Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/sage/ceph-client

Pull Ceph updates from Sage Weil:
 "There is the long-awaited discard support for RBD (Guangliang Zhao,
  Josh Durgin), a pile of RBD bug fixes that didn't belong in late -rc's
  (Ilya Dryomov, Li RongQing), a pile of fs/ceph bug fixes and
  performance and debugging improvements (Yan, Zheng, John Spray), and a
  smattering of cleanups (Chao Yu, Fabian Frederick, Joe Perches)"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (40 commits)
  ceph: fix divide-by-zero in __validate_layout()
  rbd: rbd workqueues need a resque worker
  libceph: ceph-msgr workqueue needs a resque worker
  ceph: fix bool assignments
  libceph: separate multiple ops with commas in debugfs output
  libceph: sync osd op definitions in rados.h
  libceph: remove redundant declaration
  ceph: additional debugfs output
  ceph: export ceph_session_state_name function
  ceph: include the initial ACL in create/mkdir/mknod MDS requests
  ceph: use pagelist to present MDS request data
  libceph: reference counting pagelist
  ceph: fix llistxattr on symlink
  ceph: send client metadata to MDS
  ceph: remove redundant code for max file size verification
  ceph: remove redundant io_iter_advance()
  ceph: move ceph_find_inode() outside the s_mutex
  ceph: request xattrs if xattr_version is zero
  rbd: set the remaining discard properties to enable support
  rbd: use helpers to handle discard for layered images correctly
  ...

fs/ceph/acl.c

@@ -169,36 +169,109 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	return ret;
 }
 
-int ceph_init_acl(struct dentry *dentry, struct inode *inode, struct inode *dir)
+int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
+		       struct ceph_acls_info *info)
 {
-	struct posix_acl *default_acl, *acl;
-	umode_t new_mode = inode->i_mode;
-	int error;
-
-	error = posix_acl_create(dir, &new_mode, &default_acl, &acl);
-	if (error)
-		return error;
-
-	if (!default_acl && !acl) {
-		cache_no_acl(inode);
-		if (new_mode != inode->i_mode) {
-			struct iattr newattrs = {
-				.ia_mode = new_mode,
-				.ia_valid = ATTR_MODE,
-			};
-			error = ceph_setattr(dentry, &newattrs);
+	struct posix_acl *acl, *default_acl;
+	size_t val_size1 = 0, val_size2 = 0;
+	struct ceph_pagelist *pagelist = NULL;
+	void *tmp_buf = NULL;
+	int err;
+
+	err = posix_acl_create(dir, mode, &default_acl, &acl);
+	if (err)
+		return err;
+
+	if (acl) {
+		int ret = posix_acl_equiv_mode(acl, mode);
+		if (ret < 0)
+			goto out_err;
+		if (ret == 0) {
+			posix_acl_release(acl);
+			acl = NULL;
 		}
-		return error;
 	}
 
-	if (default_acl) {
-		error = ceph_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
-		posix_acl_release(default_acl);
-	}
+	if (!default_acl && !acl)
+		return 0;
+
+	if (acl)
+		val_size1 = posix_acl_xattr_size(acl->a_count);
+	if (default_acl)
+		val_size2 = posix_acl_xattr_size(default_acl->a_count);
+
+	err = -ENOMEM;
+	tmp_buf = kmalloc(max(val_size1, val_size2), GFP_NOFS);
+	if (!tmp_buf)
+		goto out_err;
+	pagelist = kmalloc(sizeof(struct ceph_pagelist), GFP_NOFS);
+	if (!pagelist)
+		goto out_err;
+	ceph_pagelist_init(pagelist);
+
+	err = ceph_pagelist_reserve(pagelist, PAGE_SIZE);
+	if (err)
+		goto out_err;
+
+	ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1);
+
 	if (acl) {
-		if (!error)
-			error = ceph_set_acl(inode, acl, ACL_TYPE_ACCESS);
-		posix_acl_release(acl);
+		size_t len = strlen(POSIX_ACL_XATTR_ACCESS);
+		err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8);
+		if (err)
+			goto out_err;
+		ceph_pagelist_encode_string(pagelist, POSIX_ACL_XATTR_ACCESS,
+					    len);
+		err = posix_acl_to_xattr(&init_user_ns, acl,
+					 tmp_buf, val_size1);
+		if (err < 0)
+			goto out_err;
+		ceph_pagelist_encode_32(pagelist, val_size1);
+		ceph_pagelist_append(pagelist, tmp_buf, val_size1);
 	}
-	return error;
+	if (default_acl) {
+		size_t len = strlen(POSIX_ACL_XATTR_DEFAULT);
+		err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
+		if (err)
+			goto out_err;
+		err = ceph_pagelist_encode_string(pagelist,
+						  POSIX_ACL_XATTR_DEFAULT, len);
+		err = posix_acl_to_xattr(&init_user_ns, default_acl,
+					 tmp_buf, val_size2);
+		if (err < 0)
+			goto out_err;
+		ceph_pagelist_encode_32(pagelist, val_size2);
+		ceph_pagelist_append(pagelist, tmp_buf, val_size2);
+	}
+
+	kfree(tmp_buf);
+
+	info->acl = acl;
+	info->default_acl = default_acl;
+	info->pagelist = pagelist;
+	return 0;
+
+out_err:
+	posix_acl_release(acl);
+	posix_acl_release(default_acl);
+	kfree(tmp_buf);
+	if (pagelist)
+		ceph_pagelist_release(pagelist);
+	return err;
+}
+
+void ceph_init_inode_acls(struct inode* inode, struct ceph_acls_info *info)
+{
+	if (!inode)
+		return;
+	ceph_set_cached_acl(inode, ACL_TYPE_ACCESS, info->acl);
+	ceph_set_cached_acl(inode, ACL_TYPE_DEFAULT, info->default_acl);
+}
+
+void ceph_release_acls_info(struct ceph_acls_info *info)
+{
+	posix_acl_release(info->acl);
+	posix_acl_release(info->default_acl);
+	if (info->pagelist)
+		ceph_pagelist_release(info->pagelist);
 }

fs/ceph/addr.c

@@ -1076,12 +1076,6 @@ static int ceph_update_writeable_page(struct file *file,
 	/* past end of file? */
 	i_size = inode->i_size;   /* caller holds i_mutex */
 
-	if (i_size + len > inode->i_sb->s_maxbytes) {
-		/* file is too big */
-		r = -EINVAL;
-		goto fail;
-	}
-
 	if (page_off >= i_size ||
 	    (pos_in_page == 0 && (pos+len) >= i_size &&
 	     end_in_page - pos_in_page != PAGE_CACHE_SIZE)) {
@@ -1099,9 +1093,6 @@ static int ceph_update_writeable_page(struct file *file,
 	if (r < 0)
 		goto fail_nosnap;
 	goto retry_locked;
-
-fail:
-	up_read(&mdsc->snap_rwsem);
 fail_nosnap:
 	unlock_page(page);
 	return r;

fs/ceph/caps.c

@@ -2397,12 +2397,12 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	u64 max_size = le64_to_cpu(grant->max_size);
 	struct timespec mtime, atime, ctime;
 	int check_caps = 0;
-	bool wake = 0;
-	bool writeback = 0;
-	bool queue_trunc = 0;
-	bool queue_invalidate = 0;
-	bool queue_revalidate = 0;
-	bool deleted_inode = 0;
+	bool wake = false;
+	bool writeback = false;
+	bool queue_trunc = false;
+	bool queue_invalidate = false;
+	bool queue_revalidate = false;
+	bool deleted_inode = false;
 
 	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
 	     inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2437,7 +2437,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 			/* there were locked pages.. invalidate later
 			   in a separate thread. */
 			if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
-				queue_invalidate = 1;
+				queue_invalidate = true;
 				ci->i_rdcache_revoking = ci->i_rdcache_gen;
 			}
 		}
@@ -2466,7 +2466,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 		set_nlink(inode, le32_to_cpu(grant->nlink));
 		if (inode->i_nlink == 0 &&
 		    (newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL)))
-			deleted_inode = 1;
+			deleted_inode = true;
 	}
 
 	if ((issued & CEPH_CAP_XATTR_EXCL) == 0 && grant->xattr_len) {
@@ -2487,7 +2487,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	/* Do we need to revalidate our fscache cookie. Don't bother on the
 	 * first cache cap as we already validate at cookie creation time. */
 	if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
-		queue_revalidate = 1;
+		queue_revalidate = true;
 
 	if (newcaps & CEPH_CAP_ANY_RD) {
 		/* ctime/mtime/atime? */
@@ -2516,7 +2516,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 				ci->i_wanted_max_size = 0;  /* reset */
 				ci->i_requested_max_size = 0;
 			}
-			wake = 1;
+			wake = true;
 		}
 	}
 
@@ -2546,7 +2546,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 		     ceph_cap_string(newcaps),
 		     ceph_cap_string(revoking));
 		if (revoking & used & CEPH_CAP_FILE_BUFFER)
-			writeback = 1;  /* initiate writeback; will delay ack */
+			writeback = true;  /* initiate writeback; will delay ack */
 		else if (revoking == CEPH_CAP_FILE_CACHE &&
 			 (newcaps & CEPH_CAP_FILE_LAZYIO) == 0 &&
 			 queue_invalidate)
@@ -2572,7 +2572,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 		cap->implemented |= newcaps; /* add bits only, to
 					      * avoid stepping on a
 					      * pending revocation */
-		wake = 1;
+		wake = true;
 	}
 	BUG_ON(cap->issued & ~cap->implemented);
 
@@ -2586,7 +2586,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 		kick_flushing_inode_caps(mdsc, session, inode);
 		up_read(&mdsc->snap_rwsem);
 		if (newcaps & ~issued)
-			wake = 1;
+			wake = true;
 	}
 
 	if (queue_trunc) {
@@ -3045,6 +3045,12 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		}
 	}
 
+	/* lookup ino */
+	inode = ceph_find_inode(sb, vino);
+	ci = ceph_inode(inode);
+	dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
+	     vino.snap, inode);
+
 	mutex_lock(&session->s_mutex);
 	session->s_seq++;
 	dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
@@ -3053,11 +3059,6 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	if (op == CEPH_CAP_OP_IMPORT)
 		ceph_add_cap_releases(mdsc, session);
 
-	/* lookup ino */
-	inode = ceph_find_inode(sb, vino);
-	ci = ceph_inode(inode);
-	dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
-	     vino.snap, inode);
 	if (!inode) {
 		dout(" i don't have ino %llx\n", vino.ino);
 

fs/ceph/debugfs.c

@@ -158,10 +158,47 @@ static int dentry_lru_show(struct seq_file *s, void *ptr)
 	return 0;
 }
 
+static int mds_sessions_show(struct seq_file *s, void *ptr)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_auth_client *ac = fsc->client->monc.auth;
+	struct ceph_options *opt = fsc->client->options;
+	int mds = -1;
+
+	mutex_lock(&mdsc->mutex);
+
+	/* The 'num' portion of an 'entity name' */
+	seq_printf(s, "global_id %llu\n", ac->global_id);
+
+	/* The -o name mount argument */
+	seq_printf(s, "name \"%s\"\n", opt->name ? opt->name : "");
+
+	/* The list of MDS session rank+state */
+	for (mds = 0; mds < mdsc->max_sessions; mds++) {
+		struct ceph_mds_session *session =
+			__ceph_lookup_mds_session(mdsc, mds);
+		if (!session) {
+			continue;
+		}
+		mutex_unlock(&mdsc->mutex);
+		seq_printf(s, "mds.%d %s\n",
+				session->s_mds,
+				ceph_session_state_name(session->s_state));
+
+		ceph_put_mds_session(session);
+		mutex_lock(&mdsc->mutex);
+	}
+	mutex_unlock(&mdsc->mutex);
+
+	return 0;
+}
+
 CEPH_DEFINE_SHOW_FUNC(mdsmap_show)
 CEPH_DEFINE_SHOW_FUNC(mdsc_show)
 CEPH_DEFINE_SHOW_FUNC(caps_show)
 CEPH_DEFINE_SHOW_FUNC(dentry_lru_show)
+CEPH_DEFINE_SHOW_FUNC(mds_sessions_show)
 
 
 /*
@@ -193,6 +230,7 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 	debugfs_remove(fsc->debugfs_bdi);
 	debugfs_remove(fsc->debugfs_congestion_kb);
 	debugfs_remove(fsc->debugfs_mdsmap);
+	debugfs_remove(fsc->debugfs_mds_sessions);
 	debugfs_remove(fsc->debugfs_caps);
 	debugfs_remove(fsc->debugfs_mdsc);
 	debugfs_remove(fsc->debugfs_dentry_lru);
@@ -231,6 +269,14 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 	if (!fsc->debugfs_mdsmap)
 		goto out;
 
+	fsc->debugfs_mds_sessions = debugfs_create_file("mds_sessions",
+					0600,
+					fsc->client->debugfs_dir,
+					fsc,
+					&mds_sessions_show_fops);
+	if (!fsc->debugfs_mds_sessions)
+		goto out;
+
 	fsc->debugfs_mdsc = debugfs_create_file("mdsc",
 						0600,
 						fsc->client->debugfs_dir,