Merge tag '4.20-rc1-smb3-fixes' of git://git.samba.org/sfrench/cifs-2.6

Pull cifs fixes and updates from Steve French:
 "Three small fixes (one Kerberos related, one for stable, and another
  fixes an oops in xfstest 377), two helpful debugging improvements,
  three patches for cifs directio and some minor cleanup"

* tag '4.20-rc1-smb3-fixes' of git://git.samba.org/sfrench/cifs-2.6:
  cifs: fix signed/unsigned mismatch on aio_read patch
  cifs: don't dereference smb_file_target before null check
  CIFS: Add direct I/O functions to file_operations
  CIFS: Add support for direct I/O write
  CIFS: Add support for direct I/O read
  smb3: missing defines and structs for reparse point handling
  smb3: allow more detailed protocol info on open files for debugging
  smb3: on kerberos mount if server doesn't specify auth type use krb5
  smb3: add trace point for tree connection
  cifs: fix spelling mistake, EACCESS -> EACCES
  cifs: fix return value for cifs_listxattr

fs/cifs/cifs_debug.c

@@ -145,6 +145,58 @@ cifs_dump_iface(struct seq_file *m, struct cifs_server_iface *iface)
 		seq_printf(m, "\t\tIPv6: %pI6\n", &ipv6->sin6_addr);
 }
 
+static int cifs_debug_files_proc_show(struct seq_file *m, void *v)
+{
+	struct list_head *stmp, *tmp, *tmp1, *tmp2;
+	struct TCP_Server_Info *server;
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
+	struct cifsFileInfo *cfile;
+
+	seq_puts(m, "# Version:1\n");
+	seq_puts(m, "# Format:\n");
+	seq_puts(m, "# <tree id> <persistent fid> <flags> <count> <pid> <uid>");
+#ifdef CONFIG_CIFS_DEBUG2
+	seq_printf(m, " <filename> <mid>\n");
+#else
+	seq_printf(m, " <filename>\n");
+#endif /* CIFS_DEBUG2 */
+	spin_lock(&cifs_tcp_ses_lock);
+	list_for_each(stmp, &cifs_tcp_ses_list) {
+		server = list_entry(stmp, struct TCP_Server_Info,
+				    tcp_ses_list);
+		list_for_each(tmp, &server->smb_ses_list) {
+			ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
+			list_for_each(tmp1, &ses->tcon_list) {
+				tcon = list_entry(tmp1, struct cifs_tcon, tcon_list);
+				spin_lock(&tcon->open_file_lock);
+				list_for_each(tmp2, &tcon->openFileList) {
+					cfile = list_entry(tmp2, struct cifsFileInfo,
+						     tlist);
+					seq_printf(m,
+						"0x%x 0x%llx 0x%x %d %d %d %s",
+						tcon->tid,
+						cfile->fid.persistent_fid,
+						cfile->f_flags,
+						cfile->count,
+						cfile->pid,
+						from_kuid(&init_user_ns, cfile->uid),
+						cfile->dentry->d_name.name);
+#ifdef CONFIG_CIFS_DEBUG2
+					seq_printf(m, " 0x%llx\n", cfile->fid.mid);
+#else
+					seq_printf(m, "\n");
+#endif /* CIFS_DEBUG2 */
+				}
+				spin_unlock(&tcon->open_file_lock);
+			}
+		}
+	}
+	spin_unlock(&cifs_tcp_ses_lock);
+	seq_putc(m, '\n');
+	return 0;
+}
+
 static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 {
 	struct list_head *tmp1, *tmp2, *tmp3;
@@ -565,6 +617,9 @@ cifs_proc_init(void)
 	proc_create_single("DebugData", 0, proc_fs_cifs,
 			cifs_debug_data_proc_show);
 
+	proc_create_single("open_files", 0400, proc_fs_cifs,
+			cifs_debug_files_proc_show);
+
 	proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_fops);
 	proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_fops);
 	proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_fops);
@@ -601,6 +656,7 @@ cifs_proc_clean(void)
 		return;
 
 	remove_proc_entry("DebugData", proc_fs_cifs);
+	remove_proc_entry("open_files", proc_fs_cifs);
 	remove_proc_entry("cifsFYI", proc_fs_cifs);
 	remove_proc_entry("traceSMB", proc_fs_cifs);
 	remove_proc_entry("Stats", proc_fs_cifs);

fs/cifs/cifs_spnego.c

@@ -147,8 +147,10 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo)
 		sprintf(dp, ";sec=krb5");
 	else if (server->sec_mskerberos)
 		sprintf(dp, ";sec=mskrb5");
-	else
-		goto out;
+	else {
+		cifs_dbg(VFS, "unknown or missing server auth type, use krb5\n");
+		sprintf(dp, ";sec=krb5");
+	}
 
 	dp = description + strlen(description);
 	sprintf(dp, ";uid=0x%x",

fs/cifs/cifsfs.c

@@ -999,8 +999,8 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 	struct inode *src_inode = file_inode(src_file);
 	struct inode *target_inode = file_inode(dst_file);
 	struct cifsFileInfo *smb_file_src = src_file->private_data;
-	struct cifsFileInfo *smb_file_target = dst_file->private_data;
-	struct cifs_tcon *target_tcon = tlink_tcon(smb_file_target->tlink);
+	struct cifsFileInfo *smb_file_target;
+	struct cifs_tcon *target_tcon;
 	unsigned int xid;
 	int rc;
 
@@ -1017,6 +1017,9 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 		goto out;
 	}
 
+	smb_file_target = dst_file->private_data;
+	target_tcon = tlink_tcon(smb_file_target->tlink);
+
 	/*
 	 * Note: cifs case is easier than btrfs since server responsible for
 	 * checks for proper open modes and file type and if it wants
@@ -1180,9 +1183,8 @@ const struct file_operations cifs_file_strict_ops = {
 };
 
 const struct file_operations cifs_file_direct_ops = {
-	/* BB reevaluate whether they can be done with directio, no cache */
-	.read_iter = cifs_user_readv,
-	.write_iter = cifs_user_writev,
+	.read_iter = cifs_direct_readv,
+	.write_iter = cifs_direct_writev,
 	.open = cifs_open,
 	.release = cifs_close,
 	.lock = cifs_lock,
@@ -1236,9 +1238,8 @@ const struct file_operations cifs_file_strict_nobrl_ops = {
 };
 
 const struct file_operations cifs_file_direct_nobrl_ops = {
-	/* BB reevaluate whether they can be done with directio, no cache */
-	.read_iter = cifs_user_readv,
-	.write_iter = cifs_user_writev,
+	.read_iter = cifs_direct_readv,
+	.write_iter = cifs_direct_writev,
 	.open = cifs_open,
 	.release = cifs_close,
 	.fsync = cifs_fsync,

fs/cifs/cifsfs.h

@@ -101,8 +101,10 @@ 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);
 extern int cifs_lock(struct file *, int, struct file_lock *);
 extern int cifs_fsync(struct file *, loff_t, loff_t, int);

fs/cifs/cifsglob.h

@@ -1125,6 +1125,9 @@ struct cifs_fid {
 	__u8 create_guid[16];
 	struct cifs_pending_open *pending_open;
 	unsigned int epoch;
+#ifdef CONFIG_CIFS_DEBUG2
+	__u64 mid;
+#endif /* CIFS_DEBUG2 */
 	bool purge_cache;
 };
 
@@ -1183,6 +1186,11 @@ struct cifs_aio_ctx {
 	unsigned int		len;
 	unsigned int		total_len;
 	bool			should_dirty;
+	/*
+	 * Indicates if this aio_ctx is for direct_io,
+	 * If yes, iter is a copy of the user passed iov_iter
+	 */
+	bool			direct_io;
 };
 
 struct cifs_readdata;

fs/cifs/cifspdu.h

@@ -1539,6 +1539,9 @@ struct reparse_symlink_data {
 	char	PathBuffer[0];
 } __attribute__((packed));
 
+/* Flag above */
+#define SYMLINK_FLAG_RELATIVE 0x00000001
+
 /* For IO_REPARSE_TAG_NFS */
 #define NFS_SPECFILE_LNK	0x00000000014B4E4C
 #define NFS_SPECFILE_CHR	0x0000000000524843

fs/cifs/file.c

@@ -1005,7 +1005,7 @@ cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock)
  * Set the byte-range lock (mandatory style). Returns:
  * 1) 0, if we set the lock and don't need to request to the server;
  * 2) 1, if no locks prevent us but we need to request to the server;
- * 3) -EACCESS, if there is a lock that prevents us and wait is false.
+ * 3) -EACCES, if there is a lock that prevents us and wait is false.
  */
 static int
 cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock,
@@ -2537,6 +2537,61 @@ wdata_fill_from_iovec(struct cifs_writedata *wdata, struct iov_iter *from,
 	return 0;
 }
 
+static int
+cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list,
+	struct cifs_aio_ctx *ctx)
+{
+	int wait_retry = 0;
+	unsigned int wsize, credits;
+	int rc;
+	struct TCP_Server_Info *server =
+		tlink_tcon(wdata->cfile->tlink)->ses->server;
+
+	/*
+	 * Try to resend this wdata, waiting for credits up to 3 seconds.
+	 * 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)
+			break;
+
+		if (wsize < wdata->bytes) {
+			add_credits_and_wake_if(server, credits, 0);
+			msleep(1000);
+			wait_retry++;
+		}
+	} while (wsize < wdata->bytes && wait_retry < 3);
+
+	if (wsize < wdata->bytes) {
+		rc = -EBUSY;
+		goto out;
+	}
+
+	rc = -EAGAIN;
+	while (rc == -EAGAIN) {
+		rc = 0;
+		if (wdata->cfile->invalidHandle)
+			rc = cifs_reopen_file(wdata->cfile, false);
+		if (!rc)
+			rc = server->ops->async_writev(wdata,
+					cifs_uncached_writedata_release);
+	}
+
+	if (!rc) {
+		list_add_tail(&wdata->list, wdata_list);
+		return 0;
+	}
+
+	add_credits_and_wake_if(server, wdata->credits, 0);
+out:
+	kref_put(&wdata->refcount, cifs_uncached_writedata_release);
+
+	return rc;
+}
+
 static int
 cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 		     struct cifsFileInfo *open_file,
@@ -2551,6 +2606,8 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 	loff_t saved_offset = offset;
 	pid_t pid;
 	struct TCP_Server_Info *server;
+	struct page **pagevec;
+	size_t start;
 
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
 		pid = open_file->pid;
@@ -2567,38 +2624,79 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 		if (rc)
 			break;
 
-		nr_pages = get_numpages(wsize, len, &cur_len);
-		wdata = cifs_writedata_alloc(nr_pages,
+		if (ctx->direct_io) {
+			ssize_t result;
+
+			result = iov_iter_get_pages_alloc(
+				from, &pagevec, wsize, &start);
+			if (result < 0) {
+				cifs_dbg(VFS,
+					"direct_writev couldn't get user pages "
+					"(rc=%zd) iter type %d iov_offset %zd "
+					"count %zd\n",
+					result, from->type,
+					from->iov_offset, from->count);
+				dump_stack();
+				break;
+			}
+			cur_len = (size_t)result;
+			iov_iter_advance(from, cur_len);
+
+			nr_pages =
+				(cur_len + start + PAGE_SIZE - 1) / PAGE_SIZE;
+
+			wdata = cifs_writedata_direct_alloc(pagevec,
 					     cifs_uncached_writev_complete);
-		if (!wdata) {
-			rc = -ENOMEM;
-			add_credits_and_wake_if(server, credits, 0);
-			break;
-		}
+			if (!wdata) {
+				rc = -ENOMEM;
+				add_credits_and_wake_if(server, credits, 0);
+				break;
+			}
 
-		rc = cifs_write_allocate_pages(wdata->pages, nr_pages);
-		if (rc) {
-			kfree(wdata);
-			add_credits_and_wake_if(server, credits, 0);
-			break;
-		}
 
-		num_pages = nr_pages;
-		rc = wdata_fill_from_iovec(wdata, from, &cur_len, &num_pages);
-		if (rc) {
-			for (i = 0; i < nr_pages; i++)
-				put_page(wdata->pages[i]);
-			kfree(wdata);
-			add_credits_and_wake_if(server, credits, 0);
-			break;
-		}
+			wdata->page_offset = start;
+			wdata->tailsz =
+				nr_pages > 1 ?
+					cur_len - (PAGE_SIZE - start) -
+					(nr_pages - 2) * PAGE_SIZE :
+					cur_len;
+		} else {
+			nr_pages = get_numpages(wsize, len, &cur_len);
+			wdata = cifs_writedata_alloc(nr_pages,
+					     cifs_uncached_writev_complete);
+			if (!wdata) {
+				rc = -ENOMEM;
+				add_credits_and_wake_if(server, credits, 0);
+				break;
+			}
 
-		/*
-		 * Bring nr_pages down to the number of pages we actually used,
-		 * and free any pages that we didn't use.
-		 */
-		for ( ; nr_pages > num_pages; nr_pages--)
-			put_page(wdata->pages[nr_pages - 1]);
+			rc = cifs_write_allocate_pages(wdata->pages, nr_pages);
+			if (rc) {
+				kfree(wdata);
+				add_credits_and_wake_if(server, credits, 0);
+				break;
+			}
+
+			num_pages = nr_pages;
+			rc = wdata_fill_from_iovec(
+				wdata, from, &cur_len, &num_pages);
+			if (rc) {
+				for (i = 0; i < nr_pages; i++)
+					put_page(wdata->pages[i]);
+				kfree(wdata);
+				add_credits_and_wake_if(server, credits, 0);
+				break;
+			}
+
+			/*
+			 * Bring nr_pages down to the number of pages we
+			 * actually used, and free any pages that we didn't use.
+			 */
+			for ( ; nr_pages > num_pages; nr_pages--)
+				put_page(wdata->pages[nr_pages - 1]);
+
+			wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE);
+		}
 
 		wdata->sync_mode = WB_SYNC_ALL;
 		wdata->nr_pages = nr_pages;
@@ -2607,7 +2705,6 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 		wdata->pid = pid;
 		wdata->bytes = cur_len;
 		wdata->pagesz = PAGE_SIZE;
-		wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE);
 		wdata->credits = credits;
 		wdata->ctx = ctx;
 		kref_get(&ctx->refcount);
@@ -2682,13 +2779,18 @@ restart_loop:
 				INIT_LIST_HEAD(&tmp_list);
 				list_del_init(&wdata->list);
 
-				iov_iter_advance(&tmp_from,
+				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,
+					rc = cifs_write_from_iter(wdata->offset,
 						wdata->bytes, &tmp_from,
 						ctx->cfile, cifs_sb, &tmp_list,
 						ctx);
+				}
 
 				list_splice(&tmp_list, &ctx->list);
 
@@ -2701,8 +2803,9 @@ restart_loop:
 		kref_put(&wdata->refcount, cifs_uncached_writedata_release);
 	}
 
-	for (i = 0; i < ctx->npages; i++)
-		put_page(ctx->bv[i].bv_page);
+	if (!ctx->direct_io)
+		for (i = 0; i < ctx->npages; i++)
+			put_page(ctx->bv[i].bv_page);
 
 	cifs_stats_bytes_written(tcon, ctx->total_len);
 	set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags);
@@ -2717,7 +2820,8 @@ restart_loop:
 		complete(&ctx->done);
 }
 
-ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
+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;
@@ -2726,13 +2830,18 @@ ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_aio_ctx *ctx;
 	struct iov_iter saved_from = *from;
+	size_t len = iov_iter_count(from);
 	int rc;
 
 	/*
-	 * BB - optimize the way when signing is disabled. We can drop this
-	 * extra memory-to-memory copying and use iovec buffers for constructing
-	 * write request.
+	 * iov_iter_get_pages_alloc doesn't work with ITER_KVEC.
+	 * In this case, fall back to non-direct write function.
+	 * this could be improved by getting pages directly in ITER_KVEC
 	 */
+	if (direct && from->type & ITER_KVEC) {
+		cifs_dbg(FYI, "use non-direct cifs_writev for kvec I/O\n");
+		direct = false;
+	}
 
 	rc = generic_write_checks(iocb, from);
 	if (rc <= 0)
@@ -2756,10 +2865,16 @@ ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
 
 	ctx->pos = iocb->ki_pos;
 
-	rc = setup_aio_ctx_iter(ctx, from, WRITE);
-	if (rc) {
-		kref_put(&ctx->refcount, cifs_aio_ctx_release);
-		return rc;
+	if (direct) {
+		ctx->direct_io = true;
+		ctx->iter = *from;
+		ctx->len = len;
+	} else {
+		rc = setup_aio_ctx_iter(ctx, from, WRITE);
+		if (rc) {
+			kref_put(&ctx->refcount, cifs_aio_ctx_release);
+			return rc;
+		}
 	}
 
 	/* grab a lock here due to read response handlers can access ctx */
@@ -2809,6 +2924,16 @@ ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
 	return total_written;
 }
 
+ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from)
+{
+	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)
 {
@@ -2979,7 +3104,6 @@ cifs_uncached_readdata_release(struct kref *refcount)
 	kref_put(&rdata->ctx->refcount, cifs_aio_ctx_release);
 	for (i = 0; i < rdata->nr_pages; i++) {
 		put_page(rdata->pages[i]);
-		rdata->pages[i] = NULL;
 	}
 	cifs_readdata_release(refcount);
 }
@@ -3106,6 +3230,67 @@ cifs_uncached_copy_into_pages(struct TCP_Server_Info *server,
 	return uncached_fill_pages(server, rdata, iter, iter->count);
 }
 
+static int cifs_resend_rdata(struct cifs_readdata *rdata,
+			struct list_head *rdata_list,
+			struct cifs_aio_ctx *ctx)
+{
+	int wait_retry = 0;
+	unsigned int rsize, credits;
+	int rc;
+	struct TCP_Server_Info *server =
+		tlink_tcon(rdata->cfile->tlink)->ses->server;
+
+	/*
+	 * Try to resend this rdata, waiting for credits up to 3 seconds.
+	 * 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)
+			break;
+
+		if (rsize < rdata->bytes) {
+			add_credits_and_wake_if(server, credits, 0);
+			msleep(1000);
+			wait_retry++;
+		}
+	} while (rsize < rdata->bytes && wait_retry < 3);
+
+	/*
+	 * If we can't find enough credits to send this rdata
+	 * release the rdata and return failure, this will pass
+	 * whatever I/O amount we have finished to VFS.
+	 */
+	if (rsize < rdata->bytes) {
+		rc = -EBUSY;
+		goto out;
+	}
+
+	rc = -EAGAIN;
+	while (rc == -EAGAIN) {
+		rc = 0;
+		if (rdata->cfile->invalidHandle)
+			rc = cifs_reopen_file(rdata->cfile, true);
+		if (!rc)
+			rc = server->ops->async_readv(rdata);
+	}
+
+	if (!rc) {
+		/* Add to aio pending list */
+		list_add_tail(&rdata->list, rdata_list);
+		return 0;
+	}
+
+	add_credits_and_wake_if(server, rdata->credits, 0);
+out:
+	kref_put(&rdata->refcount,
+		cifs_uncached_readdata_release);
+
+	return rc;
+}
+
 static int
 cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 		     struct cifs_sb_info *cifs_sb, struct list_head *rdata_list,
@@ -3117,6 +3302,9 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 	int rc;
 	pid_t pid;
 	struct TCP_Server_Info *server;
+	struct page **pagevec;
+	size_t start;
+	struct iov_iter direct_iov = ctx->iter;
 
 	server = tlink_tcon(open_file->tlink)->ses->server;
 
@@ -3125,6 +3313,9 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 	else
 		pid = current->tgid;
 
+	if (ctx->direct_io)
+		iov_iter_advance(&direct_iov, offset - ctx->pos);
+
 	do {
 		rc = server->ops->wait_mtu_credits(server, cifs_sb->rsize,
 						   &rsize, &credits);
@@ -3132,20 +3323,59 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 			break;
 
 		cur_len = min_t(const size_t, len, rsize);
-		npages = DIV_ROUND_UP(cur_len, PAGE_SIZE);
 
-		/* allocate a readdata struct */
-		rdata = cifs_readdata_alloc(npages,
+		if (ctx->direct_io) {
+			ssize_t result;
+
+			result = iov_iter_get_pages_alloc(
+					&direct_iov, &pagevec,
+					cur_len, &start);
+			if (result < 0) {
+				cifs_dbg(VFS,
+					"couldn't get user pages (cur_len=%zd)"
+					" iter type %d"
+					" iov_offset %zd count %zd\n",
+					result, direct_iov.type,
+					direct_iov.iov_offset,
+					direct_iov.count);
+				dump_stack();
+				break;
+			}
+			cur_len = (size_t)result;
+			iov_iter_advance(&direct_iov, cur_len);
+
+			rdata = cifs_readdata_direct_alloc(
+					pagevec, cifs_uncached_readv_complete);
+			if (!rdata) {
+				add_credits_and_wake_if(server, credits, 0);
+				rc = -ENOMEM;
+				break;
+			}
+
+			npages = (cur_len + start + PAGE_SIZE-1) / PAGE_SIZE;
+			rdata->page_offset = start;
+			rdata->tailsz = npages > 1 ?
+				cur_len-(PAGE_SIZE-start)-(npages-2)*PAGE_SIZE :
+				cur_len;
+
+		} else {
+
+			npages = DIV_ROUND_UP(cur_len, PAGE_SIZE);
+			/* allocate a readdata struct */
+			rdata = cifs_readdata_alloc(npages,
 					    cifs_uncached_readv_complete);
-		if (!rdata) {
-			add_credits_and_wake_if(server, credits, 0);
-			rc = -ENOMEM;
-			break;
-		}
+			if (!rdata) {
+				add_credits_and_wake_if(server, credits, 0);
+				rc = -ENOMEM;
+				break;
+			}
 
-		rc = cifs_read_allocate_pages(rdata, npages);
-		if (rc)
-			goto error;
+			rc = cifs_read_allocate_pages(rdata, npages);
+			if (rc)
+				goto error;
+
+			rdata->tailsz = PAGE_SIZE;
+		}
 
 		rdata->cfile = cifsFileInfo_get(open_file);
 		rdata->nr_pages = npages;
@@ -3153,7 +3383,6 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 		rdata->bytes = cur_len;
 		rdata->pid = pid;
 		rdata->pagesz = PAGE_SIZE;
-		rdata->tailsz = PAGE_SIZE;
 		rdata->read_into_pages = cifs_uncached_read_into_pages;
 		rdata->copy_into_pages = cifs_uncached_copy_into_pages;
 		rdata->credits = credits;
@@ -3167,9 +3396,11 @@ error:
 		if (rc) {
 			add_credits_and_wake_if(server, rdata->credits, 0);
 			kref_put(&rdata->refcount,
-				 cifs_uncached_readdata_release);
-			if (rc == -EAGAIN)
+				cifs_uncached_readdata_release);
+			if (rc == -EAGAIN) {
+				iov_iter_revert(&direct_iov, cur_len);
 				continue;
+			}
 			break;
 		}
 
@@ -3225,45 +3456,62 @@ again:
 				 * reading.
 				 */
 				if (got_bytes && got_bytes < rdata->bytes) {
-					rc = cifs_readdata_to_iov(rdata, to);
+					rc = 0;
+					if (!ctx->direct_io)
+						rc = cifs_readdata_to_iov(rdata, to);
 					if (rc) {
 						kref_put(&rdata->refcount,
-						cifs_uncached_readdata_release);
+							cifs_uncached_readdata_release);
 						continue;
 					}
 				}
 
-				rc = cifs_send_async_read(
+				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_uncached_readdata_release);
+				}
+
 				list_splice(&tmp_list, &ctx->list);
 
-				kref_put(&rdata->refcount,
-					 cifs_uncached_readdata_release);
 				goto again;
 			} else if (rdata->result)
 				rc = rdata->result;
-			else
+			else if (!ctx->direct_io)
 				rc = cifs_readdata_to_iov(rdata, to);
 
 			/* 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_uncached_readdata_release);
 	}
 
-	for (i = 0; i < ctx->npages; i++) {
-		if (ctx->should_dirty)
-			set_page_dirty(ctx->bv[i].bv_page);
-		put_page(ctx->bv[i].bv_page);
-	}
+	if (!ctx->direct_io) {
+		for (i = 0; i < ctx->npages; i++) {
+			if (ctx->should_dirty)
+				set_page_dirty(ctx->bv[i].bv_page);
+			put_page(ctx->bv[i].bv_page);
+		}
 
-	ctx->total_len = ctx->len - iov_iter_count(to);
+		ctx->total_len = ctx->len - iov_iter_count(to);
+	}
 
 	cifs_stats_bytes_read(tcon, ctx->total_len);
 
@@ -3281,18 +3529,28 @@ again:
 		complete(&ctx->done);
 }
 
-ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
+static ssize_t __cifs_readv(
+	struct kiocb *iocb, struct iov_iter *to, bool direct)
 {
-	struct file *file = iocb->ki_filp;
-	ssize_t rc;
 	size_t len;
-	ssize_t total_read = 0;
-	loff_t offset = iocb->ki_pos;
+	struct file *file = iocb->ki_filp;
 	struct cifs_sb_info *cifs_sb;
-	struct cifs_tcon *tcon;
 	struct cifsFileInfo *cfile;
+	struct cifs_tcon *tcon;
+	ssize_t rc, total_read = 0;
+	loff_t offset = iocb->ki_pos;
 	struct cifs_aio_ctx *ctx;
 
+	/*
+	 * iov_iter_get_pages_alloc() doesn't work with ITER_KVEC,
+	 * fall back to data copy read path
+	 * this could be improved by getting pages directly in ITER_KVEC
+	 */
+	if (direct && to->type & ITER_KVEC) {
+		cifs_dbg(FYI, "use non-direct cifs_user_readv for kvec I/O\n");
+		direct = false;
+	}
+
 	len = iov_iter_count(to);
 	if (!len)
 		return 0;
@@ -3319,14 +3577,20 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
 	if (iter_is_iovec(to))
 		ctx->should_dirty = true;
 
-	rc = setup_aio_ctx_iter(ctx, to, READ);
-	if (rc) {
-		kref_put(&ctx->refcount, cifs_aio_ctx_release);
-		return rc;
+	if (direct) {
+		ctx->pos = offset;
+		ctx->direct_io = true;
+		ctx->iter = *to;
+		ctx->len = len;
+	} else {
+		rc = setup_aio_ctx_iter(ctx, to, READ);
+		if (rc) {
+			kref_put(&ctx->refcount, cifs_aio_ctx_release);
+			return rc;
+		}
+		len = ctx->len;
 	}
 
-	len = ctx->len;
-
 	/* grab a lock here due to read response handlers can access ctx */
 	mutex_lock(&ctx->aio_mutex);
 
@@ -3368,6 +3632,16 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
 	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);
+}
+
 ssize_t
 cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
 {

fs/cifs/inode.c

@@ -1320,8 +1320,8 @@ cifs_drop_nlink(struct inode *inode)
 /*
  * If d_inode(dentry) is null (usually meaning the cached dentry
  * is a negative dentry) then we would attempt a standard SMB delete, but
- * if that fails we can not attempt the fall back mechanisms on EACCESS
- * but will return the EACCESS to the caller. Note that the VFS does not call
+ * if that fails we can not attempt the fall back mechanisms on EACCES
+ * but will return the EACCES to the caller. Note that the VFS does not call
  * unlink on negative dentries currently.
  */
 int cifs_unlink(struct inode *dir, struct dentry *dentry)

fs/cifs/smb2ops.c

@@ -747,6 +747,7 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size,
 	int rc = 0;
 	unsigned int ea_name_len = ea_name ? strlen(ea_name) : 0;
 	char *name, *value;
+	size_t buf_size = dst_size;
 	size_t name_len, value_len, user_name_len;
 
 	while (src_size > 0) {
@@ -782,9 +783,10 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size,
 			/* 'user.' plus a terminating null */
 			user_name_len = 5 + 1 + name_len;
 
-			rc += user_name_len;
-
-			if (dst_size >= user_name_len) {
+			if (buf_size == 0) {
+				/* skip copy - calc size only */
+				rc += user_name_len;
+			} else if (dst_size >= user_name_len) {
 				dst_size -= user_name_len;
 				memcpy(dst, "user.", 5);
 				dst += 5;
@@ -792,8 +794,7 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size,
 				dst += name_len;
 				*dst = 0;
 				++dst;
-			} else if (dst_size == 0) {
-				/* skip copy - calc size only */
+				rc += user_name_len;
 			} else {
 				/* stop before overrun buffer */
 				rc = -ERANGE;
@@ -1078,6 +1079,9 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock)
 
 	cfile->fid.persistent_fid = fid->persistent_fid;
 	cfile->fid.volatile_fid = fid->volatile_fid;
+#ifdef CONFIG_CIFS_DEBUG2
+	cfile->fid.mid = fid->mid;
+#endif /* CIFS_DEBUG2 */
 	server->ops->set_oplock_level(cinode, oplock, fid->epoch,
 				      &fid->purge_cache);
 	cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode);

fs/cifs/smb2pdu.c

@@ -1512,7 +1512,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
 	cifs_small_buf_release(req);
 	rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base;
-
+	trace_smb3_tcon(xid, tcon->tid, ses->Suid, tree, rc);
 	if (rc != 0) {
 		if (tcon) {
 			cifs_stats_fail_inc(tcon, SMB2_TREE_CONNECT_HE);
@@ -1559,6 +1559,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	if (tcon->ses->server->ops->validate_negotiate)
 		rc = tcon->ses->server->ops->validate_negotiate(xid, tcon);
 tcon_exit:
+
 	free_rsp_buf(resp_buftype, rsp);
 	kfree(unc_path);
 	return rc;
@@ -2308,6 +2309,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	atomic_inc(&tcon->num_remote_opens);
 	oparms->fid->persistent_fid = rsp->PersistentFileId;
 	oparms->fid->volatile_fid = rsp->VolatileFileId;
+#ifdef CONFIG_CIFS_DEBUG2
+	oparms->fid->mid = le64_to_cpu(rsp->sync_hdr.MessageId);
+#endif /* CIFS_DEBUG2 */
 
 	if (buf) {
 		memcpy(buf, &rsp->CreationTime, 32);

fs/cifs/smb2pdu.h

@@ -842,6 +842,41 @@ struct fsctl_get_integrity_information_rsp {
 /* Integrity flags for above */
 #define FSCTL_INTEGRITY_FLAG_CHECKSUM_ENFORCEMENT_OFF	0x00000001
 
+/* Reparse structures - see MS-FSCC 2.1.2 */
+
+/* struct fsctl_reparse_info_req is empty, only response structs (see below) */
+
+struct reparse_data_buffer {
+	__le32	ReparseTag;
+	__le16	ReparseDataLength;
+	__u16	Reserved;
+	__u8	DataBuffer[0]; /* Variable Length */
+} __packed;
+
+struct reparse_guid_data_buffer {
+	__le32	ReparseTag;
+	__le16	ReparseDataLength;
+	__u16	Reserved;
+	__u8	ReparseGuid[16];
+	__u8	DataBuffer[0]; /* Variable Length */
+} __packed;
+
+struct reparse_mount_point_data_buffer {
+	__le32	ReparseTag;
+	__le16	ReparseDataLength;
+	__u16	Reserved;
+	__le16	SubstituteNameOffset;
+	__le16	SubstituteNameLength;
+	__le16	PrintNameOffset;
+	__le16	PrintNameLength;
+	__u8	PathBuffer[0]; /* Variable Length */
+} __packed;
+
+/* See MS-FSCC 2.1.2.4 and cifspdu.h for struct reparse_symlink_data */
+
+/* See MS-FSCC 2.1.2.6 and cifspdu.h for struct reparse_posix_data */
+
+
 /* See MS-DFSC 2.2.2 */
 struct fsctl_get_dfs_referral_req {
 	__le16 MaxReferralLevel;

fs/cifs/trace.h

@@ -373,6 +373,48 @@ DEFINE_EVENT(smb3_enter_exit_class, smb3_##name,  \
 DEFINE_SMB3_ENTER_EXIT_EVENT(enter);
 DEFINE_SMB3_ENTER_EXIT_EVENT(exit_done);
 
+/*
+ * For SMB2/SMB3 tree connect
+ */
+
+DECLARE_EVENT_CLASS(smb3_tcon_class,
+	TP_PROTO(unsigned int xid,
+		__u32	tid,
+		__u64	sesid,
+		const char *unc_name,
+		int	rc),
+	TP_ARGS(xid, tid, sesid, unc_name, rc),
+	TP_STRUCT__entry(
+		__field(unsigned int, xid)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(const char *,  unc_name)
+		__field(int, rc)
+	),
+	TP_fast_assign(
+		__entry->xid = xid;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->unc_name = unc_name;
+		__entry->rc = rc;
+	),
+	TP_printk("xid=%u sid=0x%llx tid=0x%x unc_name=%s rc=%d",
+		__entry->xid, __entry->sesid, __entry->tid,
+		__entry->unc_name, __entry->rc)
+)
+
+#define DEFINE_SMB3_TCON_EVENT(name)          \
+DEFINE_EVENT(smb3_tcon_class, smb3_##name,    \
+	TP_PROTO(unsigned int xid,		\
+		__u32	tid,			\
+		__u64	sesid,			\
+		const char *unc_name,		\
+		int	rc),			\
+	TP_ARGS(xid, tid, sesid, unc_name, rc))
+
+DEFINE_SMB3_TCON_EVENT(tcon);
+
+
 /*
  * For smb2/smb3 open call
  */