Merge git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull ceph updates from Sage Weil:
 "There are some updates and cleanups to the CRUSH placement code, a bug
  fix with incremental maps, several cleanups and fixes from Josh Durgin
  in the RBD block device code, a series of cleanups and bug fixes from
  Alex Elder in the messenger code, and some miscellaneous bounds
  checking and gfp cleanups/fixes."

Fix up trivial conflicts in net/ceph/{messenger.c,osdmap.c} due to the
networking people preferring "unsigned int" over just "unsigned".

* git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (45 commits)
  libceph: fix pg_temp updates
  libceph: avoid unregistering osd request when not registered
  ceph: add auth buf in prepare_write_connect()
  ceph: rename prepare_connect_authorizer()
  ceph: return pointer from prepare_connect_authorizer()
  ceph: use info returned by get_authorizer
  ceph: have get_authorizer methods return pointers
  ceph: ensure auth ops are defined before use
  ceph: messenger: reduce args to create_authorizer
  ceph: define ceph_auth_handshake type
  ceph: messenger: check return from get_authorizer
  ceph: messenger: rework prepare_connect_authorizer()
  ceph: messenger: check prepare_write_connect() result
  ceph: don't set WRITE_PENDING too early
  ceph: drop msgr argument from prepare_write_connect()
  ceph: messenger: send banner in process_connect()
  ceph: messenger: reset connection kvec caller
  libceph: don't reset kvec in prepare_write_banner()
  ceph: ignore preferred_osd field
  ceph: fully initialize new layout
  ...

6 files changed, 75 insertions, 98 deletions

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ed72428d9c7..988d4f302e4 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -54,7 +54,6 @@ prepare_open_request(struct super_block *sb, int flags, int create_mode)
 	req->r_fmode = ceph_flags_to_mode(flags);
 	req->r_args.open.flags = cpu_to_le32(flags);
 	req->r_args.open.mode = cpu_to_le32(create_mode);
-	req->r_args.open.preferred = cpu_to_le32(-1);
 out:
 	return req;
 }
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 790914a598d..8e3fb69fbe6 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -26,8 +26,7 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
 		l.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
 		l.object_size = ceph_file_layout_object_size(ci->i_layout);
 		l.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool);
-		l.preferred_osd =
-			(s32)le32_to_cpu(ci->i_layout.fl_pg_preferred);
+		l.preferred_osd = (s32)-1;
 		if (copy_to_user(arg, &l, sizeof(l)))
 			return -EFAULT;
 	}
@@ -35,6 +34,32 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
 	return err;
 }
 
+static long __validate_layout(struct ceph_mds_client *mdsc,
+			      struct ceph_ioctl_layout *l)
+{
+	int i, err;
+
+	/* validate striping parameters */
+	if ((l->object_size & ~PAGE_MASK) ||
+	    (l->stripe_unit & ~PAGE_MASK) ||
+	    ((unsigned)l->object_size % (unsigned)l->stripe_unit))
+		return -EINVAL;
+
+	/* make sure it's a valid data pool */
+	mutex_lock(&mdsc->mutex);
+	err = -EINVAL;
+	for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
+		if (mdsc->mdsmap->m_data_pg_pools[i] == l->data_pool) {
+			err = 0;
+			break;
+		}
+	mutex_unlock(&mdsc->mutex);
+	if (err)
+		return err;
+
+	return 0;
+}
+
 static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 {
 	struct inode *inode = file->f_dentry->d_inode;
@@ -44,52 +69,40 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 	struct ceph_ioctl_layout l;
 	struct ceph_inode_info *ci = ceph_inode(file->f_dentry->d_inode);
 	struct ceph_ioctl_layout nl;
-	int err, i;
+	int err;
 
 	if (copy_from_user(&l, arg, sizeof(l)))
 		return -EFAULT;
 
 	/* validate changed params against current layout */
 	err = ceph_do_getattr(file->f_dentry->d_inode, CEPH_STAT_CAP_LAYOUT);
-	if (!err) {
-		nl.stripe_unit = ceph_file_layout_su(ci->i_layout);
-		nl.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
-		nl.object_size = ceph_file_layout_object_size(ci->i_layout);
-		nl.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool);
-		nl.preferred_osd =
-				(s32)le32_to_cpu(ci->i_layout.fl_pg_preferred);
-	} else
+	if (err)
 		return err;
 
+	memset(&nl, 0, sizeof(nl));
 	if (l.stripe_count)
 		nl.stripe_count = l.stripe_count;
+	else
+		nl.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
 	if (l.stripe_unit)
 		nl.stripe_unit = l.stripe_unit;
+	else
+		nl.stripe_unit = ceph_file_layout_su(ci->i_layout);
 	if (l.object_size)
 		nl.object_size = l.object_size;
+	else
+		nl.object_size = ceph_file_layout_object_size(ci->i_layout);
 	if (l.data_pool)
 		nl.data_pool = l.data_pool;
-	if (l.preferred_osd)
-		nl.preferred_osd = l.preferred_osd;
+	else
+		nl.data_pool = ceph_file_layout_pg_pool(ci->i_layout);
 
-	if ((nl.object_size & ~PAGE_MASK) ||
-	    (nl.stripe_unit & ~PAGE_MASK) ||
-	    ((unsigned)nl.object_size % (unsigned)nl.stripe_unit))
-		return -EINVAL;
+	/* this is obsolete, and always -1 */
+	nl.preferred_osd = le64_to_cpu(-1);
 
-	/* make sure it's a valid data pool */
-	if (l.data_pool > 0) {
-		mutex_lock(&mdsc->mutex);
-		err = -EINVAL;
-		for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
-			if (mdsc->mdsmap->m_data_pg_pools[i] == l.data_pool) {
-				err = 0;
-				break;
-			}
-		mutex_unlock(&mdsc->mutex);
-		if (err)
-			return err;
-	}
+	err = __validate_layout(mdsc, &nl);
+	if (err)
+		return err;
 
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETLAYOUT,
 				       USE_AUTH_MDS);
@@ -106,8 +119,6 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 	req->r_args.setlayout.layout.fl_object_size =
 		cpu_to_le32(l.object_size);
 	req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool);
-	req->r_args.setlayout.layout.fl_pg_preferred =
-		cpu_to_le32(l.preferred_osd);
 
 	parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
 	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
@@ -127,33 +138,16 @@ static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_mds_request *req;
 	struct ceph_ioctl_layout l;
-	int err, i;
+	int err;
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 
 	/* copy and validate */
 	if (copy_from_user(&l, arg, sizeof(l)))
 		return -EFAULT;
 
-	if ((l.object_size & ~PAGE_MASK) ||
-	    (l.stripe_unit & ~PAGE_MASK) ||
-	    !l.stripe_unit ||
-	    (l.object_size &&
-	        (unsigned)l.object_size % (unsigned)l.stripe_unit))
-		return -EINVAL;
-
-	/* make sure it's a valid data pool */
-	if (l.data_pool > 0) {
-		mutex_lock(&mdsc->mutex);
-		err = -EINVAL;
-		for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
-			if (mdsc->mdsmap->m_data_pg_pools[i] == l.data_pool) {
-				err = 0;
-				break;
-			}
-		mutex_unlock(&mdsc->mutex);
-		if (err)
-			return err;
-	}
+	err = __validate_layout(mdsc, &l);
+	if (err)
+		return err;
 
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETDIRLAYOUT,
 				       USE_AUTH_MDS);
@@ -171,8 +165,6 @@ static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
 			cpu_to_le32(l.object_size);
 	req->r_args.setlayout.layout.fl_pg_pool =
 			cpu_to_le32(l.data_pool);
-	req->r_args.setlayout.layout.fl_pg_preferred =
-			cpu_to_le32(l.preferred_osd);
 
 	err = ceph_mdsc_do_request(mdsc, inode, req);
 	ceph_mdsc_put_request(req);
diff --git a/fs/ceph/ioctl.h b/fs/ceph/ioctl.h
index be4a6048733..c77028afb1e 100644
--- a/fs/ceph/ioctl.h
+++ b/fs/ceph/ioctl.h
@@ -34,6 +34,8 @@
 struct ceph_ioctl_layout {
 	__u64 stripe_unit, stripe_count, object_size;
 	__u64 data_pool;
+
+	/* obsolete.  new values ignored, always return -1 */
 	__s64 preferred_osd;
 };
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 89971e137aa..200bc87eceb 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -334,10 +334,10 @@ void ceph_put_mds_session(struct ceph_mds_session *s)
 	dout("mdsc put_session %p %d -> %d\n", s,
 	     atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
 	if (atomic_dec_and_test(&s->s_ref)) {
-		if (s->s_authorizer)
+		if (s->s_auth.authorizer)
 		     s->s_mdsc->fsc->client->monc.auth->ops->destroy_authorizer(
 			     s->s_mdsc->fsc->client->monc.auth,
-			     s->s_authorizer);
+			     s->s_auth.authorizer);
 		kfree(s);
 	}
 }
@@ -3395,39 +3395,33 @@ out:
 /*
  * authentication
  */
-static int get_authorizer(struct ceph_connection *con,
-			  void **buf, int *len, int *proto,
-			  void **reply_buf, int *reply_len, int force_new)
+
+/*
+ * Note: returned pointer is the address of a structure that's
+ * managed separately.  Caller must *not* attempt to free it.
+ */
+static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
+					int *proto, int force_new)
 {
 	struct ceph_mds_session *s = con->private;
 	struct ceph_mds_client *mdsc = s->s_mdsc;
 	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
-	int ret = 0;
-
-	if (force_new && s->s_authorizer) {
-		ac->ops->destroy_authorizer(ac, s->s_authorizer);
-		s->s_authorizer = NULL;
-	}
-	if (s->s_authorizer == NULL) {
-		if (ac->ops->create_authorizer) {
-			ret = ac->ops->create_authorizer(
-				ac, CEPH_ENTITY_TYPE_MDS,
-				&s->s_authorizer,
-				&s->s_authorizer_buf,
-				&s->s_authorizer_buf_len,
-				&s->s_authorizer_reply_buf,
-				&s->s_authorizer_reply_buf_len);
-			if (ret)
-				return ret;
-		}
-	}
+	struct ceph_auth_handshake *auth = &s->s_auth;
 
+	if (force_new && auth->authorizer) {
+		if (ac->ops && ac->ops->destroy_authorizer)
+			ac->ops->destroy_authorizer(ac, auth->authorizer);
+		auth->authorizer = NULL;
+	}
+	if (!auth->authorizer && ac->ops && ac->ops->create_authorizer) {
+		int ret = ac->ops->create_authorizer(ac, CEPH_ENTITY_TYPE_MDS,
+							auth);
+		if (ret)
+			return ERR_PTR(ret);
+	}
 	*proto = ac->protocol;
-	*buf = s->s_authorizer_buf;
-	*len = s->s_authorizer_buf_len;
-	*reply_buf = s->s_authorizer_reply_buf;
-	*reply_len = s->s_authorizer_reply_buf_len;
-	return 0;
+
+	return auth;
 }
 
 
@@ -3437,7 +3431,7 @@ static int verify_authorizer_reply(struct ceph_connection *con, int len)
 	struct ceph_mds_client *mdsc = s->s_mdsc;
 	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 
-	return ac->ops->verify_authorizer_reply(ac, s->s_authorizer, len);
+	return ac->ops->verify_authorizer_reply(ac, s->s_auth.authorizer, len);
 }
 
 static int invalidate_authorizer(struct ceph_connection *con)
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 8c7c04ebb59..dd26846dd71 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -11,6 +11,7 @@
 #include <linux/ceph/types.h>
 #include <linux/ceph/messenger.h>
 #include <linux/ceph/mdsmap.h>
+#include <linux/ceph/auth.h>
 
 /*
  * Some lock dependencies:
@@ -113,9 +114,7 @@ struct ceph_mds_session {
 
 	struct ceph_connection s_con;
 
-	struct ceph_authorizer *s_authorizer;
-	void             *s_authorizer_buf, *s_authorizer_reply_buf;
-	size_t            s_authorizer_buf_len, s_authorizer_reply_buf_len;
+	struct ceph_auth_handshake s_auth;
 
 	/* protected by s_gen_ttl_lock */
 	spinlock_t        s_gen_ttl_lock;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 35b86331d8a..785cb3057c9 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -118,15 +118,6 @@ static size_t ceph_vxattrcb_file_layout(struct ceph_inode_info *ci, char *val,
 		(unsigned long long)ceph_file_layout_su(ci->i_layout),
 		(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
 		(unsigned long long)ceph_file_layout_object_size(ci->i_layout));
-
-	if (ceph_file_layout_pg_preferred(ci->i_layout) >= 0) {
-		val += ret;
-		size -= ret;
-		ret += snprintf(val, size, "preferred_osd=%lld\n",
-			    (unsigned long long)ceph_file_layout_pg_preferred(
-				    ci->i_layout));
-	}
-
 	return ret;
 }