_get(&wdata->refcount); rc = cifs_call_async(server, &rqst, NULL, smb2_writev_callback, NULL, wdata, flags, &wdata->credits); - + /* Can't touch wdata if rc == 0 */ if (rc) { - trace_smb3_write_err(0 /* no xid */, + trace_smb3_write_err(xid, io_parms->persistent_fid, io_parms->tcon->tid, io_parms->tcon->ses->Suid, io_parms->offset, io_parms->length, rc); - kref_put(&wdata->refcount, release); cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); } async_writev_out: cifs_small_buf_release(req); - return rc; +out: + if (rc) { + add_credits_and_wake_if(wdata->server, &wdata->credits, 0); + cifs_write_subrequest_terminated(wdata, rc, true); + } } /* diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h index db08194484e0..5c458ab3b05a 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -117,9 +117,10 @@ struct share_redirect_error_context_rsp { * [4] : posix context * [5] : time warp context * [6] : query id context - * [7] : compound padding + * [7] : create ea context + * [8] : compound padding */ -#define SMB2_CREATE_IOV_SIZE 8 +#define SMB2_CREATE_IOV_SIZE 9 /* * Maximum size of a SMB2_CREATE response is 64 (smb2 header) + @@ -144,7 +145,7 @@ struct durable_context_v2 { } __packed; struct create_durable_v2 { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; struct durable_context_v2 dcontext; } __packed; @@ -166,7 +167,7 @@ struct durable_reconnect_context_v2_rsp { } __packed; struct create_durable_handle_reconnect_v2 { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; struct durable_reconnect_context_v2 dcontext; __u8 Pad[4]; @@ -174,7 +175,7 @@ struct create_durable_handle_reconnect_v2 { /* See MS-SMB2 2.2.13.2.5 */ struct crt_twarp_ctxt { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; __le64 Timestamp; @@ -182,12 +183,12 @@ struct crt_twarp_ctxt { /* See MS-SMB2 2.2.13.2.9 */ struct crt_query_id_ctxt { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; } __packed; struct crt_sd_ctxt { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; struct smb3_sd sd; } __packed; @@ -319,7 +320,7 @@ struct smb2_file_reparse_point_info { } __packed; struct smb2_file_network_open_info { - struct_group(network_open_info, + struct_group_attr(network_open_info, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; @@ -413,4 +414,35 @@ struct smb2_posix_info_parsed { const u8 *name; }; +struct smb2_create_ea_ctx { + struct create_context_hdr ctx; + __u8 name[8]; + struct smb2_file_full_ea_info ea; +} __packed; + +#define SMB2_WSL_XATTR_UID "$LXUID" +#define SMB2_WSL_XATTR_GID "$LXGID" +#define SMB2_WSL_XATTR_MODE "$LXMOD" +#define SMB2_WSL_XATTR_DEV "$LXDEV" +#define SMB2_WSL_XATTR_NAME_LEN 6 +#define SMB2_WSL_NUM_XATTRS 4 + +#define SMB2_WSL_XATTR_UID_SIZE 4 +#define SMB2_WSL_XATTR_GID_SIZE 4 +#define SMB2_WSL_XATTR_MODE_SIZE 4 +#define SMB2_WSL_XATTR_DEV_SIZE 8 + +#define SMB2_WSL_MIN_QUERY_EA_RESP_SIZE \ + (ALIGN((SMB2_WSL_NUM_XATTRS - 1) * \ + (SMB2_WSL_XATTR_NAME_LEN + 1 + \ + sizeof(struct smb2_file_full_ea_info)), 4) + \ + SMB2_WSL_XATTR_NAME_LEN + 1 + sizeof(struct smb2_file_full_ea_info)) + +#define SMB2_WSL_MAX_QUERY_EA_RESP_SIZE \ + (ALIGN(SMB2_WSL_MIN_QUERY_EA_RESP_SIZE + \ + SMB2_WSL_XATTR_UID_SIZE + \ + SMB2_WSL_XATTR_GID_SIZE + \ + SMB2_WSL_XATTR_MODE_SIZE + \ + SMB2_WSL_XATTR_DEV_SIZE, 4)) + #endif /* _SMB2PDU_H */ diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index b3069911e9dd..b208232b12a2 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -61,7 +61,8 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data, const unsigned int xid, struct cifs_tcon *tcon, const char *full_path, - struct kvec *iov); + struct kvec *reparse_iov, + struct kvec *xattr_iov); int smb2_query_reparse_point(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, @@ -75,7 +76,8 @@ int smb2_query_path_info(const unsigned int xid, struct cifs_open_info_data *data); extern int smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, const char *full_path, __u64 size, - struct cifs_sb_info *cifs_sb, bool set_alloc); + struct cifs_sb_info *cifs_sb, bool set_alloc, + struct dentry *dentry); extern int smb2_set_file_info(struct inode *inode, const char *full_path, FILE_BASIC_INFO *buf, const unsigned int xid); extern int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, @@ -91,7 +93,8 @@ extern void smb2_mkdir_setinfo(struct inode *inode, const char *full_path, extern int smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb); extern int smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, - const char *name, struct cifs_sb_info *cifs_sb); + const char *name, struct cifs_sb_info *cifs_sb, + struct dentry *dentry); int smb2_rename_path(const unsigned int xid, struct cifs_tcon *tcon, struct dentry *source_dentry, @@ -207,11 +210,10 @@ extern int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon, extern int SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le64 *uniqueid); -extern int smb2_async_readv(struct cifs_readdata *rdata); +extern int smb2_async_readv(struct cifs_io_subrequest *rdata); extern int SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, unsigned int *nbytes, char **buf, int *buf_type); -extern int smb2_async_writev(struct cifs_writedata *wdata, - void (*release)(struct kref *kref)); +extern void smb2_async_writev(struct cifs_io_subrequest *wdata); extern int SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, unsigned int *nbytes, struct kvec *iov, int n_vec); extern int SMB2_echo(struct TCP_Server_Info *server); @@ -308,5 +310,11 @@ int smb311_posix_query_path_info(const unsigned int xid, int posix_info_parse(const void *beg, const void *end, struct smb2_posix_info_parsed *out); int posix_info_sid_size(const void *beg, const void *end); +int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, const char *symname); +int smb2_make_nfs_node(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev); #endif /* _SMB2PROTO_H */ diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 5a3ca62d2f07..02135a605305 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -189,6 +189,8 @@ smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32 tid) if (tcon->tid != tid) continue; ++tcon->tc_count; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_get_find_sess_tcon); return tcon; } @@ -659,7 +661,7 @@ smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) } spin_unlock(&server->srv_lock); if (!is_binding && !server->session_estab) { - strncpy(shdr->Signature, "BSRSPYL", 8); + strscpy(shdr->Signature, "BSRSPYL"); return 0; } diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 522fa387fcfd..36d47ce59631 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -3,6 +3,9 @@ * Copyright (C) 2018, Microsoft Corporation. * * Author(s): Steve French <stfrench@microsoft.com> + * + * Please use this 3-part article as a reference for writing new tracepoints: + * https://lwn.net/Articles/379903/ */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cifs @@ -15,12 +18,129 @@ #include <linux/inet.h> /* - * Please use this 3-part article as a reference for writing new tracepoints: - * https://lwn.net/Articles/379903/ + * Specify enums for tracing information. */ +#define smb3_tcon_ref_traces \ + EM(netfs_trace_tcon_ref_dec_dfs_refer, "DEC DfsRef") \ + EM(netfs_trace_tcon_ref_free, "FRE ") \ + EM(netfs_trace_tcon_ref_free_fail, "FRE Fail ") \ + EM(netfs_trace_tcon_ref_free_ipc, "FRE Ipc ") \ + EM(netfs_trace_tcon_ref_free_ipc_fail, "FRE Ipc-F ") \ + EM(netfs_trace_tcon_ref_free_reconnect_server, "FRE Reconn") \ + EM(netfs_trace_tcon_ref_get_cancelled_close, "GET Cn-Cls") \ + EM(netfs_trace_tcon_ref_get_dfs_refer, "GET DfsRef") \ + EM(netfs_trace_tcon_ref_get_find, "GET Find ") \ + EM(netfs_trace_tcon_ref_get_find_sess_tcon, "GET FndSes") \ + EM(netfs_trace_tcon_ref_get_reconnect_server, "GET Reconn") \ + EM(netfs_trace_tcon_ref_new, "NEW ") \ + EM(netfs_trace_tcon_ref_new_ipc, "NEW Ipc ") \ + EM(netfs_trace_tcon_ref_new_reconnect_server, "NEW Reconn") \ + EM(netfs_trace_tcon_ref_put_cancelled_close, "PUT Cn-Cls") \ + EM(netfs_trace_tcon_ref_put_cancelled_close_fid, "PUT Cn-Fid") \ + EM(netfs_trace_tcon_ref_put_cancelled_mid, "PUT Cn-Mid") \ + EM(netfs_trace_tcon_ref_put_mnt_ctx, "PUT MntCtx") \ + EM(netfs_trace_tcon_ref_put_reconnect_server, "PUT Reconn") \ + EM(netfs_trace_tcon_ref_put_tlink, "PUT Tlink ") \ + EM(netfs_trace_tcon_ref_see_cancelled_close, "SEE Cn-Cls") \ + EM(netfs_trace_tcon_ref_see_fscache_collision, "SEE FV-CO!") \ + EM(netfs_trace_tcon_ref_see_fscache_okay, "SEE FV-Ok ") \ + EM(netfs_trace_tcon_ref_see_fscache_relinq, "SEE FV-Rlq") \ + E_(netfs_trace_tcon_ref_see_umount, "SEE Umount") + +#undef EM +#undef E_ + +/* + * Define those tracing enums. + */ +#ifndef __SMB3_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __SMB3_DECLARE_TRACE_ENUMS_ONCE_ONLY + +#define EM(a, b) a, +#define E_(a, b) a + +enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte); + +#undef EM +#undef E_ +#endif + +/* + * Export enum symbols via userspace. + */ +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define E_(a, b) TRACE_DEFINE_ENUM(a); + +smb3_tcon_ref_traces; + +#undef EM +#undef E_ + +/* + * Now redefine the EM() and E_() macros to map the enums to the strings that + * will be printed in the output. + */ +#define EM(a, b) { a, b }, +#define E_(a, b) { a, b } /* For logging errors in read or write */ DECLARE_EVENT_CLASS(smb3_rw_err_class, + TP_PROTO(unsigned int rreq_debug_id, + unsigned int rreq_debug_index, + unsigned int xid, + __u64 fid, + __u32 tid, + __u64 sesid, + __u64 offset, + __u32 len, + int rc), + TP_ARGS(rreq_debug_id, rreq_debug_index, + xid, fid, tid, sesid, offset, len, rc), + TP_STRUCT__entry( + __field(unsigned int, rreq_debug_id) + __field(unsigned int, rreq_debug_index) + __field(unsigned int, xid) + __field(__u64, fid) + __field(__u32, tid) + __field(__u64, sesid) + __field(__u64, offset) + __field(__u32, len) + __field(int, rc) + ), + TP_fast_assign( + __entry->rreq_debug_id = rreq_debug_id; + __entry->rreq_debug_index = rreq_debug_index; + __entry->xid = xid; + __entry->fid = fid; + __entry->tid = tid; + __entry->sesid = sesid; + __entry->offset = offset; + __entry->len = len; + __entry->rc = rc; + ), + TP_printk("\tR=%08x[%x] xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d", + __entry->rreq_debug_id, __entry->rreq_debug_index, + __entry->xid, __entry->sesid, __entry->tid, __entry->fid, + __entry->offset, __entry->len, __entry->rc) +) + +#define DEFINE_SMB3_RW_ERR_EVENT(name) \ +DEFINE_EVENT(smb3_rw_err_class, smb3_##name, \ + TP_PROTO(unsigned int rreq_debug_id, \ + unsigned int rreq_debug_index, \ + unsigned int xid, \ + __u64 fid, \ + __u32 tid, \ + __u64 sesid, \ + __u64 offset, \ + __u32 len, \ + int rc), \ + TP_ARGS(rreq_debug_id, rreq_debug_index, xid, fid, tid, sesid, offset, len, rc)) + +DEFINE_SMB3_RW_ERR_EVENT(read_err); + +/* For logging errors in other file I/O ops */ +DECLARE_EVENT_CLASS(smb3_other_err_class, TP_PROTO(unsigned int xid, __u64 fid, __u32 tid, @@ -52,8 +172,8 @@ DECLARE_EVENT_CLASS(smb3_rw_err_class, __entry->offset, __entry->len, __entry->rc) ) -#define DEFINE_SMB3_RW_ERR_EVENT(name) \ -DEFINE_EVENT(smb3_rw_err_class, smb3_##name, \ +#define DEFINE_SMB3_OTHER_ERR_EVENT(name) \ +DEFINE_EVENT(smb3_other_err_class, smb3_##name, \ TP_PROTO(unsigned int xid, \ __u64 fid, \ __u32 tid, \ @@ -63,15 +183,67 @@ DEFINE_EVENT(smb3_rw_err_class, smb3_##name, \ int rc), \ TP_ARGS(xid, fid, tid, sesid, offset, len, rc)) -DEFINE_SMB3_RW_ERR_EVENT(write_err); -DEFINE_SMB3_RW_ERR_EVENT(read_err); -DEFINE_SMB3_RW_ERR_EVENT(query_dir_err); -DEFINE_SMB3_RW_ERR_EVENT(zero_err); -DEFINE_SMB3_RW_ERR_EVENT(falloc_err); +DEFINE_SMB3_OTHER_ERR_EVENT(write_err); +DEFINE_SMB3_OTHER_ERR_EVENT(query_dir_err); +DEFINE_SMB3_OTHER_ERR_EVENT(zero_err); +DEFINE_SMB3_OTHER_ERR_EVENT(falloc_err); /* For logging successful read or write */ DECLARE_EVENT_CLASS(smb3_rw_done_class, + TP_PROTO(unsigned int rreq_debug_id, + unsigned int rreq_debug_index, + unsigned int xid, + __u64 fid, + __u32 tid, + __u64 sesid, + __u64 offset, + __u32 len), + TP_ARGS(rreq_debug_id, rreq_debug_index, + xid, fid, tid, sesid, offset, len), + TP_STRUCT__entry( + __field(unsigned int, rreq_debug_id) + __field(unsigned int, rreq_debug_index) + __field(unsigned int, xid) + __field(__u64, fid) + __field(__u32, tid) + __field(__u64, sesid) + __field(__u64, offset) + __field(__u32, len) + ), + TP_fast_assign( + __entry->rreq_debug_id = rreq_debug_id; + __entry->rreq_debug_index = rreq_debug_index; + __entry->xid = xid; + __entry->fid = fid; + __entry->tid = tid; + __entry->sesid = sesid; + __entry->offset = offset; + __entry->len = len; + ), + TP_printk("R=%08x[%x] xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x", + __entry->rreq_debug_id, __entry->rreq_debug_index, + __entry->xid, __entry->sesid, __entry->tid, __entry->fid, + __entry->offset, __entry->len) +) + +#define DEFINE_SMB3_RW_DONE_EVENT(name) \ +DEFINE_EVENT(smb3_rw_done_class, smb3_##name, \ + TP_PROTO(unsigned int rreq_debug_id, \ + unsigned int rreq_debug_index, \ + unsigned int xid, \ + __u64 fid, \ + __u32 tid, \ + __u64 sesid, \ + __u64 offset, \ + __u32 len), \ + TP_ARGS(rreq_debug_id, rreq_debug_index, xid, fid, tid, sesid, offset, len)) + +DEFINE_SMB3_RW_DONE_EVENT(read_enter); +DEFINE_SMB3_RW_DONE_EVENT(read_done); + +/* For logging successful other op */ +DECLARE_EVENT_CLASS(smb3_other_done_class, TP_PROTO(unsigned int xid, __u64 fid, __u32 tid, @@ -100,8 +272,8 @@ DECLARE_EVENT_CLASS(smb3_rw_done_class, __entry->offset, __entry->len) ) -#define DEFINE_SMB3_RW_DONE_EVENT(name) \ -DEFINE_EVENT(smb3_rw_done_class, smb3_##name, \ +#define DEFINE_SMB3_OTHER_DONE_EVENT(name) \ +DEFINE_EVENT(smb3_other_done_class, smb3_##name, \ TP_PROTO(unsigned int xid, \ __u64 fid, \ __u32 tid, \ @@ -110,16 +282,14 @@ DEFINE_EVENT(smb3_rw_done_class, smb3_##name, \ __u32 len), \ TP_ARGS(xid, fid, tid, sesid, offset, len)) -DEFINE_SMB3_RW_DONE_EVENT(write_enter); -DEFINE_SMB3_RW_DONE_EVENT(read_enter); -DEFINE_SMB3_RW_DONE_EVENT(query_dir_enter); -DEFINE_SMB3_RW_DONE_EVENT(zero_enter); -DEFINE_SMB3_RW_DONE_EVENT(falloc_enter); -DEFINE_SMB3_RW_DONE_EVENT(write_done); -DEFINE_SMB3_RW_DONE_EVENT(read_done); -DEFINE_SMB3_RW_DONE_EVENT(query_dir_done); -DEFINE_SMB3_RW_DONE_EVENT(zero_done); -DEFINE_SMB3_RW_DONE_EVENT(falloc_done); +DEFINE_SMB3_OTHER_DONE_EVENT(write_enter); +DEFINE_SMB3_OTHER_DONE_EVENT(query_dir_enter); +DEFINE_SMB3_OTHER_DONE_EVENT(zero_enter); +DEFINE_SMB3_OTHER_DONE_EVENT(falloc_enter); +DEFINE_SMB3_OTHER_DONE_EVENT(write_done); +DEFINE_SMB3_OTHER_DONE_EVENT(query_dir_done); +DEFINE_SMB3_OTHER_DONE_EVENT(zero_done); +DEFINE_SMB3_OTHER_DONE_EVENT(falloc_done); /* For logging successful set EOF (truncate) */ DECLARE_EVENT_CLASS(smb3_eof_class, @@ -348,7 +518,7 @@ DECLARE_EVENT_CLASS(smb3_inf_compound_enter_class, __entry->xid = xid; __entry->tid = tid; __entry->sesid = sesid; - __assign_str(path, full_path); + __assign_str(path); ), TP_printk("xid=%u sid=0x%llx tid=0x%x path=%s", __entry->xid, __entry->sesid, __entry->tid, @@ -375,6 +545,7 @@ DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(get_reparse_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(delete_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mkdir_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(tdis_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mknod_enter); DECLARE_EVENT_CLASS(smb3_inf_compound_done_class, TP_PROTO(unsigned int xid, @@ -411,10 +582,11 @@ DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_eof_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_info_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_reparse_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(get_reparse_compound_done); +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_wsl_ea_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(delete_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mkdir_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(tdis_done); - +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mknod_done); DECLARE_EVENT_CLASS(smb3_inf_compound_err_class, TP_PROTO(unsigned int xid, @@ -456,9 +628,11 @@ DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_eof_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_info_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_reparse_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(get_reparse_compound_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_wsl_ea_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mkdir_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(delete_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(tdis_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mknod_err); /* * For logging SMB3 Status code and Command for responses which return errors @@ -588,7 +762,7 @@ DECLARE_EVENT_CLASS(smb3_exit_err_class, ), TP_fast_assign( __entry->xid = xid; - __assign_str(func_name, func_name); + __assign_str(func_name); __entry->rc = rc; ), TP_printk("\t%s: xid=%u rc=%d", @@ -641,7 +815,7 @@ DECLARE_EVENT_CLASS(smb3_enter_exit_class, ), TP_fast_assign( __entry->xid = xid; - __assign_str(func_name, func_name); + __assign_str(func_name); ), TP_printk("\t%s: xid=%u", __get_str(func_name), __entry->xid) @@ -678,7 +852,7 @@ DECLARE_EVENT_CLASS(smb3_tcon_class, __entry->xid = xid; __entry->tid = tid; __entry->sesid = sesid; - __assign_str(name, unc_name); + __assign_str(name); __entry->rc = rc; ), TP_printk("xid=%u sid=0x%llx tid=0x%x unc_name=%s rc=%d", @@ -722,7 +896,7 @@ DECLARE_EVENT_CLASS(smb3_open_enter_class, __entry->xid = xid; __entry->tid = tid; __entry->sesid = sesid; - __assign_str(path, full_path); + __assign_str(path); __entry->create_options = create_options; __entry->desired_access = desired_access; ), @@ -924,7 +1098,7 @@ DECLARE_EVENT_CLASS(smb3_connect_class, __entry->conn_id = conn_id; pss = (struct sockaddr_storage *)__entry->dst_addr; *pss = *dst_addr; - __assign_str(hostname, hostname); + __assign_str(hostname); ), TP_printk("conn_id=0x%llx server=%s addr=%pISpsfc", __entry->conn_id, @@ -960,7 +1134,7 @@ DECLARE_EVENT_CLASS(smb3_connect_err_class, __entry->rc = rc; pss = (struct sockaddr_storage *)__entry->dst_addr; *pss = *dst_addr; - __assign_str(hostname, hostname); + __assign_str(hostname); ), TP_printk("rc=%d conn_id=0x%llx server=%s addr=%pISpsfc", __entry->rc, @@ -992,7 +1166,7 @@ DECLARE_EVENT_CLASS(smb3_reconnect_class, TP_fast_assign( __entry->currmid = currmid; __entry->conn_id = conn_id; - __assign_str(hostname, hostname); + __assign_str(hostname); ), TP_printk("conn_id=0x%llx server=%s current_mid=%llu", __entry->conn_id, @@ -1030,6 +1204,38 @@ DEFINE_EVENT(smb3_ses_class, smb3_##name, \ DEFINE_SMB3_SES_EVENT(ses_not_found); +DECLARE_EVENT_CLASS(smb3_ioctl_class, + TP_PROTO(unsigned int xid, + __u64 fid, + unsigned int command), + TP_ARGS(xid, fid, command), + TP_STRUCT__entry( + __field(unsigned int, xid) + __field(__u64, fid) + __field(unsigned int, command) + ), + TP_fast_assign( + __entry->xid = xid; + __entry->fid = fid; + __entry->command = command; + ), + TP_printk("xid=%u fid=0x%llx ioctl cmd=0x%x", + __entry->xid, __entry->fid, __entry->command) +) + +#define DEFINE_SMB3_IOCTL_EVENT(name) \ +DEFINE_EVENT(smb3_ioctl_class, smb3_##name, \ + TP_PROTO(unsigned int xid, \ + __u64 fid, \ + unsigned int command), \ + TP_ARGS(xid, fid, command)) + +DEFINE_SMB3_IOCTL_EVENT(ioctl); + + + + + DECLARE_EVENT_CLASS(smb3_credit_class, TP_PROTO(__u64 currmid, __u64 conn_id, @@ -1049,7 +1255,7 @@ DECLARE_EVENT_CLASS(smb3_credit_class, TP_fast_assign( __entry->currmid = currmid; __entry->conn_id = conn_id; - __assign_str(hostname, hostname); + __assign_str(hostname); __entry->credits = credits; __entry->credits_to_add = credits_to_add; __entry->in_flight = in_flight; @@ -1089,6 +1295,30 @@ DEFINE_SMB3_CREDIT_EVENT(waitff_credits); DEFINE_SMB3_CREDIT_EVENT(overflow_credits); DEFINE_SMB3_CREDIT_EVENT(set_credits); + +TRACE_EVENT(smb3_tcon_ref, + TP_PROTO(unsigned int tcon_debug_id, int ref, + enum smb3_tcon_ref_trace trace), + TP_ARGS(tcon_debug_id, ref, trace), + TP_STRUCT__entry( + __field(unsigned int, tcon) + __field(int, ref) + __field(enum smb3_tcon_ref_trace, trace) + ), + TP_fast_assign( + __entry->tcon = tcon_debug_id; + __entry->ref = ref; + __entry->trace = trace; + ), + TP_printk("TC=%08x %s r=%u", + __entry->tcon, + __print_symbolic(__entry->trace, smb3_tcon_ref_traces), + __entry->ref) + ); + + +#undef EM +#undef E_ #endif /* _CIFS_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 994d70193432..012b9bd06995 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -691,8 +691,8 @@ wait_for_compound_request(struct TCP_Server_Info *server, int num, } int -cifs_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, - unsigned int *num, struct cifs_credits *credits) +cifs_wait_mtu_credits(struct TCP_Server_Info *server, size_t size, + size_t *num, struct cifs_credits *credits) { *num = size; credits->value = 0; @@ -909,12 +909,15 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) list_del_init(&mid->qhead); mid->mid_flags |= MID_DELETED; } + spin_unlock(&server->mid_lock); cifs_server_dbg(VFS, "%s: invalid mid state mid=%llu state=%d\n", __func__, mid->mid, mid->mid_state); rc = -EIO; + goto sync_mid_done; } spin_unlock(&server->mid_lock); +sync_mid_done: release_mid(mid); return rc; } @@ -1057,9 +1060,11 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) index = (uint)atomic_inc_return(&ses->chan_seq); index %= ses->chan_count; } + + server = ses->chans[index].server; spin_unlock(&ses->chan_lock); - return ses->chans[index].server; + return server; } int @@ -1687,7 +1692,7 @@ __cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid, static int cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) { - struct cifs_readdata *rdata = mid->callback_data; + struct cifs_io_subrequest *rdata = mid->callback_data; return __cifs_readv_discard(server, mid, rdata->result); } @@ -1697,13 +1702,13 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) { int length, len; unsigned int data_offset, data_len; - struct cifs_readdata *rdata = mid->callback_data; + struct cifs_io_subrequest *rdata = mid->callback_data; char *buf = server->smallbuf; unsigned int buflen = server->pdu_size + HEADER_PREAMBLE_SIZE(server); bool use_rdma_mr = false; - cifs_dbg(FYI, "%s: mid=%llu offset=%llu bytes=%u\n", - __func__, mid->mid, rdata->offset, rdata->bytes); + cifs_dbg(FYI, "%s: mid=%llu offset=%llu bytes=%zu\n", + __func__, mid->mid, rdata->subreq.start, rdata->subreq.len); /* * read the rest of READ_RSP header (sans Data array), or whatever we @@ -1808,8 +1813,11 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) length = data_len; /* An RDMA read is already done. */ else #endif - length = cifs_read_iter_from_socket(server, &rdata->iter, + { + length = cifs_read_iter_from_socket(server, &rdata->subreq.io_iter, data_len); + iov_iter_revert(&rdata->subreq.io_iter, data_len); + } if (length > 0) rdata->got_bytes += length; server->total_read += length; diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 57f2343164a3..8d10be1fe18a 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -208,38 +208,45 @@ struct smb2_transform_hdr { __le64 SessionId; } __packed; +/* + * These are simplified versions from the spec, as we don't need a fully fledged + * form of both unchained and chained structs. + * + * Moreover, even in chained compressed payloads, the initial compression header + * has the form of the unchained one -- i.e. it never has the + * OriginalPayloadSize field and ::Offset field always represent an offset + * (instead of a length, as it is in the chained header). + * + * See MS-SMB2 2.2.42 for more details. + */ +#define SMB2_COMPRESSION_FLAG_NONE 0x0000 +#define SMB2_COMPRESSION_FLAG_CHAINED 0x0001 -/* See MS-SMB2 2.2.42 */ -struct smb2_compression_transform_hdr_unchained { - __le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */ +struct smb2_compression_hdr { + __le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */ __le32 OriginalCompressedSegmentSize; __le16 CompressionAlgorithm; __le16 Flags; - __le16 Length; /* if chained it is length, else offset */ + __le32 Offset; /* this is the size of the uncompressed SMB2 header below */ + /* uncompressed SMB2 header (READ or WRITE) goes here */ + /* compressed data goes here */ } __packed; -/* See MS-SMB2 2.2.42.1 */ -#define SMB2_COMPRESSION_FLAG_NONE 0x0000 -#define SMB2_COMPRESSION_FLAG_CHAINED 0x0001 - -struct compression_payload_header { +/* + * ... OTOH, set compression payload header to always have OriginalPayloadSize + * as it's easier to pass the struct size minus sizeof(OriginalPayloadSize) + * than to juggle around the header/data memory. + */ +struct smb2_compression_payload_hdr { __le16 CompressionAlgorithm; __le16 Flags; __le32 Length; /* length of compressed playload including field below if present */ - /* __le32 OriginalPayloadSize; */ /* optional, present when LZNT1, LZ77, LZ77+Huffman */ -} __packed; - -/* See MS-SMB2 2.2.42.2 */ -struct smb2_compression_transform_hdr_chained { - __le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */ - __le32 OriginalCompressedSegmentSize; - /* struct compression_payload_header[] */ + __le32 OriginalPayloadSize; /* accounted when LZNT1, LZ77, LZ77+Huffman */ } __packed; -/* See MS-SMB2 2.2.42.2.2 */ -struct compression_pattern_payload_v1 { - __le16 Pattern; - __le16 Reserved1; +struct smb2_compression_pattern_v1 { + __u8 Pattern; + __u8 Reserved1; __le16 Reserved2; __le32 Repetitions; } __packed; @@ -273,15 +280,16 @@ struct smb3_blob_data { #define SE_GROUP_RESOURCE 0x20000000 #define SE_GROUP_LOGON_ID 0xC0000000 -/* struct sid_attr_data is SidData array in BlobData format then le32 Attr */ - struct sid_array_data { __le16 SidAttrCount; /* SidAttrList - array of sid_attr_data structs */ } __packed; -struct luid_attr_data { - +/* struct sid_attr_data is SidData array in BlobData format then le32 Attr */ +struct sid_attr_data { + __le16 BlobSize; + __u8 BlobData[]; + /* __le32 Attr */ } __packed; /* @@ -495,6 +503,7 @@ struct smb2_encryption_neg_context { #define SMB3_COMPRESS_LZ77_HUFF cpu_to_le16(0x0003) /* Pattern scanning algorithm See MS-SMB2 3.1.4.4.1 */ #define SMB3_COMPRESS_PATTERN cpu_to_le16(0x0004) /* Pattern_V1 */ +#define SMB3_COMPRESS_LZ4 cpu_to_le16(0x0005) /* Compression Flags */ #define SMB2_COMPRESSION_CAPABILITIES_FLAG_NONE cpu_to_le32(0x00000000) @@ -702,7 +711,7 @@ struct smb2_close_rsp { __le16 StructureSize; /* 60 */ __le16 Flags; __le32 Reserved; - struct_group(network_open_info, + struct_group_attr(network_open_info, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; @@ -1162,12 +1171,15 @@ struct smb2_server_client_notification { #define SMB2_CREATE_FLAG_REPARSEPOINT 0x01 struct create_context { - __le32 Next; - __le16 NameOffset; - __le16 NameLength; - __le16 Reserved; - __le16 DataOffset; - __le32 DataLength; + /* New members must be added within the struct_group() macro below. */ + __struct_group(create_context_hdr, hdr, __packed, + __le32 Next; + __le16 NameOffset; + __le16 NameLength; + __le16 Reserved; + __le16 DataOffset; + __le32 DataLength; + ); __u8 Buffer[]; } __packed; @@ -1213,7 +1225,7 @@ struct smb2_create_rsp { } __packed; struct create_posix { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[16]; __le32 Mode; __u32 Reserved; @@ -1221,7 +1233,7 @@ struct create_posix { /* See MS-SMB2 2.2.13.2.3 and MS-SMB2 2.2.13.2.4 */ struct create_durable { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; union { __u8 Reserved[16]; @@ -1234,14 +1246,14 @@ struct create_durable { /* See MS-SMB2 2.2.13.2.5 */ struct create_mxac_req { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; __le64 Timestamp; } __packed; /* See MS-SMB2 2.2.14.2.5 */ struct create_mxac_rsp { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; __le32 QueryStatus; __le32 MaximalAccess; @@ -1277,13 +1289,13 @@ struct lease_context_v2 { } __packed; struct create_lease { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; struct lease_context lcontext; } __packed; struct create_lease_v2 { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; struct lease_context_v2 lcontext; __u8 Pad[4]; @@ -1291,7 +1303,7 @@ struct create_lease_v2 { /* See MS-SMB2 2.2.14.2.9 */ struct create_disk_id_rsp { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; __le64 DiskFileId; __le64 VolumeId; @@ -1300,7 +1312,7 @@ struct create_disk_id_rsp { /* See MS-SMB2 2.2.13.2.13 */ struct create_app_inst_id { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[16]; __le32 StructureSize; /* Must be 20 */ __u16 Reserved; @@ -1309,7 +1321,7 @@ struct create_app_inst_id { /* See MS-SMB2 2.2.13.2.15 */ struct create_app_inst_id_vers { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[16]; __le32 StructureSize; /* Must be 24 */ __u16 Reserved; diff --git a/fs/smb/common/smbfsctl.h b/fs/smb/common/smbfsctl.h index edd7fc2a7921..a94d658b88e8 100644 --- a/fs/smb/common/smbfsctl.h +++ b/fs/smb/common/smbfsctl.h @@ -158,12 +158,6 @@ #define IO_REPARSE_TAG_LX_CHR 0x80000025 #define IO_REPARSE_TAG_LX_BLK 0x80000026 -#define IO_REPARSE_TAG_LX_SYMLINK_LE cpu_to_le32(0xA000001D) -#define IO_REPARSE_TAG_AF_UNIX_LE cpu_to_le32(0x80000023) -#define IO_REPARSE_TAG_LX_FIFO_LE cpu_to_le32(0x80000024) -#define IO_REPARSE_TAG_LX_CHR_LE cpu_to_le32(0x80000025) -#define IO_REPARSE_TAG_LX_BLK_LE cpu_to_le32(0x80000026) - /* fsctl flags */ /* If Flags is set to this value, the request is an FSCTL not ioctl request */ #define SMB2_0_IOCTL_IS_FSCTL 0x00000001 diff --git a/fs/smb/server/glob.h b/fs/smb/server/glob.h index 5b8f3e0ebdb3..d528b20b37a8 100644 --- a/fs/smb/server/glob.h +++ b/fs/smb/server/glob.h @@ -12,8 +12,6 @@ #include "unicode.h" #include "vfs_cache.h" -#define KSMBD_VERSION "3.4.2" - extern int ksmbd_debug_types; #define KSMBD_DEBUG_SMB BIT(0) diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index 0ebf91ffa236..f4e55199938d 100644 --- a/fs/smb/server/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h @@ -75,6 +75,7 @@ struct ksmbd_heartbeat { #define KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION BIT(1) #define KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL BIT(2) #define KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF BIT(3) +#define KSMBD_GLOBAL_FLAG_DURABLE_HANDLE BIT(4) /* * IPC request for ksmbd server startup @@ -166,7 +167,8 @@ struct ksmbd_share_config_response { __u16 force_uid; __u16 force_gid; __s8 share_name[KSMBD_REQ_MAX_SHARE_NAME]; - __u32 reserved[112]; /* Reserved room */ + __u32 reserved[111]; /* Reserved room */ + __u32 payload_sz; __u32 veto_list_sz; __s8 ____payload[]; }; @@ -338,23 +340,24 @@ enum KSMBD_TREE_CONN_STATUS { /* * Share config flags. */ -#define KSMBD_SHARE_FLAG_INVALID (0) -#define KSMBD_SHARE_FLAG_AVAILABLE BIT(0) -#define KSMBD_SHARE_FLAG_BROWSEABLE BIT(1) -#define KSMBD_SHARE_FLAG_WRITEABLE BIT(2) -#define KSMBD_SHARE_FLAG_READONLY BIT(3) -#define KSMBD_SHARE_FLAG_GUEST_OK BIT(4) -#define KSMBD_SHARE_FLAG_GUEST_ONLY BIT(5) -#define KSMBD_SHARE_FLAG_STORE_DOS_ATTRS BIT(6) -#define KSMBD_SHARE_FLAG_OPLOCKS BIT(7) -#define KSMBD_SHARE_FLAG_PIPE BIT(8) -#define KSMBD_SHARE_FLAG_HIDE_DOT_FILES BIT(9) -#define KSMBD_SHARE_FLAG_INHERIT_OWNER BIT(10) -#define KSMBD_SHARE_FLAG_STREAMS BIT(11) -#define KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS BIT(12) -#define KSMBD_SHARE_FLAG_ACL_XATTR BIT(13) -#define KSMBD_SHARE_FLAG_UPDATE BIT(14) -#define KSMBD_SHARE_FLAG_CROSSMNT BIT(15) +#define KSMBD_SHARE_FLAG_INVALID (0) +#define KSMBD_SHARE_FLAG_AVAILABLE BIT(0) +#define KSMBD_SHARE_FLAG_BROWSEABLE BIT(1) +#define KSMBD_SHARE_FLAG_WRITEABLE BIT(2) +#define KSMBD_SHARE_FLAG_READONLY BIT(3) +#define KSMBD_SHARE_FLAG_GUEST_OK BIT(4) +#define KSMBD_SHARE_FLAG_GUEST_ONLY BIT(5) +#define KSMBD_SHARE_FLAG_STORE_DOS_ATTRS BIT(6) +#define KSMBD_SHARE_FLAG_OPLOCKS BIT(7) +#define KSMBD_SHARE_FLAG_PIPE BIT(8) +#define KSMBD_SHARE_FLAG_HIDE_DOT_FILES BIT(9) +#define KSMBD_SHARE_FLAG_INHERIT_OWNER BIT(10) +#define KSMBD_SHARE_FLAG_STREAMS BIT(11) +#define KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS BIT(12) +#define KSMBD_SHARE_FLAG_ACL_XATTR BIT(13) +#define KSMBD_SHARE_FLAG_UPDATE BIT(14) +#define KSMBD_SHARE_FLAG_CROSSMNT BIT(15) +#define KSMBD_SHARE_FLAG_CONTINUOUS_AVAILABILITY BIT(16) /* * Tree connect request flags. diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index 328a412259dc..e0a6b758094f 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -158,10 +158,19 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um, share->name = kstrdup(name, GFP_KERNEL); if (!test_share_config_flag(share, KSMBD_SHARE_FLAG_PIPE)) { - share->path = kstrdup(ksmbd_share_config_path(resp), + int path_len = PATH_MAX; + + if (resp->payload_sz) + path_len = resp->payload_sz - resp->veto_list_sz; + + share->path = kstrndup(ksmbd_share_config_path(resp), path_len, GFP_KERNEL); - if (share->path) + if (share->path) { share->path_sz = strlen(share->path); + while (share->path_sz > 1 && + share->path[share->path_sz - 1] == '/') + share->path[--share->path_sz] = '\0'; + } share->create_mask = resp->create_mask; share->directory_mask = resp->directory_mask; share->force_create_mode = resp->force_create_mode; diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 15f68ee05089..aec0a7a12405 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -156,7 +156,7 @@ void ksmbd_session_destroy(struct ksmbd_session *sess) kfree(sess); } -static struct ksmbd_session *__session_lookup(unsigned long long id) +struct ksmbd_session *__session_lookup(unsigned long long id) { struct ksmbd_session *sess; @@ -305,6 +305,32 @@ struct preauth_session *ksmbd_preauth_session_alloc(struct ksmbd_conn *conn, return sess; } +void destroy_previous_session(struct ksmbd_conn *conn, + struct ksmbd_user *user, u64 id) +{ + struct ksmbd_session *prev_sess; + struct ksmbd_user *prev_user; + + down_write(&sessions_table_lock); + down_write(&conn->session_lock); + prev_sess = __session_lookup(id); + if (!prev_sess || prev_sess->state == SMB2_SESSION_EXPIRED) + goto out; + + prev_user = prev_sess->user; + if (!prev_user || + strcmp(user->name, prev_user->name) || + user->passkey_sz != prev_user->passkey_sz || + memcmp(user->passkey, prev_user->passkey, user->passkey_sz)) + goto out; + + ksmbd_destroy_file_table(&prev_sess->file_table); + prev_sess->state = SMB2_SESSION_EXPIRED; +out: + up_write(&conn->session_lock); + up_write(&sessions_table_lock); +} + static bool ksmbd_preauth_session_id_match(struct preauth_session *sess, unsigned long long id) { diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index 63cb08fffde8..dc9fded2cd43 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -88,8 +88,11 @@ struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, int ksmbd_session_register(struct ksmbd_conn *conn, struct ksmbd_session *sess); void ksmbd_sessions_deregister(struct ksmbd_conn *conn); +struct ksmbd_session *__session_lookup(unsigned long long id); struct ksmbd_session *ksmbd_session_lookup_all(struct ksmbd_conn *conn, unsigned long long id); +void destroy_previous_session(struct ksmbd_conn *conn, + struct ksmbd_user *user, u64 id); struct preauth_session *ksmbd_preauth_session_alloc(struct ksmbd_conn *conn, u64 sess_id); struct preauth_session *ksmbd_preauth_session_lookup(struct ksmbd_conn *conn, diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 53dfaac425c6..a8f52c4ebbda 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -159,7 +159,8 @@ static struct oplock_info *opinfo_get_list(struct ksmbd_inode *ci) opinfo = list_first_or_null_rcu(&ci->m_op_list, struct oplock_info, op_entry); if (opinfo) { - if (!atomic_inc_not_zero(&opinfo->refcount)) + if (opinfo->conn == NULL || + !atomic_inc_not_zero(&opinfo->refcount)) opinfo = NULL; else { atomic_inc(&opinfo->conn->r_count); @@ -206,9 +207,9 @@ static void opinfo_add(struct oplock_info *opinfo) { struct ksmbd_inode *ci = opinfo->o_fp->f_ci; - write_lock(&ci->m_lock); + down_write(&ci->m_lock); list_add_rcu(&opinfo->op_entry, &ci->m_op_list); - write_unlock(&ci->m_lock); + up_write(&ci->m_lock); } static void opinfo_del(struct oplock_info *opinfo) @@ -220,9 +221,9 @@ static void opinfo_del(struct oplock_info *opinfo) lease_del_list(opinfo); write_unlock(&lease_list_lock); } - write_lock(&ci->m_lock); + down_write(&ci->m_lock); list_del_rcu(&opinfo->op_entry); - write_unlock(&ci->m_lock); + up_write(&ci->m_lock); } static unsigned long opinfo_count(struct ksmbd_file *fp) @@ -525,21 +526,18 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, * Compare lease key and client_guid to know request from same owner * of same client */ - read_lock(&ci->m_lock); + down_read(&ci->m_lock); list_for_each_entry(opinfo, &ci->m_op_list, op_entry) { - if (!opinfo->is_lease) + if (!opinfo->is_lease || !opinfo->conn) continue; - read_unlock(&ci->m_lock); lease = opinfo->o_lease; ret = compare_guid_key(opinfo, client_guid, lctx->lease_key); if (ret) { m_opinfo = opinfo; /* skip upgrading lease about breaking lease */ - if (atomic_read(&opinfo->breaking_cnt)) { - read_lock(&ci->m_lock); + if (atomic_read(&opinfo->breaking_cnt)) continue; - } /* upgrading lease */ if ((atomic_read(&ci->op_count) + @@ -569,9 +567,8 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, lease_none_upgrade(opinfo, lctx->req_state); } } - read_lock(&ci->m_lock); } - read_unlock(&ci->m_lock); + up_read(&ci->m_lock); return m_opinfo; } @@ -612,13 +609,28 @@ static int oplock_break_pending(struct oplock_info *opinfo, int req_op_level) if (opinfo->op_state == OPLOCK_CLOSING) return -ENOENT; - else if (!opinfo->is_lease && opinfo->level <= req_op_level) - return 1; + else if (opinfo->level <= req_op_level) { + if (opinfo->is_lease == false) + return 1; + + if (opinfo->o_lease->state != + (SMB2_LEASE_HANDLE_CACHING_LE | + SMB2_LEASE_READ_CACHING_LE)) + return 1; + } } - if (!opinfo->is_lease && opinfo->level <= req_op_level) { - wake_up_oplock_break(opinfo); - return 1; + if (opinfo->level <= req_op_level) { + if (opinfo->is_lease == false) { + wake_up_oplock_break(opinfo); + return 1; + } + if (opinfo->o_lease->state != + (SMB2_LEASE_HANDLE_CACHING_LE | + SMB2_LEASE_READ_CACHING_LE)) { + wake_up_oplock_break(opinfo); + return 1; + } } return 0; } @@ -641,7 +653,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) struct smb2_hdr *rsp_hdr; struct ksmbd_file *fp; - fp = ksmbd_lookup_durable_fd(br_info->fid); + fp = ksmbd_lookup_global_fd(br_info->fid); if (!fp) goto out; @@ -886,7 +898,6 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level) struct lease *lease = brk_opinfo->o_lease; atomic_inc(&brk_opinfo->breaking_cnt); - err = oplock_break_pending(brk_opinfo, req_op_level); if (err) return err < 0 ? err : 0; @@ -1104,9 +1115,9 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, if (!p_ci) return; - read_lock(&p_ci->m_lock); + down_read(&p_ci->m_lock); list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { - if (!opinfo->is_lease) + if (opinfo->conn == NULL || !opinfo->is_lease) continue; if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE && @@ -1122,13 +1133,11 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, continue; } - read_unlock(&p_ci->m_lock); oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); opinfo_conn_put(opinfo); - read_lock(&p_ci->m_lock); } } - read_unlock(&p_ci->m_lock); + up_read(&p_ci->m_lock); ksmbd_inode_put(p_ci); } @@ -1142,16 +1151,16 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) opinfo = rcu_dereference(fp->f_opinfo); rcu_read_unlock(); - if (!opinfo->is_lease || opinfo->o_lease->version != 2) + if (!opinfo || !opinfo->is_lease || opinfo->o_lease->version != 2) return; p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent); if (!p_ci) return; - read_lock(&p_ci->m_lock); + down_read(&p_ci->m_lock); list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { - if (!opinfo->is_lease) + if (opinfo->conn == NULL || !opinfo->is_lease) continue; if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE) { @@ -1163,13 +1172,11 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) atomic_dec(&opinfo->conn->r_count); continue; } - read_unlock(&p_ci->m_lock); oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); opinfo_conn_put(opinfo); - read_lock(&p_ci->m_lock); } } - read_unlock(&p_ci->m_lock); + up_read(&p_ci->m_lock); ksmbd_inode_put(p_ci); } @@ -1199,7 +1206,9 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, /* Only v2 leases handle the directory */ if (S_ISDIR(file_inode(fp->filp)->i_mode)) { - if (!lctx || lctx->version != 2) + if (!lctx || lctx->version != 2 || + (lctx->flags != SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE && + !lctx->epoch)) return 0; } @@ -1361,6 +1370,9 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, rcu_read_lock(); list_for_each_entry_rcu(brk_op, &ci->m_op_list, op_entry) { + if (brk_op->conn == NULL) + continue; + if (!atomic_inc_not_zero(&brk_op->refcount)) continue; @@ -1461,8 +1473,9 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) buf->lcontext.LeaseFlags = lease->flags; buf->lcontext.Epoch = cpu_to_le16(lease->epoch); buf->lcontext.LeaseState = lease->state; - memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, - SMB2_LEASE_KEY_SIZE); + if (lease->flags == SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) + memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, + SMB2_LEASE_KEY_SIZE); buf->ccontext.DataOffset = cpu_to_le16(offsetof (struct create_lease_v2, lcontext)); buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context_v2)); @@ -1496,11 +1509,10 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) /** * parse_lease_state() - parse lease context containted in file open request * @open_req: buffer containing smb2 file open(create) request - * @is_dir: whether leasing file is directory * * Return: oplock state, -ENOENT if create lease context not found */ -struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) +struct lease_ctx_info *parse_lease_state(void *open_req) { struct create_context *cc; struct smb2_create_req *req = (struct smb2_create_req *)open_req; @@ -1518,17 +1530,13 @@ struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) struct create_lease_v2 *lc = (struct create_lease_v2 *)cc; memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); - if (is_dir) { - lreq->req_state = lc->lcontext.LeaseState & - ~SMB2_LEASE_WRITE_CACHING_LE; - lreq->is_dir = true; - } else - lreq->req_state = lc->lcontext.LeaseState; + lreq->req_state = lc->lcontext.LeaseState; lreq->flags = lc->lcontext.LeaseFlags; lreq->epoch = lc->lcontext.Epoch; lreq->duration = lc->lcontext.LeaseDuration; - memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, - SMB2_LEASE_KEY_SIZE); + if (lreq->flags == SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) + memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, + SMB2_LEASE_KEY_SIZE); lreq->version = 2; } else { struct create_lease *lc = (struct create_lease *)cc; @@ -1646,6 +1654,8 @@ void create_durable_v2_rsp_buf(char *cc, struct ksmbd_file *fp) buf->Name[3] = 'Q'; buf->Timeout = cpu_to_le32(fp->durable_timeout); + if (fp->is_persistent) + buf->Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT); } /** @@ -1813,3 +1823,71 @@ out: read_unlock(&lease_list_lock); return ret_op; } + +int smb2_check_durable_oplock(struct ksmbd_conn *conn, + struct ksmbd_share_config *share, + struct ksmbd_file *fp, + struct lease_ctx_info *lctx, + char *name) +{ + struct oplock_info *opinfo = opinfo_get(fp); + int ret = 0; + + if (!opinfo) + return 0; + + if (opinfo->is_lease == false) { + if (lctx) { + pr_err("create context include lease\n"); + ret = -EBADF; + goto out; + } + + if (opinfo->level != SMB2_OPLOCK_LEVEL_BATCH) { + pr_err("oplock level is not equal to SMB2_OPLOCK_LEVEL_BATCH\n"); + ret = -EBADF; + } + + goto out; + } + + if (memcmp(conn->ClientGUID, fp->client_guid, + SMB2_CLIENT_GUID_SIZE)) { + ksmbd_debug(SMB, "Client guid of fp is not equal to the one of connection\n"); + ret = -EBADF; + goto out; + } + + if (!lctx) { + ksmbd_debug(SMB, "create context does not include lease\n"); + ret = -EBADF; + goto out; + } + + if (memcmp(opinfo->o_lease->lease_key, lctx->lease_key, + SMB2_LEASE_KEY_SIZE)) { + ksmbd_debug(SMB, + "lease key of fp does not match lease key in create context\n"); + ret = -EBADF; + goto out; + } + + if (!(opinfo->o_lease->state & SMB2_LEASE_HANDLE_CACHING_LE)) { + ksmbd_debug(SMB, "lease state does not contain SMB2_LEASE_HANDLE_CACHING\n"); + ret = -EBADF; + goto out; + } + + if (opinfo->o_lease->version != lctx->version) { + ksmbd_debug(SMB, + "lease version of fp does not match the one in create context\n"); + ret = -EBADF; + goto out; + } + + if (!ksmbd_inode_pending_delete(fp)) + ret = ksmbd_validate_name_reconnect(share, fp, name); +out: + opinfo_put(opinfo); + return ret; +} diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 5b93ea9196c0..e9da63f25b20 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -111,7 +111,7 @@ void opinfo_put(struct oplock_info *opinfo); /* Lease related functions */ void create_lease_buf(u8 *rbuf, struct lease *lease); -struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir); +struct lease_ctx_info *parse_lease_state(void *open_req); __u8 smb2_map_lease_to_oplock(__le32 lease_state); int lease_read_to_write(struct oplock_info *opinfo); @@ -130,4 +130,9 @@ void destroy_lease_table(struct ksmbd_conn *conn); void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, struct lease_ctx_info *lctx); void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp); +int smb2_check_durable_oplock(struct ksmbd_conn *conn, + struct ksmbd_share_config *share, + struct ksmbd_file *fp, + struct lease_ctx_info *lctx, + char *name); #endif /* __KSMBD_OPLOCK_H */ diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 3079e607c5fe..c67fbc8d6683 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -167,20 +167,17 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, int rc; bool is_chained = false; - if (conn->ops->allocate_rsp_buf(work)) - return; - if (conn->ops->is_transform_hdr && conn->ops->is_transform_hdr(work->request_buf)) { rc = conn->ops->decrypt_req(work); - if (rc < 0) { - conn->ops->set_rsp_status(work, STATUS_DATA_ERROR); - goto send; - } - + if (rc < 0) + return; work->encrypted = true; } + if (conn->ops->allocate_rsp_buf(work)) + return; + rc = conn->ops->init_rsp_hdr(work); if (rc) { /* either uid or tid is not correct */ @@ -625,7 +622,6 @@ static void __exit ksmbd_server_exit(void) } MODULE_AUTHOR("Namjae Jeon <linkinjeon@kernel.org>"); -MODULE_VERSION(KSMBD_VERSION); MODULE_DESCRIPTION("Linux kernel CIFS/SMB SERVER"); MODULE_LICENSE("GPL"); MODULE_SOFTDEP("pre: ecb"); diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 03dded29a980..727cb49926ee 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -101,13 +101,17 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, *len = le16_to_cpu(((struct smb2_sess_setup_req *)hdr)->SecurityBufferLength); break; case SMB2_TREE_CONNECT: - *off = le16_to_cpu(((struct smb2_tree_connect_req *)hdr)->PathOffset); + *off = max_t(unsigned short int, + le16_to_cpu(((struct smb2_tree_connect_req *)hdr)->PathOffset), + offsetof(struct smb2_tree_connect_req, Buffer)); *len = le16_to_cpu(((struct smb2_tree_connect_req *)hdr)->PathLength); break; case SMB2_CREATE: { unsigned short int name_off = - le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset); + max_t(unsigned short int, + le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset), + offsetof(struct smb2_create_req, Buffer)); unsigned short int name_len = le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength); @@ -128,11 +132,15 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, break; } case SMB2_QUERY_INFO: - *off = le16_to_cpu(((struct smb2_query_info_req *)hdr)->InputBufferOffset); + *off = max_t(unsigned int, + le16_to_cpu(((struct smb2_query_info_req *)hdr)->InputBufferOffset), + offsetof(struct smb2_query_info_req, Buffer)); *len = le32_to_cpu(((struct smb2_query_info_req *)hdr)->InputBufferLength); break; case SMB2_SET_INFO: - *off = le16_to_cpu(((struct smb2_set_info_req *)hdr)->BufferOffset); + *off = max_t(unsigned int, + le16_to_cpu(((struct smb2_set_info_req *)hdr)->BufferOffset), + offsetof(struct smb2_set_info_req, Buffer)); *len = le32_to_cpu(((struct smb2_set_info_req *)hdr)->BufferLength); break; case SMB2_READ: @@ -142,7 +150,7 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, case SMB2_WRITE: if (((struct smb2_write_req *)hdr)->DataOffset || ((struct smb2_write_req *)hdr)->Length) { - *off = max_t(unsigned int, + *off = max_t(unsigned short int, le16_to_cpu(((struct smb2_write_req *)hdr)->DataOffset), offsetof(struct smb2_write_req, Buffer)); *len = le32_to_cpu(((struct smb2_write_req *)hdr)->Length); @@ -153,7 +161,9 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, *len = le16_to_cpu(((struct smb2_write_req *)hdr)->WriteChannelInfoLength); break; case SMB2_QUERY_DIRECTORY: - *off = le16_to_cpu(((struct smb2_query_directory_req *)hdr)->FileNameOffset); + *off = max_t(unsigned short int, + le16_to_cpu(((struct smb2_query_directory_req *)hdr)->FileNameOffset), + offsetof(struct smb2_query_directory_req, Buffer)); *len = le16_to_cpu(((struct smb2_query_directory_req *)hdr)->FileNameLength); break; case SMB2_LOCK: @@ -168,7 +178,9 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, break; } case SMB2_IOCTL: - *off = le32_to_cpu(((struct smb2_ioctl_req *)hdr)->InputOffset); + *off = max_t(unsigned int, + le32_to_cpu(((struct smb2_ioctl_req *)hdr)->InputOffset), + offsetof(struct smb2_ioctl_req, Buffer)); *len = le32_to_cpu(((struct smb2_ioctl_req *)hdr)->InputCount); break; default: diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c index 27a9dce3e03a..606aa3c5189a 100644 --- a/fs/smb/server/smb2ops.c +++ b/fs/smb/server/smb2ops.c @@ -228,6 +228,11 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION) conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || + (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && + conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) + conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; } @@ -256,6 +261,9 @@ void init_smb3_02_server(struct ksmbd_conn *conn) if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; + + if (server_conf.flags & KSMBD_GLOBAL_FLAG_DURABLE_HANDLE) + conn->vals->capabilities |= SMB2_GLOBAL_CAP_PERSISTENT_HANDLES; } /** @@ -275,14 +283,12 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_DIRECTORY_LEASING; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || - (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && - conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_DURABLE_HANDLE) + conn->vals->capabilities |= SMB2_GLOBAL_CAP_PERSISTENT_HANDLES; + INIT_LIST_HEAD(&conn->preauth_sess_table); return 0; } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 0c97d3c86072..b6c5a8ea3887 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -535,6 +535,10 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) if (cmd == SMB2_QUERY_INFO_HE) { struct smb2_query_info_req *req; + if (get_rfc1002_len(work->request_buf) < + offsetof(struct smb2_query_info_req, OutputBufferLength)) + return -EINVAL; + req = smb2_get_msg(work->request_buf); if ((req->InfoType == SMB2_O_INFO_FILE && (req->FileInfoClass == FILE_FULL_EA_INFORMATION || @@ -607,30 +611,6 @@ int smb2_check_user_session(struct ksmbd_work *work) return -ENOENT; } -static void destroy_previous_session(struct ksmbd_conn *conn, - struct ksmbd_user *user, u64 id) -{ - struct ksmbd_session *prev_sess = ksmbd_session_lookup_slowpath(id); - struct ksmbd_user *prev_user; - struct channel *chann; - long index; - - if (!prev_sess) - return; - - prev_user = prev_sess->user; - - if (!prev_user || - strcmp(user->name, prev_user->name) || - user->passkey_sz != prev_user->passkey_sz || - memcmp(user->passkey, prev_user->passkey, user->passkey_sz)) - return; - - prev_sess->state = SMB2_SESSION_EXPIRED; - xa_for_each(&prev_sess->ksmbd_chann_list, index, chann) - ksmbd_conn_set_exiting(chann->conn); -} - /** * smb2_get_name() - get filename string from on the wire smb format * @src: source buffer @@ -1946,12 +1926,12 @@ int smb2_tree_connect(struct ksmbd_work *work) struct ksmbd_session *sess = work->sess; char *treename = NULL, *name = NULL; struct ksmbd_tree_conn_status status; - struct ksmbd_share_config *share; + struct ksmbd_share_config *share = NULL; int rc = -EINVAL; WORK_BUFFERS(work, req, rsp); - treename = smb_strndup_from_utf16(req->Buffer, + treename = smb_strndup_from_utf16((char *)req + le16_to_cpu(req->PathOffset), le16_to_cpu(req->PathLength), true, conn->local_nls); if (IS_ERR(treename)) { @@ -2008,7 +1988,12 @@ int smb2_tree_connect(struct ksmbd_work *work) write_unlock(&sess->tree_conns_lock); rsp->StructureSize = cpu_to_le16(16); out_err1: - rsp->Capabilities = 0; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_DURABLE_HANDLE && share && + test_share_config_flag(share, + KSMBD_SHARE_FLAG_CONTINUOUS_AVAILABILITY)) + rsp->Capabilities = SMB2_SHARE_CAP_CONTINUOUS_AVAILABILITY; + else + rsp->Capabilities = 0; rsp->Reserved = 0; /* default manual caching */ rsp->ShareFlags = SMB2_SHAREFLAG_MANUAL_CACHING; @@ -2642,6 +2627,165 @@ static void ksmbd_acls_fattr(struct smb_fattr *fattr, } } +enum { + DURABLE_RECONN_V2 = 1, + DURABLE_RECONN, + DURABLE_REQ_V2, + DURABLE_REQ, +}; + +struct durable_info { + struct ksmbd_file *fp; + unsigned short int type; + bool persistent; + bool reconnected; + unsigned int timeout; + char *CreateGuid; +}; + +static int parse_durable_handle_context(struct ksmbd_work *work, + struct smb2_create_req *req, + struct lease_ctx_info *lc, + struct durable_info *dh_info) +{ + struct ksmbd_conn *conn = work->conn; + struct create_context *context; + int dh_idx, err = 0; + u64 persistent_id = 0; + int req_op_level; + static const char * const durable_arr[] = {"DH2C", "DHnC", "DH2Q", "DHnQ"}; + + req_op_level = req->RequestedOplockLevel; + for (dh_idx = DURABLE_RECONN_V2; dh_idx <= ARRAY_SIZE(durable_arr); + dh_idx++) { + context = smb2_find_context_vals(req, durable_arr[dh_idx - 1], 4); + if (IS_ERR(context)) { + err = PTR_ERR(context); + goto out; + } + if (!context) + continue; + + switch (dh_idx) { + case DURABLE_RECONN_V2: + { + struct create_durable_reconn_v2_req *recon_v2; + + if (dh_info->type == DURABLE_RECONN || + dh_info->type == DURABLE_REQ_V2) { + err = -EINVAL; + goto out; + } + + recon_v2 = (struct create_durable_reconn_v2_req *)context; + persistent_id = recon_v2->Fid.PersistentFileId; + dh_info->fp = ksmbd_lookup_durable_fd(persistent_id); + if (!dh_info->fp) { + ksmbd_debug(SMB, "Failed to get durable handle state\n"); + err = -EBADF; + goto out; + } + + if (memcmp(dh_info->fp->create_guid, recon_v2->CreateGuid, + SMB2_CREATE_GUID_SIZE)) { + err = -EBADF; + ksmbd_put_durable_fd(dh_info->fp); + goto out; + } + + dh_info->type = dh_idx; + dh_info->reconnected = true; + ksmbd_debug(SMB, + "reconnect v2 Persistent-id from reconnect = %llu\n", + persistent_id); + break; + } + case DURABLE_RECONN: + { + struct create_durable_reconn_req *recon; + + if (dh_info->type == DURABLE_RECONN_V2 || + dh_info->type == DURABLE_REQ_V2) { + err = -EINVAL; + goto out; + } + + recon = (struct create_durable_reconn_req *)context; + persistent_id = recon->Data.Fid.PersistentFileId; + dh_info->fp = ksmbd_lookup_durable_fd(persistent_id); + if (!dh_info->fp) { + ksmbd_debug(SMB, "Failed to get durable handle state\n"); + err = -EBADF; + goto out; + } + + dh_info->type = dh_idx; + dh_info->reconnected = true; + ksmbd_debug(SMB, "reconnect Persistent-id from reconnect = %llu\n", + persistent_id); + break; + } + case DURABLE_REQ_V2: + { + struct create_durable_req_v2 *durable_v2_blob; + + if (dh_info->type == DURABLE_RECONN || + dh_info->type == DURABLE_RECONN_V2) { + err = -EINVAL; + goto out; + } + + durable_v2_blob = + (struct create_durable_req_v2 *)context; + ksmbd_debug(SMB, "Request for durable v2 open\n"); + dh_info->fp = ksmbd_lookup_fd_cguid(durable_v2_blob->CreateGuid); + if (dh_info->fp) { + if (!memcmp(conn->ClientGUID, dh_info->fp->client_guid, + SMB2_CLIENT_GUID_SIZE)) { + if (!(req->hdr.Flags & SMB2_FLAGS_REPLAY_OPERATION)) { + err = -ENOEXEC; + goto out; + } + + dh_info->fp->conn = conn; + dh_info->reconnected = true; + goto out; + } + } + + if (((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) || + req_op_level == SMB2_OPLOCK_LEVEL_BATCH)) { + dh_info->CreateGuid = + durable_v2_blob->CreateGuid; + dh_info->persistent = + le32_to_cpu(durable_v2_blob->Flags); + dh_info->timeout = + le32_to_cpu(durable_v2_blob->Timeout); + dh_info->type = dh_idx; + } + break; + } + case DURABLE_REQ: + if (dh_info->type == DURABLE_RECONN) + goto out; + if (dh_info->type == DURABLE_RECONN_V2 || + dh_info->type == DURABLE_REQ_V2) { + err = -EINVAL; + goto out; + } + + if (((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) || + req_op_level == SMB2_OPLOCK_LEVEL_BATCH)) { + ksmbd_debug(SMB, "Request for durable open\n"); + dh_info->type = dh_idx; + } + } + } + +out: + return err; +} + /** * smb2_open() - handler for smb file open request * @work: smb work containing request buffer @@ -2665,6 +2809,7 @@ int smb2_open(struct ksmbd_work *work) struct lease_ctx_info *lc = NULL; struct create_ea_buf_req *ea_buf = NULL; struct oplock_info *opinfo; + struct durable_info dh_info = {0}; __le32 *next_ptr = NULL; int req_op_level = 0, open_flags = 0, may_flags = 0, file_info = 0; int rc = 0; @@ -2704,7 +2849,7 @@ int smb2_open(struct ksmbd_work *work) goto err_out2; } - name = smb2_get_name(req->Buffer, + name = smb2_get_name((char *)req + le16_to_cpu(req->NameOffset), le16_to_cpu(req->NameLength), work->conn->local_nls); if (IS_ERR(name)) { @@ -2745,6 +2890,49 @@ int smb2_open(struct ksmbd_work *work) } } + req_op_level = req->RequestedOplockLevel; + + if (server_conf.flags & KSMBD_GLOBAL_FLAG_DURABLE_HANDLE && + req->CreateContextsOffset) { + lc = parse_lease_state(req); + rc = parse_durable_handle_context(work, req, lc, &dh_info); + if (rc) { + ksmbd_debug(SMB, "error parsing durable handle context\n"); + goto err_out2; + } + + if (dh_info.reconnected == true) { + rc = smb2_check_durable_oplock(conn, share, dh_info.fp, lc, name); + if (rc) { + ksmbd_put_durable_fd(dh_info.fp); + goto err_out2; + } + + rc = ksmbd_reopen_durable_fd(work, dh_info.fp); + if (rc) { + ksmbd_put_durable_fd(dh_info.fp); + goto err_out2; + } + + if (ksmbd_override_fsids(work)) { + rc = -ENOMEM; + ksmbd_put_durable_fd(dh_info.fp); + goto err_out2; + } + + fp = dh_info.fp; + file_info = FILE_OPENED; + + rc = ksmbd_vfs_getattr(&fp->filp->f_path, &stat); + if (rc) + goto err_out2; + + ksmbd_put_durable_fd(fp); + goto reconnected_fp; + } + } else if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) + lc = parse_lease_state(req); + if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) { pr_err("Invalid impersonationlevel : 0x%x\n", le32_to_cpu(req->ImpersonationLevel)); @@ -3188,9 +3376,9 @@ int smb2_open(struct ksmbd_work *work) * after daccess, saccess, attrib_only, and stream are * initialized. */ - write_lock(&fp->f_ci->m_lock); + down_write(&fp->f_ci->m_lock); list_add(&fp->node, &fp->f_ci->m_fp_list); - write_unlock(&fp->f_ci->m_lock); + up_write(&fp->f_ci->m_lock); /* Check delete pending among previous fp before oplock break */ if (ksmbd_inode_pending_delete(fp)) { @@ -3207,10 +3395,6 @@ int smb2_open(struct ksmbd_work *work) need_truncate = 1; } - req_op_level = req->RequestedOplockLevel; - if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) - lc = parse_lease_state(req, S_ISDIR(file_inode(filp)->i_mode)); - share_ret = ksmbd_smb_check_shared_mode(fp->filp, fp); if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS) || (req_op_level == SMB2_OPLOCK_LEVEL_LEASE && @@ -3221,6 +3405,11 @@ int smb2_open(struct ksmbd_work *work) } } else { if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) { + if (S_ISDIR(file_inode(filp)->i_mode)) { + lc->req_state &= ~SMB2_LEASE_WRITE_CACHING_LE; + lc->is_dir = true; + } + /* * Compare parent lease using parent key. If there is no * a lease that has same parent key, Send lease break @@ -3317,6 +3506,26 @@ int smb2_open(struct ksmbd_work *work) memcpy(fp->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE); + if (dh_info.type == DURABLE_REQ_V2 || dh_info.type == DURABLE_REQ) { + if (dh_info.type == DURABLE_REQ_V2 && dh_info.persistent && + test_share_config_flag(work->tcon->share_conf, + KSMBD_SHARE_FLAG_CONTINUOUS_AVAILABILITY)) + fp->is_persistent = true; + else + fp->is_durable = true; + + if (dh_info.type == DURABLE_REQ_V2) { + memcpy(fp->create_guid, dh_info.CreateGuid, + SMB2_CREATE_GUID_SIZE); + if (dh_info.timeout) + fp->durable_timeout = min(dh_info.timeout, + 300000); + else + fp->durable_timeout = 60; + } + } + +reconnected_fp: rsp->StructureSize = cpu_to_le16(89); rcu_read_lock(); opinfo = rcu_dereference(fp->f_opinfo); @@ -3403,6 +3612,33 @@ int smb2_open(struct ksmbd_work *work) next_off = conn->vals->create_disk_id_size; } + if (dh_info.type == DURABLE_REQ || dh_info.type == DURABLE_REQ_V2) { + struct create_context *durable_ccontext; + + durable_ccontext = (struct create_context *)(rsp->Buffer + + le32_to_cpu(rsp->CreateContextsLength)); + contxt_cnt++; + if (dh_info.type == DURABLE_REQ) { + create_durable_rsp_buf(rsp->Buffer + + le32_to_cpu(rsp->CreateContextsLength)); + le32_add_cpu(&rsp->CreateContextsLength, + conn->vals->create_durable_size); + iov_len += conn->vals->create_durable_size; + } else { + create_durable_v2_rsp_buf(rsp->Buffer + + le32_to_cpu(rsp->CreateContextsLength), + fp); + le32_add_cpu(&rsp->CreateContextsLength, + conn->vals->create_durable_v2_size); + iov_len += conn->vals->create_durable_v2_size; + } + + if (next_ptr) + *next_ptr = cpu_to_le32(next_off); + next_ptr = &durable_ccontext->Next; + next_off = conn->vals->create_durable_size; + } + if (posix_ctxt) { contxt_cnt++; create_posix_rsp_buf(rsp->Buffer + @@ -3828,11 +4064,16 @@ static int process_query_dir_entries(struct smb2_query_dir_private *priv) } ksmbd_kstat.kstat = &kstat; - if (priv->info_level != FILE_NAMES_INFORMATION) - ksmbd_vfs_fill_dentry_attrs(priv->work, - idmap, - dent, - &ksmbd_kstat); + if (priv->info_level != FILE_NAMES_INFORMATION) { + rc = ksmbd_vfs_fill_dentry_attrs(priv->work, + idmap, + dent, + &ksmbd_kstat); + if (rc) { + dput(dent); + continue; + } + } rc = smb2_populate_readdir_entry(priv->work->conn, priv->info_level, @@ -4075,7 +4316,7 @@ int smb2_query_dir(struct ksmbd_work *work) } srch_flag = req->Flags; - srch_ptr = smb_strndup_from_utf16(req->Buffer, + srch_ptr = smb_strndup_from_utf16((char *)req + le16_to_cpu(req->FileNameOffset), le16_to_cpu(req->FileNameLength), 1, conn->local_nls); if (IS_ERR(srch_ptr)) { @@ -4335,7 +4576,8 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, sizeof(struct smb2_ea_info_req)) return -EINVAL; - ea_req = (struct smb2_ea_info_req *)req->Buffer; + ea_req = (struct smb2_ea_info_req *)((char *)req + + le16_to_cpu(req->InputBufferOffset)); } else { /* need to send all EAs, if no specific EA is requested*/ if (le32_to_cpu(req->Flags) & SL_RETURN_SINGLE_ENTRY) @@ -4480,6 +4722,7 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, struct smb2_file_basic_info *basic_info; struct kstat stat; u64 time; + int ret; if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) { pr_err("no right to read the attributes : 0x%x\n", @@ -4487,9 +4730,12 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return -EACCES; } + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; + basic_info = (struct smb2_file_basic_info *)rsp->Buffer; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); basic_info->CreationTime = cpu_to_le64(fp->create_time); time = ksmbd_UnixTimeToNT(stat.atime); basic_info->LastAccessTime = cpu_to_le64(time); @@ -4504,27 +4750,31 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return 0; } -static void get_file_standard_info(struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, void *rsp_org) +static int get_file_standard_info(struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_standard_info *sinfo; unsigned int delete_pending; - struct inode *inode; struct kstat stat; + int ret; - inode = file_inode(fp->filp); - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, inode, &stat); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; sinfo = (struct smb2_file_standard_info *)rsp->Buffer; delete_pending = ksmbd_inode_pending_delete(fp); - sinfo->AllocationSize = cpu_to_le64(inode->i_blocks << 9); + sinfo->AllocationSize = cpu_to_le64(stat.blocks << 9); sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); sinfo->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); sinfo->DeletePending = delete_pending; sinfo->Directory = S_ISDIR(stat.mode) ? 1 : 0; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_standard_info)); + + return 0; } static void get_file_alignment_info(struct smb2_query_info_rsp *rsp, @@ -4546,11 +4796,11 @@ static int get_file_all_info(struct ksmbd_work *work, struct ksmbd_conn *conn = work->conn; struct smb2_file_all_info *file_info; unsigned int delete_pending; - struct inode *inode; struct kstat stat; int conv_len; char *filename; u64 time; + int ret; if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) { ksmbd_debug(SMB, "no right to read the attributes : 0x%x\n", @@ -4562,8 +4812,10 @@ static int get_file_all_info(struct ksmbd_work *work, if (IS_ERR(filename)) return PTR_ERR(filename); - inode = file_inode(fp->filp); - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, inode, &stat); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; ksmbd_debug(SMB, "filename = %s\n", filename); delete_pending = ksmbd_inode_pending_delete(fp); @@ -4579,7 +4831,7 @@ static int get_file_all_info(struct ksmbd_work *work, file_info->Attributes = fp->f_ci->m_fattr; file_info->Pad1 = 0; file_info->AllocationSize = - cpu_to_le64(inode->i_blocks << 9); + cpu_to_le64(stat.blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); @@ -4623,10 +4875,10 @@ static void get_file_alternate_info(struct ksmbd_work *work, cpu_to_le32(sizeof(struct smb2_file_alt_name_info) + conv_len); } -static void get_file_stream_info(struct ksmbd_work *work, - struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, - void *rsp_org) +static int get_file_stream_info(struct ksmbd_work *work, + struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, + void *rsp_org) { struct ksmbd_conn *conn = work->conn; struct smb2_file_stream_info *file_info; @@ -4637,9 +4889,13 @@ static void get_file_stream_info(struct ksmbd_work *work, int nbytes = 0, streamlen, stream_name_len, next, idx = 0; int buf_free_len; struct smb2_query_info_req *req = ksmbd_req_buf_next(work); + int ret; + + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); file_info = (struct smb2_file_stream_info *)rsp->Buffer; buf_free_len = @@ -4720,29 +4976,37 @@ out: kvfree(xattr_list); rsp->OutputBufferLength = cpu_to_le32(nbytes); + + return 0; } -static void get_file_internal_info(struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, void *rsp_org) +static int get_file_internal_info(struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_internal_info *file_info; struct kstat stat; + int ret; + + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); file_info = (struct smb2_file_internal_info *)rsp->Buffer; file_info->IndexNumber = cpu_to_le64(stat.ino); rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_internal_info)); + + return 0; } static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_ntwrk_info *file_info; - struct inode *inode; struct kstat stat; u64 time; + int ret; if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) { pr_err("no right to read the attributes : 0x%x\n", @@ -4750,10 +5014,12 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, return -EACCES; } - file_info = (struct smb2_file_ntwrk_info *)rsp->Buffer; + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; - inode = file_inode(fp->filp); - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, inode, &stat); + file_info = (struct smb2_file_ntwrk_info *)rsp->Buffer; file_info->CreationTime = cpu_to_le64(fp->create_time); time = ksmbd_UnixTimeToNT(stat.atime); @@ -4763,8 +5029,7 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, time = ksmbd_UnixTimeToNT(stat.ctime); file_info->ChangeTime = cpu_to_le64(time); file_info->Attributes = fp->f_ci->m_fattr; - file_info->AllocationSize = - cpu_to_le64(inode->i_blocks << 9); + file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->Reserved = cpu_to_le32(0); rsp->OutputBufferLength = @@ -4804,14 +5069,17 @@ static void get_file_mode_info(struct smb2_query_info_rsp *rsp, cpu_to_le32(sizeof(struct smb2_file_mode_info)); } -static void get_file_compression_info(struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, void *rsp_org) +static int get_file_compression_info(struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_comp_info *file_info; struct kstat stat; + int ret; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; file_info = (struct smb2_file_comp_info *)rsp->Buffer; file_info->CompressedFileSize = cpu_to_le64(stat.blocks << 9); @@ -4823,6 +5091,8 @@ static void get_file_compression_info(struct smb2_query_info_rsp *rsp, rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_comp_info)); + + return 0; } static int get_file_attribute_tag_info(struct smb2_query_info_rsp *rsp, @@ -4844,7 +5114,7 @@ static int get_file_attribute_tag_info(struct smb2_query_info_rsp *rsp, return 0; } -static void find_file_posix_info(struct smb2_query_info_rsp *rsp, +static int find_file_posix_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { struct smb311_posix_qinfo *file_info; @@ -4852,24 +5122,31 @@ static void find_file_posix_info(struct smb2_query_info_rsp *rsp, struct mnt_idmap *idmap = file_mnt_idmap(fp->filp); vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); + struct kstat stat; u64 time; int out_buf_len = sizeof(struct smb311_posix_qinfo) + 32; + int ret; + + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; file_info = (struct smb311_posix_qinfo *)rsp->Buffer; file_info->CreationTime = cpu_to_le64(fp->create_time); - time = ksmbd_UnixTimeToNT(inode_get_atime(inode)); + time = ksmbd_UnixTimeToNT(stat.atime); file_info->LastAccessTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_mtime(inode)); + time = ksmbd_UnixTimeToNT(stat.mtime); file_info->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_ctime(inode)); + time = ksmbd_UnixTimeToNT(stat.ctime); file_info->ChangeTime = cpu_to_le64(time); file_info->DosAttributes = fp->f_ci->m_fattr; - file_info->Inode = cpu_to_le64(inode->i_ino); - file_info->EndOfFile = cpu_to_le64(inode->i_size); - file_info->AllocationSize = cpu_to_le64(inode->i_blocks << 9); - file_info->HardLinks = cpu_to_le32(inode->i_nlink); - file_info->Mode = cpu_to_le32(inode->i_mode & 0777); - file_info->DeviceId = cpu_to_le32(inode->i_rdev); + file_info->Inode = cpu_to_le64(stat.ino); + file_info->EndOfFile = cpu_to_le64(stat.size); + file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); + file_info->HardLinks = cpu_to_le32(stat.nlink); + file_info->Mode = cpu_to_le32(stat.mode & 0777); + file_info->DeviceId = cpu_to_le32(stat.rdev); /* * Sids(32) contain two sids(Domain sid(16), UNIX group sid(16)). @@ -4882,6 +5159,8 @@ static void find_file_posix_info(struct smb2_query_info_rsp *rsp, SIDUNIX_GROUP, (struct smb_sid *)&file_info->Sids[16]); rsp->OutputBufferLength = cpu_to_le32(out_buf_len); + + return 0; } static int smb2_get_info_file(struct ksmbd_work *work, @@ -4930,7 +5209,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, break; case FILE_STANDARD_INFORMATION: - get_file_standard_info(rsp, fp, work->response_buf); + rc = get_file_standard_info(rsp, fp, work->response_buf); break; case FILE_ALIGNMENT_INFORMATION: @@ -4946,11 +5225,11 @@ static int smb2_get_info_file(struct ksmbd_work *work, break; case FILE_STREAM_INFORMATION: - get_file_stream_info(work, rsp, fp, work->response_buf); + rc = get_file_stream_info(work, rsp, fp, work->response_buf); break; case FILE_INTERNAL_INFORMATION: - get_file_internal_info(rsp, fp, work->response_buf); + rc = get_file_internal_info(rsp, fp, work->response_buf); break; case FILE_NETWORK_OPEN_INFORMATION: @@ -4974,7 +5253,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, break; case FILE_COMPRESSION_INFORMATION: - get_file_compression_info(rsp, fp, work->response_buf); + rc = get_file_compression_info(rsp, fp, work->response_buf); break; case FILE_ATTRIBUTE_TAG_INFORMATION: @@ -4985,7 +5264,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, pr_err("client doesn't negotiate with SMB3.1.1 POSIX Extensions\n"); rc = -EOPNOTSUPP; } else { - find_file_posix_info(rsp, fp, work->response_buf); + rc = find_file_posix_info(rsp, fp, work->response_buf); } break; default: @@ -5398,7 +5677,6 @@ int smb2_close(struct ksmbd_work *work) struct smb2_close_rsp *rsp; struct ksmbd_conn *conn = work->conn; struct ksmbd_file *fp; - struct inode *inode; u64 time; int err = 0; @@ -5453,24 +5731,33 @@ int smb2_close(struct ksmbd_work *work) rsp->Reserved = 0; if (req->Flags == SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB) { + struct kstat stat; + int ret; + fp = ksmbd_lookup_fd_fast(work, volatile_id); if (!fp) { err = -ENOENT; goto out; } - inode = file_inode(fp->filp); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) { + ksmbd_fd_put(work, fp); + goto out; + } + rsp->Flags = SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB; - rsp->AllocationSize = S_ISDIR(inode->i_mode) ? 0 : - cpu_to_le64(inode->i_blocks << 9); - rsp->EndOfFile = cpu_to_le64(inode->i_size); + rsp->AllocationSize = S_ISDIR(stat.mode) ? 0 : + cpu_to_le64(stat.blocks << 9); + rsp->EndOfFile = cpu_to_le64(stat.size); rsp->Attributes = fp->f_ci->m_fattr; rsp->CreationTime = cpu_to_le64(fp->create_time); - time = ksmbd_UnixTimeToNT(inode_get_atime(inode)); + time = ksmbd_UnixTimeToNT(stat.atime); rsp->LastAccessTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_mtime(inode)); + time = ksmbd_UnixTimeToNT(stat.mtime); rsp->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_ctime(inode)); + time = ksmbd_UnixTimeToNT(stat.ctime); rsp->ChangeTime = cpu_to_le64(time); ksmbd_fd_put(work, fp); } else { @@ -5581,8 +5868,9 @@ static int smb2_rename(struct ksmbd_work *work, if (!file_info->ReplaceIfExists) flags = RENAME_NOREPLACE; - smb_break_all_levII_oplock(work, fp, 0); rc = ksmbd_vfs_rename(work, &fp->filp->f_path, new_name, flags); + if (!rc) + smb_break_all_levII_oplock(work, fp, 0); out: kfree(new_name); return rc; @@ -5759,15 +6047,21 @@ static int set_file_allocation_info(struct ksmbd_work *work, loff_t alloc_blks; struct inode *inode; + struct kstat stat; int rc; if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; + rc = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (rc) + return rc; + alloc_blks = (le64_to_cpu(file_alloc_info->AllocationSize) + 511) >> 9; inode = file_inode(fp->filp); - if (alloc_blks > inode->i_blocks) { + if (alloc_blks > stat.blocks) { smb_break_all_levII_oplock(work, fp, 1); rc = vfs_fallocate(fp->filp, FALLOC_FL_KEEP_SIZE, 0, alloc_blks * 512); @@ -5775,7 +6069,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, pr_err("vfs_fallocate is failed : %d\n", rc); return rc; } - } else if (alloc_blks < inode->i_blocks) { + } else if (alloc_blks < stat.blocks) { loff_t size; /* @@ -5930,6 +6224,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, struct ksmbd_share_config *share) { unsigned int buf_len = le32_to_cpu(req->BufferLength); + char *buffer = (char *)req + le16_to_cpu(req->BufferOffset); switch (req->FileInfoClass) { case FILE_BASIC_INFORMATION: @@ -5937,7 +6232,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, if (buf_len < sizeof(struct smb2_file_basic_info)) return -EINVAL; - return set_file_basic_info(fp, (struct smb2_file_basic_info *)req->Buffer, share); + return set_file_basic_info(fp, (struct smb2_file_basic_info *)buffer, share); } case FILE_ALLOCATION_INFORMATION: { @@ -5945,7 +6240,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_file_allocation_info(work, fp, - (struct smb2_file_alloc_info *)req->Buffer); + (struct smb2_file_alloc_info *)buffer); } case FILE_END_OF_FILE_INFORMATION: { @@ -5953,7 +6248,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_end_of_file_info(work, fp, - (struct smb2_file_eof_info *)req->Buffer); + (struct smb2_file_eof_info *)buffer); } case FILE_RENAME_INFORMATION: { @@ -5961,7 +6256,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_rename_info(work, fp, - (struct smb2_file_rename_info *)req->Buffer, + (struct smb2_file_rename_info *)buffer, buf_len); } case FILE_LINK_INFORMATION: @@ -5970,7 +6265,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return smb2_create_link(work, work->tcon->share_conf, - (struct smb2_file_link_info *)req->Buffer, + (struct smb2_file_link_info *)buffer, buf_len, fp->filp, work->conn->local_nls); } @@ -5980,7 +6275,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_file_disposition_info(fp, - (struct smb2_file_disposition_info *)req->Buffer); + (struct smb2_file_disposition_info *)buffer); } case FILE_FULL_EA_INFORMATION: { @@ -5993,7 +6288,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, if (buf_len < sizeof(struct smb2_ea_info)) return -EINVAL; - return smb2_set_ea((struct smb2_ea_info *)req->Buffer, + return smb2_set_ea((struct smb2_ea_info *)buffer, buf_len, &fp->filp->f_path, true); } case FILE_POSITION_INFORMATION: @@ -6001,14 +6296,14 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, if (buf_len < sizeof(struct smb2_file_pos_info)) return -EINVAL; - return set_file_position_info(fp, (struct smb2_file_pos_info *)req->Buffer); + return set_file_position_info(fp, (struct smb2_file_pos_info *)buffer); } case FILE_MODE_INFORMATION: { if (buf_len < sizeof(struct smb2_file_mode_info)) return -EINVAL; - return set_file_mode_info(fp, (struct smb2_file_mode_info *)req->Buffer); + return set_file_mode_info(fp, (struct smb2_file_mode_info *)buffer); } } @@ -6089,7 +6384,7 @@ int smb2_set_info(struct ksmbd_work *work) } rc = smb2_set_info_sec(fp, le32_to_cpu(req->AdditionalInformation), - req->Buffer, + (char *)req + le16_to_cpu(req->BufferOffset), le32_to_cpu(req->BufferLength)); ksmbd_revert_fsids(work); break; @@ -6764,10 +7059,10 @@ struct file_lock *smb_flock_init(struct file *f) locks_init_lock(fl); - fl->fl_owner = f; - fl->fl_pid = current->tgid; - fl->fl_file = f; - fl->fl_flags = FL_POSIX; + fl->c.flc_owner = f; + fl->c.flc_pid = current->tgid; + fl->c.flc_file = f; + fl->c.flc_flags = FL_POSIX; fl->fl_ops = NULL; fl->fl_lmops = NULL; @@ -6784,30 +7079,30 @@ static int smb2_set_flock_flags(struct file_lock *flock, int flags) case SMB2_LOCKFLAG_SHARED: ksmbd_debug(SMB, "received shared request\n"); cmd = F_SETLKW; - flock->fl_type = F_RDLCK; - flock->fl_flags |= FL_SLEEP; + flock->c.flc_type = F_RDLCK; + flock->c.flc_flags |= FL_SLEEP; break; case SMB2_LOCKFLAG_EXCLUSIVE: ksmbd_debug(SMB, "received exclusive request\n"); cmd = F_SETLKW; - flock->fl_type = F_WRLCK; - flock->fl_flags |= FL_SLEEP; + flock->c.flc_type = F_WRLCK; + flock->c.flc_flags |= FL_SLEEP; break; case SMB2_LOCKFLAG_SHARED | SMB2_LOCKFLAG_FAIL_IMMEDIATELY: ksmbd_debug(SMB, "received shared & fail immediately request\n"); cmd = F_SETLK; - flock->fl_type = F_RDLCK; + flock->c.flc_type = F_RDLCK; break; case SMB2_LOCKFLAG_EXCLUSIVE | SMB2_LOCKFLAG_FAIL_IMMEDIATELY: ksmbd_debug(SMB, "received exclusive & fail immediately request\n"); cmd = F_SETLK; - flock->fl_type = F_WRLCK; + flock->c.flc_type = F_WRLCK; break; case SMB2_LOCKFLAG_UNLOCK: ksmbd_debug(SMB, "received unlock request\n"); - flock->fl_type = F_UNLCK; + flock->c.flc_type = F_UNLCK; cmd = F_SETLK; break; } @@ -6845,13 +7140,13 @@ static void smb2_remove_blocked_lock(void **argv) struct file_lock *flock = (struct file_lock *)argv[0]; ksmbd_vfs_posix_lock_unblock(flock); - wake_up(&flock->fl_wait); + locks_wake_up(flock); } static inline bool lock_defer_pending(struct file_lock *fl) { /* check pending lock waiters */ - return waitqueue_active(&fl->fl_wait); + return waitqueue_active(&fl->c.flc_wait); } /** @@ -6942,8 +7237,8 @@ int smb2_lock(struct ksmbd_work *work) list_for_each_entry(cmp_lock, &lock_list, llist) { if (cmp_lock->fl->fl_start <= flock->fl_start && cmp_lock->fl->fl_end >= flock->fl_end) { - if (cmp_lock->fl->fl_type != F_UNLCK && - flock->fl_type != F_UNLCK) { + if (cmp_lock->fl->c.flc_type != F_UNLCK && + flock->c.flc_type != F_UNLCK) { pr_err("conflict two locks in one request\n"); err = -EINVAL; locks_free_lock(flock); @@ -6991,12 +7286,12 @@ int smb2_lock(struct ksmbd_work *work) list_for_each_entry(conn, &conn_list, conns_list) { spin_lock(&conn->llist_lock); list_for_each_entry_safe(cmp_lock, tmp2, &conn->lock_list, clist) { - if (file_inode(cmp_lock->fl->fl_file) != - file_inode(smb_lock->fl->fl_file)) + if (file_inode(cmp_lock->fl->c.flc_file) != + file_inode(smb_lock->fl->c.flc_file)) continue; - if (smb_lock->fl->fl_type == F_UNLCK) { - if (cmp_lock->fl->fl_file == smb_lock->fl->fl_file && + if (lock_is_unlock(smb_lock->fl)) { + if (cmp_lock->fl->c.flc_file == smb_lock->fl->c.flc_file && cmp_lock->start == smb_lock->start && cmp_lock->end == smb_lock->end && !lock_defer_pending(cmp_lock->fl)) { @@ -7013,7 +7308,7 @@ int smb2_lock(struct ksmbd_work *work) continue; } - if (cmp_lock->fl->fl_file == smb_lock->fl->fl_file) { + if (cmp_lock->fl->c.flc_file == smb_lock->fl->c.flc_file) { if (smb_lock->flags & SMB2_LOCKFLAG_SHARED) continue; } else { @@ -7055,7 +7350,7 @@ int smb2_lock(struct ksmbd_work *work) } up_read(&conn_list_lock); out_check_cl: - if (smb_lock->fl->fl_type == F_UNLCK && nolock) { + if (lock_is_unlock(smb_lock->fl) && nolock) { pr_err("Try to unlock nolocked range\n"); rsp->hdr.Status = STATUS_RANGE_NOT_LOCKED; goto out; @@ -7179,7 +7474,7 @@ out: struct file_lock *rlock = NULL; rlock = smb_flock_init(filp); - rlock->fl_type = F_UNLCK; + rlock->c.flc_type = F_UNLCK; rlock->fl_start = smb_lock->start; rlock->fl_end = smb_lock->end; @@ -7535,7 +7830,7 @@ static int fsctl_pipe_transceive(struct ksmbd_work *work, u64 id, struct smb2_ioctl_rsp *rsp) { struct ksmbd_rpc_command *rpc_resp; - char *data_buf = (char *)&req->Buffer[0]; + char *data_buf = (char *)req + le32_to_cpu(req->InputOffset); int nbytes = 0; rpc_resp = ksmbd_rpc_ioctl(work->sess, id, data_buf, @@ -7648,6 +7943,7 @@ int smb2_ioctl(struct ksmbd_work *work) u64 id = KSMBD_NO_FID; struct ksmbd_conn *conn = work->conn; int ret = 0; + char *buffer; if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); @@ -7670,6 +7966,8 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } + buffer = (char *)req + le32_to_cpu(req->InputOffset); + cnt_code = le32_to_cpu(req->CtlCode); ret = smb2_calc_max_out_buf_len(work, 48, le32_to_cpu(req->MaxOutputResponse)); @@ -7727,7 +8025,7 @@ int smb2_ioctl(struct ksmbd_work *work) } ret = fsctl_validate_negotiate_info(conn, - (struct validate_negotiate_info_req *)&req->Buffer[0], + (struct validate_negotiate_info_req *)buffer, (struct validate_negotiate_info_rsp *)&rsp->Buffer[0], in_buf_len); if (ret < 0) @@ -7780,7 +8078,7 @@ int smb2_ioctl(struct ksmbd_work *work) rsp->VolatileFileId = req->VolatileFileId; rsp->PersistentFileId = req->PersistentFileId; fsctl_copychunk(work, - (struct copychunk_ioctl_req *)&req->Buffer[0], + (struct copychunk_ioctl_req *)buffer, le32_to_cpu(req->CtlCode), le32_to_cpu(req->InputCount), req->VolatileFileId, @@ -7793,8 +8091,7 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } - ret = fsctl_set_sparse(work, id, - (struct file_sparse *)&req->Buffer[0]); + ret = fsctl_set_sparse(work, id, (struct file_sparse *)buffer); if (ret < 0) goto out; break; @@ -7817,7 +8114,7 @@ int smb2_ioctl(struct ksmbd_work *work) } zero_data = - (struct file_zero_data_information *)&req->Buffer[0]; + (struct file_zero_data_information *)buffer; off = le64_to_cpu(zero_data->FileOffset); bfz = le64_to_cpu(zero_data->BeyondFinalZero); @@ -7848,7 +8145,7 @@ int smb2_ioctl(struct ksmbd_work *work) } ret = fsctl_query_allocated_ranges(work, id, - (struct file_allocated_range_buffer *)&req->Buffer[0], + (struct file_allocated_range_buffer *)buffer, (struct file_allocated_range_buffer *)&rsp->Buffer[0], out_buf_len / sizeof(struct file_allocated_range_buffer), &nbytes); @@ -7892,7 +8189,7 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } - dup_ext = (struct duplicate_extents_to_file *)&req->Buffer[0]; + dup_ext = (struct duplicate_extents_to_file *)buffer; fp_in = ksmbd_lookup_fd_slow(work, dup_ext->VolatileFileHandle, dup_ext->PersistentFileHandle); diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index d12cfd3b0927..643f5e1cfe35 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -64,7 +64,7 @@ struct preauth_integrity_info { #define SMB2_SESSION_TIMEOUT (10 * HZ) struct create_durable_req_v2 { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; __le32 Timeout; __le32 Flags; @@ -72,8 +72,20 @@ struct create_durable_req_v2 { __u8 CreateGuid[16]; } __packed; +struct create_durable_reconn_req { + struct create_context_hdr ccontext; + __u8 Name[8]; + union { + __u8 Reserved[16]; + struct { + __u64 PersistentFileId; + __u64 VolatileFileId; + } Fid; + } Data; +} __packed; + struct create_durable_reconn_v2_req { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; struct { __u64 PersistentFileId; @@ -84,13 +96,13 @@ struct create_durable_reconn_v2_req { } __packed; struct create_alloc_size_req { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; __le64 AllocationSize; } __packed; struct create_durable_rsp { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; union { __u8 Reserved[8]; @@ -98,8 +110,11 @@ struct create_durable_rsp { } Data; } __packed; +/* See MS-SMB2 2.2.13.2.11 */ +/* Flags */ +#define SMB2_DHANDLE_FLAG_PERSISTENT 0x00000002 struct create_durable_v2_rsp { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; __le32 Timeout; __le32 Flags; @@ -107,7 +122,7 @@ struct create_durable_v2_rsp { /* equivalent of the contents of SMB3.1.1 POSIX open context response */ struct create_posix_rsp { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[16]; __le32 nlink; __le32 reparse_tag; @@ -366,13 +381,13 @@ struct smb2_ea_info { } __packed; /* level 15 Query */ struct create_ea_buf_req { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; struct smb2_ea_info ea; } __packed; struct create_sd_buf_req { - struct create_context ccontext; + struct create_context_hdr ccontext; __u8 Name[8]; struct smb_ntsd ntsd; } __packed; diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index 7c98bf699772..474dadf6b7b8 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -457,10 +457,13 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, } ksmbd_kstat.kstat = &kstat; - ksmbd_vfs_fill_dentry_attrs(work, - idmap, - dentry, - &ksmbd_kstat); + rc = ksmbd_vfs_fill_dentry_attrs(work, + idmap, + dentry, + &ksmbd_kstat); + if (rc) + break; + rc = fn(conn, info_level, d_info, &ksmbd_kstat); if (rc) break; @@ -643,7 +646,7 @@ int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp) * Lookup fp in master fp list, and check desired access and * shared mode between previous open and current open. */ - read_lock(&curr_fp->f_ci->m_lock); + down_read(&curr_fp->f_ci->m_lock); list_for_each_entry(prev_fp, &curr_fp->f_ci->m_fp_list, node) { if (file_inode(filp) != file_inode(prev_fp->filp)) continue; @@ -719,7 +722,7 @@ int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp) break; } } - read_unlock(&curr_fp->f_ci->m_lock); + up_read(&curr_fp->f_ci->m_lock); return rc; } diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index f29bb03f0dc4..8752ac82c557 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -65,6 +65,7 @@ struct ipc_msg_table_entry { struct hlist_node ipc_table_hlist; void *response; + unsigned int msg_sz; }; static struct delayed_work ipc_timer_work; @@ -275,6 +276,7 @@ static int handle_response(int type, void *payload, size_t sz) } memcpy(entry->response, payload, sz); + entry->msg_sz = sz; wake_up_interruptible(&entry->wait); ret = 0; break; @@ -453,6 +455,34 @@ out: return ret; } +static int ipc_validate_msg(struct ipc_msg_table_entry *entry) +{ + unsigned int msg_sz = entry->msg_sz; + + if (entry->type == KSMBD_EVENT_RPC_REQUEST) { + struct ksmbd_rpc_command *resp = entry->response; + + msg_sz = sizeof(struct ksmbd_rpc_command) + resp->payload_sz; + } else if (entry->type == KSMBD_EVENT_SPNEGO_AUTHEN_REQUEST) { + struct ksmbd_spnego_authen_response *resp = entry->response; + + msg_sz = sizeof(struct ksmbd_spnego_authen_response) + + resp->session_key_len + resp->spnego_blob_len; + } else if (entry->type == KSMBD_EVENT_SHARE_CONFIG_REQUEST) { + struct ksmbd_share_config_response *resp = entry->response; + + if (resp->payload_sz) { + if (resp->payload_sz < resp->veto_list_sz) + return -EINVAL; + + msg_sz = sizeof(struct ksmbd_share_config_response) + + resp->payload_sz; + } + } + + return entry->msg_sz != msg_sz ? -EINVAL : 0; +} + static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle) { struct ipc_msg_table_entry entry; @@ -477,6 +507,13 @@ static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle ret = wait_event_interruptible_timeout(entry.wait, entry.response != NULL, IPC_WAIT_TIMEOUT); + if (entry.response) { + ret = ipc_validate_msg(&entry); + if (ret) { + kvfree(entry.response); + entry.response = NULL; + } + } out: down_write(&ipc_msg_table_lock); hash_del(&entry.ipc_table_hlist); diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 002a3f0dc7c5..6633fa78e9b9 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -448,6 +448,10 @@ static int create_socket(struct interface *iface) sin6.sin6_family = PF_INET6; sin6.sin6_addr = in6addr_any; sin6.sin6_port = htons(server_conf.tcp_port); + + lock_sock(ksmbd_socket->sk); + ksmbd_socket->sk->sk_ipv6only = false; + release_sock(ksmbd_socket->sk); } ksmbd_tcp_nodelay(ksmbd_socket); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index a6961bfe3e13..51b1b0bed616 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -337,18 +337,18 @@ static int check_lock_range(struct file *filp, loff_t start, loff_t end, return 0; spin_lock(&ctx->flc_lock); - list_for_each_entry(flock, &ctx->flc_posix, fl_list) { + for_each_file_lock(flock, &ctx->flc_posix) { /* check conflict locks */ if (flock->fl_end >= start && end >= flock->fl_start) { - if (flock->fl_type == F_RDLCK) { + if (lock_is_read(flock)) { if (type == WRITE) { pr_err("not allow write by shared lock\n"); error = 1; goto out; } - } else if (flock->fl_type == F_WRLCK) { + } else if (lock_is_write(flock)) { /* check owner in lock */ - if (flock->fl_file != filp) { + if (flock->c.flc_file != filp) { error = 1; pr_err("not allow rw access by exclusive lock from other opens\n"); goto out; @@ -754,10 +754,15 @@ retry: goto out4; } + /* + * explicitly handle file overwrite case, for compatibility with + * filesystems that may not support rename flags (e.g: fuse) + */ if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) { err = -EEXIST; goto out4; } + flags &= ~(RENAME_NOREPLACE); if (old_child == trap) { err = -EINVAL; @@ -1682,11 +1687,19 @@ int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, struct dentry *dentry, struct ksmbd_kstat *ksmbd_kstat) { + struct ksmbd_share_config *share_conf = work->tcon->share_conf; u64 time; int rc; + struct path path = { + .mnt = share_conf->vfs_path.mnt, + .dentry = dentry, + }; - generic_fillattr(idmap, STATX_BASIC_STATS, d_inode(dentry), - ksmbd_kstat->kstat); + rc = vfs_getattr(&path, ksmbd_kstat->kstat, + STATX_BASIC_STATS | STATX_BTIME, + AT_STATX_SYNC_AS_STAT); + if (rc) + return rc; time = ksmbd_UnixTimeToNT(ksmbd_kstat->kstat->ctime); ksmbd_kstat->create_time = time; @@ -1837,13 +1850,13 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, void ksmbd_vfs_posix_lock_wait(struct file_lock *flock) { - wait_event(flock->fl_wait, !flock->fl_blocker); + wait_event(flock->c.flc_wait, !flock->c.flc_blocker); } int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout) { - return wait_event_interruptible_timeout(flock->fl_wait, - !flock->fl_blocker, + return wait_event_interruptible_timeout(flock->c.flc_wait, + !flock->c.flc_blocker, timeout); } diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 4e82ff627d12..6cb599cd287e 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -165,7 +165,7 @@ static int ksmbd_inode_init(struct ksmbd_inode *ci, struct ksmbd_file *fp) ci->m_fattr = 0; INIT_LIST_HEAD(&ci->m_fp_list); INIT_LIST_HEAD(&ci->m_op_list); - rwlock_init(&ci->m_lock); + init_rwsem(&ci->m_lock); ci->m_de = fp->filp->f_path.dentry; return 0; } @@ -261,14 +261,14 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) } if (atomic_dec_and_test(&ci->m_count)) { - write_lock(&ci->m_lock); + down_write(&ci->m_lock); if (ci->m_flags & (S_DEL_ON_CLS | S_DEL_PENDING)) { ci->m_flags &= ~(S_DEL_ON_CLS | S_DEL_PENDING); - write_unlock(&ci->m_lock); + up_write(&ci->m_lock); ksmbd_vfs_unlink(filp); - write_lock(&ci->m_lock); + down_write(&ci->m_lock); } - write_unlock(&ci->m_lock); + up_write(&ci->m_lock); ksmbd_inode_free(ci); } @@ -289,9 +289,9 @@ static void __ksmbd_remove_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp if (!has_file_id(fp->volatile_id)) return; - write_lock(&fp->f_ci->m_lock); + down_write(&fp->f_ci->m_lock); list_del_init(&fp->node); - write_unlock(&fp->f_ci->m_lock); + up_write(&fp->f_ci->m_lock); write_lock(&ft->lock); idr_remove(ft->idr, fp->volatile_id); @@ -305,7 +305,8 @@ static void __ksmbd_close_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) fd_limit_close(); __ksmbd_remove_durable_fd(fp); - __ksmbd_remove_fd(ft, fp); + if (ft) + __ksmbd_remove_fd(ft, fp); close_id_del_oplock(fp); filp = fp->filp; @@ -465,11 +466,32 @@ struct ksmbd_file *ksmbd_lookup_fd_slow(struct ksmbd_work *work, u64 id, return fp; } -struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id) +struct ksmbd_file *ksmbd_lookup_global_fd(unsigned long long id) { return __ksmbd_lookup_fd(&global_ft, id); } +struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id) +{ + struct ksmbd_file *fp; + + fp = __ksmbd_lookup_fd(&global_ft, id); + if (fp && fp->conn) { + ksmbd_put_durable_fd(fp); + fp = NULL; + } + + return fp; +} + +void ksmbd_put_durable_fd(struct ksmbd_file *fp) +{ + if (!atomic_dec_and_test(&fp->refcount)) + return; + + __ksmbd_close_fd(NULL, fp); +} + struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid) { struct ksmbd_file *fp = NULL; @@ -501,17 +523,17 @@ struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry) if (!ci) return NULL; - read_lock(&ci->m_lock); + down_read(&ci->m_lock); list_for_each_entry(lfp, &ci->m_fp_list, node) { if (inode == file_inode(lfp->filp)) { atomic_dec(&ci->m_count); lfp = ksmbd_fp_get(lfp); - read_unlock(&ci->m_lock); + up_read(&ci->m_lock); return lfp; } } atomic_dec(&ci->m_count); - read_unlock(&ci->m_lock); + up_read(&ci->m_lock); return NULL; } @@ -639,6 +661,32 @@ __close_file_table_ids(struct ksmbd_file_table *ft, return num; } +static inline bool is_reconnectable(struct ksmbd_file *fp) +{ + struct oplock_info *opinfo = opinfo_get(fp); + bool reconn = false; + + if (!opinfo) + return false; + + if (opinfo->op_state != OPLOCK_STATE_NONE) { + opinfo_put(opinfo); + return false; + } + + if (fp->is_resilient || fp->is_persistent) + reconn = true; + else if (fp->is_durable && opinfo->is_lease && + opinfo->o_lease->state & SMB2_LEASE_HANDLE_CACHING_LE) + reconn = true; + + else if (fp->is_durable && opinfo->level == SMB2_OPLOCK_LEVEL_BATCH) + reconn = true; + + opinfo_put(opinfo); + return reconn; +} + static bool tree_conn_fd_check(struct ksmbd_tree_connect *tcon, struct ksmbd_file *fp) { @@ -648,7 +696,28 @@ static bool tree_conn_fd_check(struct ksmbd_tree_connect *tcon, static bool session_fd_check(struct ksmbd_tree_connect *tcon, struct ksmbd_file *fp) { - return false; + struct ksmbd_inode *ci; + struct oplock_info *op; + struct ksmbd_conn *conn; + + if (!is_reconnectable(fp)) + return false; + + conn = fp->conn; + ci = fp->f_ci; + down_write(&ci->m_lock); + list_for_each_entry_rcu(op, &ci->m_op_list, op_entry) { + if (op->conn != conn) + continue; + op->conn = NULL; + } + up_write(&ci->m_lock); + + fp->conn = NULL; + fp->tcon = NULL; + fp->volatile_id = KSMBD_NO_FID; + + return true; } void ksmbd_close_tree_conn_fds(struct ksmbd_work *work) @@ -687,6 +756,68 @@ void ksmbd_free_global_file_table(void) ksmbd_destroy_file_table(&global_ft); } +int ksmbd_validate_name_reconnect(struct ksmbd_share_config *share, + struct ksmbd_file *fp, char *name) +{ + char *pathname, *ab_pathname; + int ret = 0; + + pathname = kmalloc(PATH_MAX, GFP_KERNEL); + if (!pathname) + return -EACCES; + + ab_pathname = d_path(&fp->filp->f_path, pathname, PATH_MAX); + if (IS_ERR(ab_pathname)) { + kfree(pathname); + return -EACCES; + } + + if (name && strcmp(&ab_pathname[share->path_sz + 1], name)) { + ksmbd_debug(SMB, "invalid name reconnect %s\n", name); + ret = -EINVAL; + } + + kfree(pathname); + + return ret; +} + +int ksmbd_reopen_durable_fd(struct ksmbd_work *work, struct ksmbd_file *fp) +{ + struct ksmbd_inode *ci; + struct oplock_info *op; + + if (!fp->is_durable || fp->conn || fp->tcon) { + pr_err("Invalid durable fd [%p:%p]\n", fp->conn, fp->tcon); + return -EBADF; + } + + if (has_file_id(fp->volatile_id)) { + pr_err("Still in use durable fd: %llu\n", fp->volatile_id); + return -EBADF; + } + + fp->conn = work->conn; + fp->tcon = work->tcon; + + ci = fp->f_ci; + down_write(&ci->m_lock); + list_for_each_entry_rcu(op, &ci->m_op_list, op_entry) { + if (op->conn) + continue; + op->conn = fp->conn; + } + up_write(&ci->m_lock); + + __open_id(&work->sess->file_table, fp, OPEN_ID_TYPE_VOLATILE_ID); + if (!has_file_id(fp->volatile_id)) { + fp->conn = NULL; + fp->tcon = NULL; + return -EBADF; + } + return 0; +} + int ksmbd_init_file_table(struct ksmbd_file_table *ft) { ft->idr = kzalloc(sizeof(struct idr), GFP_KERNEL); diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index a528f0cc775a..5a225e7055f1 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -14,6 +14,7 @@ #include <linux/workqueue.h> #include "vfs.h" +#include "mgmt/share_config.h" /* Windows style file permissions for extended response */ #define FILE_GENERIC_ALL 0x1F01FF @@ -46,7 +47,7 @@ struct stream { }; struct ksmbd_inode { - rwlock_t m_lock; + struct rw_semaphore m_lock; atomic_t m_count; atomic_t op_count; /* opinfo count for streams */ @@ -106,6 +107,9 @@ struct ksmbd_file { int dot_dotdot[2]; unsigned int f_state; bool reserve_lease_break; + bool is_durable; + bool is_persistent; + bool is_resilient; }; static inline void set_ctx_actor(struct dir_context *ctx, @@ -141,7 +145,9 @@ struct ksmbd_file *ksmbd_lookup_fd_slow(struct ksmbd_work *work, u64 id, void ksmbd_fd_put(struct ksmbd_work *work, struct ksmbd_file *fp); struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d); void ksmbd_inode_put(struct ksmbd_inode *ci); +struct ksmbd_file *ksmbd_lookup_global_fd(unsigned long long id); struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id); +void ksmbd_put_durable_fd(struct ksmbd_file *fp); struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid); struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry); unsigned int ksmbd_open_durable_fd(struct ksmbd_file *fp); @@ -173,6 +179,9 @@ void ksmbd_set_inode_pending_delete(struct ksmbd_file *fp); void ksmbd_clear_inode_pending_delete(struct ksmbd_file *fp); void ksmbd_fd_set_delete_on_close(struct ksmbd_file *fp, int file_info); +int ksmbd_reopen_durable_fd(struct ksmbd_work *work, struct ksmbd_file *fp); +int ksmbd_validate_name_reconnect(struct ksmbd_share_config *share, + struct ksmbd_file *fp, char *name); int ksmbd_init_file_cache(void); void ksmbd_exit_file_cache(void); #endif /* __VFS_CACHE_H__ */ |