diff options
Diffstat (limited to 'fs/smb/client/cifsfs.c')
| -rw-r--r-- | fs/smb/client/cifsfs.c | 565 |
1 files changed, 434 insertions, 131 deletions
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 6fc8f43b1c9d..d9664634144d 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -25,8 +25,11 @@ #include <linux/freezer.h> #include <linux/namei.h> #include <linux/random.h> +#include <linux/splice.h> #include <linux/uuid.h> #include <linux/xattr.h> +#include <linux/mm.h> +#include <linux/key-type.h> #include <uapi/linux/magic.h> #include <net/ipv6.h> #include "cifsfs.h" @@ -34,10 +37,9 @@ #define DECLARE_GLOBALS_HERE #include "cifsglob.h" #include "cifsproto.h" +#include "smb2proto.h" #include "cifs_debug.h" #include "cifs_fs_sb.h" -#include <linux/mm.h> -#include <linux/key-type.h> #include "cifs_spnego.h" #include "fscache.h" #ifdef CONFIG_CIFS_DFS_UPCALL @@ -69,15 +71,14 @@ bool require_gcm_256; /* false by default */ bool enable_negotiate_signing; /* false by default */ unsigned int global_secflags = CIFSSEC_DEF; /* unsigned int ntlmv2_support = 0; */ -unsigned int sign_CIFS_PDUs = 1; /* * Global transaction id (XID) information */ -unsigned int GlobalCurrentXid; /* protected by GlobalMid_Sem */ -unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Sem */ -unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Sem */ -spinlock_t GlobalMid_Lock; /* protects above & list operations on midQ entries */ +unsigned int GlobalCurrentXid; /* protected by GlobalMid_Lock */ +unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Lock */ +unsigned int GlobalMaxActiveXid; /* prot by GlobalMid_Lock */ +DEFINE_SPINLOCK(GlobalMid_Lock); /* protects above & list operations on midQ entries */ /* * Global counters, updated atomically @@ -97,7 +98,7 @@ atomic_t total_buf_alloc_count; atomic_t total_small_buf_alloc_count; #endif/* STATS2 */ struct list_head cifs_tcp_ses_list; -spinlock_t cifs_tcp_ses_lock; +DEFINE_SPINLOCK(cifs_tcp_ses_lock); static const struct super_operations cifs_super_ops; unsigned int CIFSMaxBufSize = CIFS_MAX_MSGSIZE; module_param(CIFSMaxBufSize, uint, 0444); @@ -117,6 +118,50 @@ module_param(cifs_max_pending, uint, 0444); MODULE_PARM_DESC(cifs_max_pending, "Simultaneous requests to server for " "CIFS/SMB1 dialect (N/A for SMB3) " "Default: 32767 Range: 2 to 32767."); +unsigned int dir_cache_timeout = 30; +module_param(dir_cache_timeout, uint, 0644); +MODULE_PARM_DESC(dir_cache_timeout, "Number of seconds to cache directory contents for which we have a lease. Default: 30 " + "Range: 1 to 65000 seconds, 0 to disable caching dir contents"); +/* Module-wide total cached dirents (in bytes) across all tcons */ +atomic64_t cifs_dircache_bytes_used = ATOMIC64_INIT(0); + +/* + * Write-only module parameter to drop all cached directory entries across + * all CIFS mounts. Echo a non-zero value to trigger. + */ +static void cifs_drop_all_dir_caches(void) +{ + struct TCP_Server_Info *server; + struct cifs_ses *ses; + struct cifs_tcon *tcon; + + 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) + invalidate_all_cached_dirs(tcon); + } + } + spin_unlock(&cifs_tcp_ses_lock); +} + +static int cifs_param_set_drop_dir_cache(const char *val, const struct kernel_param *kp) +{ + bool bv; + int rc = kstrtobool(val, &bv); + + if (rc) + return rc; + if (bv) + cifs_drop_all_dir_caches(); + return 0; +} + +module_param_call(drop_dir_cache, cifs_param_set_drop_dir_cache, NULL, NULL, 0200); +MODULE_PARM_DESC(drop_dir_cache, "Write 1 to drop all cached directory entries across all CIFS mounts"); + #ifdef CONFIG_CIFS_STATS2 unsigned int slow_rsp_threshold = 1; module_param(slow_rsp_threshold, uint, 0644); @@ -129,7 +174,7 @@ module_param(enable_oplocks, bool, 0644); MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks. Default: y/Y/1"); module_param(enable_gcm_256, bool, 0644); -MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: n/N/0"); +MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: y/Y/1"); module_param(require_gcm_256, bool, 0644); MODULE_PARM_DESC(require_gcm_256, "Require strongest (256 bit) GCM encryption. Default: n/N/0"); @@ -146,20 +191,18 @@ 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; +struct workqueue_struct *cfid_put_wq; __u32 cifs_lock_secret; /* * Bumps refcount for cifs super block. - * Note that it should be only called if a referece to VFS super block is + * Note that it should be only called if a reference to VFS super block is * already held, e.g. in open-type syscalls context. Otherwise it can race with * atomic_dec_and_test in deactivate_locked_super. */ @@ -258,9 +301,9 @@ cifs_read_super(struct super_block *sb) } if (tcon->nocase) - sb->s_d_op = &cifs_ci_dentry_ops; + set_default_d_op(sb, &cifs_ci_dentry_ops); else - sb->s_d_op = &cifs_dentry_ops; + set_default_d_op(sb, &cifs_dentry_ops); sb->s_root = d_make_root(inode); if (!sb->s_root) { @@ -287,7 +330,7 @@ static void cifs_kill_sb(struct super_block *sb) struct cifs_sb_info *cifs_sb = CIFS_SB(sb); /* - * We ned to release all dentries for the cached directories + * We need to release all dentries for the cached directories * before we kill the sb. */ if (cifs_sb->root) { @@ -311,8 +354,17 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf) struct TCP_Server_Info *server = tcon->ses->server; unsigned int xid; int rc = 0; + const char *full_path; + void *page; xid = get_xid(); + page = alloc_dentry_path(); + + full_path = build_path_from_dentry(dentry, page); + if (IS_ERR(full_path)) { + rc = PTR_ERR(full_path); + goto statfs_out; + } if (le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength) > 0) buf->f_namelen = @@ -328,8 +380,10 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_ffree = 0; /* unlimited */ if (server->ops->queryfs) - rc = server->ops->queryfs(xid, tcon, cifs_sb, buf); + rc = server->ops->queryfs(xid, tcon, full_path, cifs_sb, buf); +statfs_out: + free_dentry_path(page); free_xid(xid); return rc; } @@ -339,11 +393,27 @@ static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len) struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct TCP_Server_Info *server = tcon->ses->server; + struct inode *inode = file_inode(file); + int rc; + + if (!server->ops->fallocate) + return -EOPNOTSUPP; + + rc = inode_lock_killable(inode); + if (rc) + return rc; - if (server->ops->fallocate) - return server->ops->fallocate(file, tcon, mode, off, len); + netfs_wait_for_outstanding_io(inode); - return -EOPNOTSUPP; + rc = file_modified(file); + if (rc) + goto out_unlock; + + rc = server->ops->fallocate(file, tcon, mode, off, len); + +out_unlock: + inode_unlock(inode); + return rc; } static int cifs_permission(struct mnt_idmap *idmap, @@ -369,9 +439,13 @@ 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_mid_pool; +mempool_t cifs_io_request_pool; +mempool_t cifs_io_subrequest_pool; static struct inode * cifs_alloc_inode(struct super_block *sb) @@ -380,18 +454,19 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode = alloc_inode_sb(sb, cifs_inode_cachep, GFP_KERNEL); if (!cifs_inode) return NULL; - cifs_inode->cifsAttrs = 0x20; /* default */ + cifs_inode->cifsAttrs = ATTR_ARCHIVE; /* default */ cifs_inode->time = 0; /* * Until the file is open and we have gotten oplock info back from the * server, can not assume caching of file data or metadata. */ 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; cifs_inode->netfs.inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */ - cifs_inode->server_eof = 0; + cifs_inode->netfs.remote_i_size = 0; cifs_inode->uniqueid = 0; cifs_inode->createtime = 0; cifs_inode->epoch = 0; @@ -424,8 +499,9 @@ cifs_free_inode(struct inode *inode) static void cifs_evict_inode(struct inode *inode) { + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); - if (inode->i_state & I_PINNING_FSCACHE_WB) + if (inode_state_read_once(inode) & I_PINNING_NETFS_WB) cifs_fscache_unuse_inode_cookie(inode, true); cifs_fscache_release_inode_cookie(inode); clear_inode(inode); @@ -527,6 +603,30 @@ static int cifs_show_devname(struct seq_file *m, struct dentry *root) return 0; } +static void +cifs_show_upcall_target(struct seq_file *s, struct cifs_sb_info *cifs_sb) +{ + if (cifs_sb->ctx->upcall_target == UPTARGET_UNSPECIFIED) { + seq_puts(s, ",upcall_target=app"); + return; + } + + seq_puts(s, ",upcall_target="); + + switch (cifs_sb->ctx->upcall_target) { + case UPTARGET_APP: + seq_puts(s, "app"); + break; + case UPTARGET_MOUNT: + seq_puts(s, "mount"); + break; + default: + /* shouldn't ever happen */ + seq_puts(s, "unknown"); + break; + } +} + /* * cifs_show_options() is for displaying mount options in /proc/mounts. * Not all settable options are displayed but most of the important @@ -543,6 +643,7 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_show_option(s, "vers", tcon->ses->server->vals->version_string); cifs_show_security(s, tcon->ses); cifs_show_cache_flavor(s, cifs_sb); + cifs_show_upcall_target(s, cifs_sb); if (tcon->no_lease) seq_puts(s, ",nolease"); @@ -592,6 +693,10 @@ cifs_show_options(struct seq_file *s, struct dentry *root) cifs_sb->ctx->dir_mode); if (cifs_sb->ctx->iocharset) seq_printf(s, ",iocharset=%s", cifs_sb->ctx->iocharset); + if (tcon->ses->unicode == 0) + seq_puts(s, ",nounicode"); + else if (tcon->ses->unicode == 1) + seq_puts(s, ",unicode"); if (tcon->seal) seq_puts(s, ",seal"); else if (tcon->ses->server->ignore_signature) @@ -668,6 +773,14 @@ 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)); + if (cifs_sb->ctx->nonativesocket) + seq_puts(s, ",nonativesocket"); + else + seq_puts(s, ",nativesocket"); + seq_show_option(s, "symlink", + cifs_symlink_type_str(cifs_symlink_type(cifs_sb))); seq_printf(s, ",rsize=%u", cifs_sb->ctx->rsize); seq_printf(s, ",wsize=%u", cifs_sb->ctx->wsize); @@ -676,6 +789,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_printf(s, ",rasize=%u", cifs_sb->ctx->rasize); if (tcon->ses->server->min_offload) seq_printf(s, ",esize=%u", tcon->ses->server->min_offload); + if (tcon->ses->server->retrans) + seq_printf(s, ",retrans=%u", tcon->ses->server->retrans); seq_printf(s, ",echo_interval=%lu", tcon->ses->server->echo_interval / HZ); @@ -695,6 +810,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_printf(s, ",snapshot=%llu", tcon->snapshot_time); if (tcon->handle_timeout) seq_printf(s, ",handletimeout=%u", tcon->handle_timeout); + if (tcon->max_cached_dirs != MAX_CACHED_FIDS) + seq_printf(s, ",max_cached_dirs=%u", tcon->max_cached_dirs); /* * Display file and directory attribute timeout in seconds. @@ -731,6 +848,8 @@ 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 @@ -786,8 +905,7 @@ static int cifs_show_stats(struct seq_file *s, struct dentry *root) static int cifs_write_inode(struct inode *inode, struct writeback_control *wbc) { - fscache_unpin_writeback(wbc, cifs_inode_cookie(inode)); - return 0; + return netfs_unpin_writeback(inode, wbc); } static int cifs_drop_inode(struct inode *inode) @@ -796,7 +914,7 @@ static int cifs_drop_inode(struct inode *inode) /* no serverino => unconditional eviction */ return !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) || - generic_drop_inode(inode); + inode_generic_drop(inode); } static const struct super_operations cifs_super_ops = { @@ -867,7 +985,8 @@ cifs_get_root(struct smb3_fs_context *ctx, struct super_block *sb) while (*s && *s != sep) s++; - child = lookup_positive_unlocked(p, dentry, s - p); + child = lookup_noperm_positive_unlocked(&QSTR_LEN(p, s - p), + dentry); dput(dentry); dentry = child; } while (!IS_ERR(dentry)); @@ -898,7 +1017,6 @@ cifs_smb3_do_mount(struct file_system_type *fs_type, } else { cifs_info("Attempting to mount %s\n", old_ctx->source); } - cifs_sb = kzalloc(sizeof(*cifs_sb), GFP_KERNEL); if (!cifs_sb) return ERR_PTR(-ENOMEM); @@ -976,61 +1094,6 @@ 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; @@ -1077,7 +1140,7 @@ 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 @@ -1086,7 +1149,7 @@ 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))) + if (!S_ISREG(inode->i_mode)) return -EINVAL; /* Check if file is oplocked if this is request for new lease */ @@ -1164,6 +1227,9 @@ const char *cifs_get_link(struct dentry *dentry, struct inode *inode, { char *target_path; + if (!dentry) + return ERR_PTR(-ECHILD); + target_path = kmalloc(PATH_MAX, GFP_KERNEL); if (!target_path) return ERR_PTR(-ENOMEM); @@ -1185,36 +1251,108 @@ const char *cifs_get_link(struct dentry *dentry, struct inode *inode, const struct inode_operations cifs_symlink_inode_ops = { .get_link = cifs_get_link, + .setattr = cifs_setattr, .permission = cifs_permission, .listxattr = cifs_listxattr, }; +/* + * Advance the EOF marker to after the source range. + */ +static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *src_cifsi, + struct cifs_tcon *src_tcon, + unsigned int xid, loff_t src_end) +{ + struct cifsFileInfo *writeable_srcfile; + int rc = -EINVAL; + + writeable_srcfile = find_writable_file(src_cifsi, FIND_WR_FSUID_ONLY); + if (writeable_srcfile) { + if (src_tcon->ses->server->ops->set_file_size) + rc = src_tcon->ses->server->ops->set_file_size( + xid, src_tcon, writeable_srcfile, + src_inode->i_size, true /* no need to set sparse */); + else + rc = -ENOSYS; + cifsFileInfo_put(writeable_srcfile); + cifs_dbg(FYI, "SetFSize for copychunk rc = %d\n", rc); + } + + if (rc < 0) + goto set_failed; + + netfs_resize_file(&src_cifsi->netfs, src_end, true); + fscache_resize_cookie(cifs_inode_cookie(src_inode), src_end); + return 0; + +set_failed: + return filemap_write_and_wait(src_inode->i_mapping); +} + +/* + * Flush out either the folio that overlaps the beginning of a range in which + * pos resides or the folio that overlaps the end of a range unless that folio + * is entirely within the range we're going to invalidate. We extend the flush + * bounds to encompass the folio. + */ +static int cifs_flush_folio(struct inode *inode, loff_t pos, loff_t *_fstart, loff_t *_fend, + bool first) +{ + struct folio *folio; + unsigned long long fpos, fend; + pgoff_t index = pos / PAGE_SIZE; + size_t size; + int rc = 0; + + folio = filemap_get_folio(inode->i_mapping, index); + if (IS_ERR(folio)) + return 0; + + size = folio_size(folio); + fpos = folio_pos(folio); + fend = fpos + size - 1; + *_fstart = min_t(unsigned long long, *_fstart, fpos); + *_fend = max_t(unsigned long long, *_fend, fend); + if ((first && pos == fpos) || (!first && pos == fend)) + goto out; + + rc = filemap_write_and_wait_range(inode->i_mapping, fpos, fend); +out: + folio_put(folio); + return rc; +} + static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, struct file *dst_file, loff_t destoff, loff_t len, unsigned int remap_flags) { struct inode *src_inode = file_inode(src_file); struct inode *target_inode = file_inode(dst_file); + struct cifsInodeInfo *src_cifsi = CIFS_I(src_inode); + struct cifsInodeInfo *target_cifsi = CIFS_I(target_inode); struct cifsFileInfo *smb_file_src = src_file->private_data; - struct cifsFileInfo *smb_file_target; - struct cifs_tcon *target_tcon; + struct cifsFileInfo *smb_file_target = dst_file->private_data; + struct cifs_tcon *target_tcon, *src_tcon; + unsigned long long destend, fstart, fend, old_size, new_size; unsigned int xid; int rc; - if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) + if (remap_flags & REMAP_FILE_DEDUP) + return -EOPNOTSUPP; + if (remap_flags & ~REMAP_FILE_ADVISORY) return -EINVAL; cifs_dbg(FYI, "clone range\n"); xid = get_xid(); - if (!src_file->private_data || !dst_file->private_data) { + if (!smb_file_src || !smb_file_target) { rc = -EBADF; cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); goto out; } - smb_file_target = dst_file->private_data; + src_tcon = tlink_tcon(smb_file_src->tlink); target_tcon = tlink_tcon(smb_file_target->tlink); /* @@ -1227,20 +1365,81 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, if (len == 0) len = src_inode->i_size - off; - cifs_dbg(FYI, "about to flush pages\n"); - /* should we flush first and last page first */ - truncate_inode_pages_range(&target_inode->i_data, destoff, - PAGE_ALIGN(destoff + len)-1); + cifs_dbg(FYI, "clone range\n"); + + /* Flush the source buffer */ + rc = filemap_write_and_wait_range(src_inode->i_mapping, off, + off + len - 1); + if (rc) + goto unlock; + + /* The server-side copy will fail if the source crosses the EOF marker. + * Advance the EOF marker after the flush above to the end of the range + * if it's short of that. + */ + if (src_cifsi->netfs.remote_i_size < off + len) { + rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len); + if (rc < 0) + goto unlock; + } + + new_size = destoff + len; + destend = destoff + len - 1; + + /* Flush the folios at either end of the destination range to prevent + * accidental loss of dirty data outside of the range. + */ + fstart = destoff; + fend = destend; + + rc = cifs_flush_folio(target_inode, destoff, &fstart, &fend, true); + if (rc) + goto unlock; + 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); + truncate_inode_pages_range(&target_inode->i_data, fstart, fend); + + fscache_invalidate(cifs_inode_cookie(target_inode), NULL, + i_size_read(target_inode), 0); - if (target_tcon->ses->server->ops->duplicate_extents) + rc = -EOPNOTSUPP; + 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); - else - rc = -EOPNOTSUPP; + if (rc == 0 && new_size > old_size) { + truncate_setsize(target_inode, new_size); + fscache_resize_cookie(cifs_inode_cookie(target_inode), + new_size); + } else if (rc == -EOPNOTSUPP) { + /* + * copy_file_range syscall man page indicates EINVAL + * is returned e.g when "fd_in and fd_out refer to the + * same file and the source and target ranges overlap." + * Test generic/157 was what showed these cases where + * we need to remap EOPNOTSUPP to EINVAL + */ + if (off >= src_inode->i_size) { + rc = -EINVAL; + } else if (src_inode == target_inode) { + if (off + len > destoff) + rc = -EINVAL; + } + } + 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 that target is updated on the server */ CIFS_I(target_inode)->time = 0; +unlock: /* although unlocking in the reverse order from locking is not strictly necessary here it is a little cleaner to be consistent */ unlock_two_nondirectories(src_inode, target_inode); @@ -1256,6 +1455,8 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, { struct inode *src_inode = file_inode(src_file); struct inode *target_inode = file_inode(dst_file); + struct cifsInodeInfo *src_cifsi = CIFS_I(src_inode); + struct cifsInodeInfo *target_cifsi = CIFS_I(target_inode); struct cifsFileInfo *smb_file_src; struct cifsFileInfo *smb_file_target; struct cifs_tcon *src_tcon; @@ -1277,7 +1478,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, target_tcon = tlink_tcon(smb_file_target->tlink); if (src_tcon->ses != target_tcon->ses) { - cifs_dbg(VFS, "source and target of copy not on same server\n"); + cifs_dbg(FYI, "source and target of copy not on same server\n"); goto out; } @@ -1299,13 +1500,41 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, if (rc) goto unlock; - /* should we flush first and last page first */ - truncate_inode_pages(&target_inode->i_data, 0); + /* The server-side copy will fail if the source crosses the EOF marker. + * Advance the EOF marker after the flush above to the end of the range + * if it's short of that. + */ + if (src_cifsi->netfs.remote_i_size < off + len) { + rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len); + if (rc < 0) + goto unlock; + } + + /* Flush and invalidate all the folios in the destination region. If + * the copy was successful, then some of the flush is extra overhead, + * but we need to allow for the copy failing in some way (eg. ENOSPC). + */ + rc = filemap_invalidate_inode(target_inode, true, destoff, destoff + len - 1); + if (rc) + goto unlock; + + fscache_invalidate(cifs_inode_cookie(target_inode), NULL, + i_size_read(target_inode), 0); rc = file_modified(dst_file); - if (!rc) + if (!rc) { rc = target_tcon->ses->server->ops->copychunk_range(xid, smb_file_src, smb_file_target, off, len, destoff); + if (rc > 0 && destoff + rc > i_size_read(target_inode)) { + truncate_setsize(target_inode, destoff + rc); + netfs_resize_file(&target_cifsi->netfs, + i_size_read(target_inode), true); + fscache_resize_cookie(cifs_inode_cookie(target_inode), + i_size_read(target_inode)); + } + if (rc > 0 && destoff + rc > target_cifsi->netfs.zero_point) + target_cifsi->netfs.zero_point = destoff + rc; + } file_accessed(src_file); @@ -1355,8 +1584,8 @@ static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off, free_xid(xid); if (rc == -EOPNOTSUPP || rc == -EXDEV) - rc = generic_copy_file_range(src_file, off, dst_file, - destoff, len, flags); + rc = splice_copy_file_range(src_file, off, dst_file, + destoff, len); return rc; } @@ -1369,7 +1598,7 @@ const struct file_operations cifs_file_ops = { .flock = cifs_flock, .fsync = cifs_fsync, .flush = cifs_flush, - .mmap = cifs_file_mmap, + .mmap_prepare = cifs_file_mmap_prepare, .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = cifs_llseek, @@ -1389,7 +1618,7 @@ const struct file_operations cifs_file_strict_ops = { .flock = cifs_flock, .fsync = cifs_strict_fsync, .flush = cifs_flush, - .mmap = cifs_file_strict_mmap, + .mmap_prepare = cifs_file_strict_mmap_prepare, .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = cifs_llseek, @@ -1401,15 +1630,15 @@ 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, .flock = cifs_flock, .fsync = cifs_fsync, .flush = cifs_flush, - .mmap = cifs_file_mmap, + .mmap_prepare = cifs_file_mmap_prepare, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, .unlocked_ioctl = cifs_ioctl, @@ -1427,7 +1656,7 @@ const struct file_operations cifs_file_nobrl_ops = { .release = cifs_close, .fsync = cifs_fsync, .flush = cifs_flush, - .mmap = cifs_file_mmap, + .mmap_prepare = cifs_file_mmap_prepare, .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = cifs_llseek, @@ -1445,7 +1674,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = { .release = cifs_close, .fsync = cifs_strict_fsync, .flush = cifs_flush, - .mmap = cifs_file_strict_mmap, + .mmap_prepare = cifs_file_strict_mmap_prepare, .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = cifs_llseek, @@ -1457,13 +1686,13 @@ 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, .flush = cifs_flush, - .mmap = cifs_file_mmap, + .mmap_prepare = cifs_file_mmap_prepare, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, .unlocked_ioctl = cifs_ioctl, @@ -1500,7 +1729,7 @@ 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; @@ -1618,8 +1847,7 @@ static int init_mids(void) return -ENOMEM; /* 3 is a reasonable minimum number of simultaneous operations */ - cifs_mid_poolp = mempool_create_slab_pool(3, cifs_mid_cachep); - if (cifs_mid_poolp == NULL) { + if (mempool_init_slab_pool(&cifs_mid_pool, 3, cifs_mid_cachep) < 0) { kmem_cache_destroy(cifs_mid_cachep); return -ENOMEM; } @@ -1629,10 +1857,52 @@ static int init_mids(void) static void destroy_mids(void) { - mempool_destroy(cifs_mid_poolp); + mempool_exit(&cifs_mid_pool); 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_exit(&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) { @@ -1665,8 +1935,6 @@ init_cifs(void) GlobalCurrentXid = 0; GlobalTotalActiveXid = 0; GlobalMaxActiveXid = 0; - spin_lock_init(&cifs_tcp_ses_lock); - spin_lock_init(&GlobalMid_Lock); cifs_lock_secret = get_random_u32(); @@ -1679,7 +1947,15 @@ init_cifs(void) CIFS_MAX_REQ); } - cifsiod_wq = alloc_workqueue("cifsiod", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); + /* Limit max to about 18 hours, and setting to zero disables directory entry caching */ + if (dir_cache_timeout > 65000) { + dir_cache_timeout = 65000; + cifs_dbg(VFS, "dir_cache_timeout set to max of 65000 seconds\n"); + } + + cifsiod_wq = alloc_workqueue("cifsiod", + WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU, + 0); if (!cifsiod_wq) { rc = -ENOMEM; goto out_clean_proc; @@ -1707,27 +1983,49 @@ init_cifs(void) } cifsoplockd_wq = alloc_workqueue("cifsoplockd", - WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); + WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU, + 0); if (!cifsoplockd_wq) { rc = -ENOMEM; goto out_destroy_fileinfo_put_wq; } deferredclose_wq = alloc_workqueue("deferredclose", - WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); + WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU, + 0); if (!deferredclose_wq) { rc = -ENOMEM; goto out_destroy_cifsoplockd_wq; } + serverclose_wq = alloc_workqueue("serverclose", + WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU, + 0); + if (!serverclose_wq) { + rc = -ENOMEM; + goto out_destroy_deferredclose_wq; + } + + cfid_put_wq = alloc_workqueue("cfid_put_wq", + WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU, + 0); + if (!cfid_put_wq) { + rc = -ENOMEM; + goto out_destroy_serverclose_wq; + } + rc = cifs_init_inodecache(); if (rc) - goto out_destroy_deferredclose_wq; + goto out_destroy_cfid_put_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; @@ -1782,8 +2080,14 @@ 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_cfid_put_wq: + destroy_workqueue(cfid_put_wq); +out_destroy_serverclose_wq: + destroy_workqueue(serverclose_wq); out_destroy_deferredclose_wq: destroy_workqueue(deferredclose_wq); out_destroy_cifsoplockd_wq: @@ -1805,7 +2109,7 @@ exit_cifs(void) cifs_dbg(NOISY, "exit_smb3\n"); unregister_filesystem(&cifs_fs_type); unregister_filesystem(&smb3_fs_type); - cifs_dfs_release_automount_timer(); + cifs_release_automount_timer(); exit_cifs_idmap(); #ifdef CONFIG_CIFS_SWN_UPCALL cifs_genl_exit(); @@ -1818,11 +2122,14 @@ 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(cfid_put_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } @@ -1834,13 +2141,9 @@ MODULE_DESCRIPTION "also older servers complying with the SNIA CIFS Specification)"); MODULE_VERSION(CIFS_VERSION); MODULE_SOFTDEP("ecb"); -MODULE_SOFTDEP("hmac"); -MODULE_SOFTDEP("md5"); MODULE_SOFTDEP("nls"); MODULE_SOFTDEP("aes"); MODULE_SOFTDEP("cmac"); -MODULE_SOFTDEP("sha256"); -MODULE_SOFTDEP("sha512"); MODULE_SOFTDEP("aead2"); MODULE_SOFTDEP("ccm"); MODULE_SOFTDEP("gcm"); |