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

Pull Ceph updates for 3.4-rc1 from Sage Weil:
 "Alex has been busy.  There are a range of rbd and libceph cleanups,
  especially surrounding device setup and teardown, and a few critical
  fixes in that code.  There are more cleanups in the messenger code,
  virtual xattrs, a fix for CRC calculation/checks, and lots of other
  miscellaneous stuff.

  There's a patch from Amon Ott to make inos behave a bit better on
  32-bit boxes, some decode check fixes from Xi Wang, and network
  throttling fix from Jim Schutt, and a couple RBD fixes from Josh
  Durgin.

  No new functionality, just a lot of cleanup and bug fixing."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (65 commits)
  rbd: move snap_rwsem to the device, rename to header_rwsem
  ceph: fix three bugs, two in ceph_vxattrcb_file_layout()
  libceph: isolate kmap() call in write_partial_msg_pages()
  libceph: rename "page_shift" variable to something sensible
  libceph: get rid of zero_page_address
  libceph: only call kernel_sendpage() via helper
  libceph: use kernel_sendpage() for sending zeroes
  libceph: fix inverted crc option logic
  libceph: some simple changes
  libceph: small refactor in write_partial_kvec()
  libceph: do crc calculations outside loop
  libceph: separate CRC calculation from byte swapping
  libceph: use "do" in CRC-related Boolean variables
  ceph: ensure Boolean options support both senses
  libceph: a few small changes
  libceph: make ceph_tcp_connect() return int
  libceph: encapsulate some messenger cleanup code
  libceph: make ceph_msgr_wq private
  libceph: encapsulate connection kvec operations
  libceph: move prepare_write_banner()
  ...

drivers/block/rbd_types.h

@@ -41,10 +41,6 @@
 #define RBD_HEADER_SIGNATURE	"RBD"
 #define RBD_HEADER_VERSION	"001.005"
 
-struct rbd_info {
-	__le64 max_id;
-} __attribute__ ((packed));
-
 struct rbd_image_snap_ondisk {
 	__le64 id;
 	__le64 image_size;

fs/ceph/inode.c

@@ -677,18 +677,19 @@ static int fill_inode(struct inode *inode,
 	case S_IFLNK:
 		inode->i_op = &ceph_symlink_iops;
 		if (!ci->i_symlink) {
-			int symlen = iinfo->symlink_len;
+			u32 symlen = iinfo->symlink_len;
 			char *sym;
 
-			BUG_ON(symlen != inode->i_size);
 			spin_unlock(&ci->i_ceph_lock);
 
+			err = -EINVAL;
+			if (WARN_ON(symlen != inode->i_size))
+				goto out;
+
 			err = -ENOMEM;
-			sym = kmalloc(symlen+1, GFP_NOFS);
+			sym = kstrndup(iinfo->symlink, symlen, GFP_NOFS);
 			if (!sym)
 				goto out;
-			memcpy(sym, iinfo->symlink, symlen);
-			sym[symlen] = 0;
 
 			spin_lock(&ci->i_ceph_lock);
 			if (!ci->i_symlink)

fs/ceph/mds_client.c

@@ -402,7 +402,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 
 	spin_lock_init(&s->s_gen_ttl_lock);
 	s->s_cap_gen = 0;
-	s->s_cap_ttl = 0;
+	s->s_cap_ttl = jiffies - 1;
 
 	spin_lock_init(&s->s_cap_lock);
 	s->s_renew_requested = 0;
@@ -1083,8 +1083,7 @@ static void renewed_caps(struct ceph_mds_client *mdsc,
 	int wake = 0;
 
 	spin_lock(&session->s_cap_lock);
-	was_stale = is_renew && (session->s_cap_ttl == 0 ||
-				 time_after_eq(jiffies, session->s_cap_ttl));
+	was_stale = is_renew && time_after_eq(jiffies, session->s_cap_ttl);
 
 	session->s_cap_ttl = session->s_renew_requested +
 		mdsc->mdsmap->m_session_timeout*HZ;
@@ -2332,7 +2331,7 @@ static void handle_session(struct ceph_mds_session *session,
 			session->s_mds);
 		spin_lock(&session->s_gen_ttl_lock);
 		session->s_cap_gen++;
-		session->s_cap_ttl = 0;
+		session->s_cap_ttl = jiffies - 1;
 		spin_unlock(&session->s_gen_ttl_lock);
 		send_renew_caps(mdsc, session);
 		break;

fs/ceph/snap.c

@@ -331,7 +331,7 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 
 	/* alloc new snap context */
 	err = -ENOMEM;
-	if (num > ULONG_MAX / sizeof(u64) - sizeof(*snapc))
+	if (num > (ULONG_MAX - sizeof(*snapc)) / sizeof(u64))
 		goto fail;
 	snapc = kzalloc(sizeof(*snapc) + num*sizeof(u64), GFP_NOFS);
 	if (!snapc)

fs/ceph/super.c

@@ -130,10 +130,12 @@ enum {
 	Opt_nodirstat,
 	Opt_rbytes,
 	Opt_norbytes,
+	Opt_asyncreaddir,
 	Opt_noasyncreaddir,
 	Opt_dcache,
 	Opt_nodcache,
 	Opt_ino32,
+	Opt_noino32,
 };
 
 static match_table_t fsopt_tokens = {
@@ -153,10 +155,12 @@ static match_table_t fsopt_tokens = {
 	{Opt_nodirstat, "nodirstat"},
 	{Opt_rbytes, "rbytes"},
 	{Opt_norbytes, "norbytes"},
+	{Opt_asyncreaddir, "asyncreaddir"},
 	{Opt_noasyncreaddir, "noasyncreaddir"},
 	{Opt_dcache, "dcache"},
 	{Opt_nodcache, "nodcache"},
 	{Opt_ino32, "ino32"},
+	{Opt_noino32, "noino32"},
 	{-1, NULL}
 };
 
@@ -232,6 +236,9 @@ static int parse_fsopt_token(char *c, void *private)
 	case Opt_norbytes:
 		fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES;
 		break;
+	case Opt_asyncreaddir:
+		fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR;
+		break;
 	case Opt_noasyncreaddir:
 		fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR;
 		break;
@@ -244,6 +251,9 @@ static int parse_fsopt_token(char *c, void *private)
 	case Opt_ino32:
 		fsopt->flags |= CEPH_MOUNT_OPT_INO32;
 		break;
+	case Opt_noino32:
+		fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
+		break;
 	default:
 		BUG_ON(token);
 	}
@@ -334,10 +344,12 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
 	*path += 2;
 	dout("server path '%s'\n", *path);
 
-	err = ceph_parse_options(popt, options, dev_name, dev_name_end,
+	*popt = ceph_parse_options(options, dev_name, dev_name_end,
 				 parse_fsopt_token, (void *)fsopt);
-	if (err)
+	if (IS_ERR(*popt)) {
+		err = PTR_ERR(*popt);
 		goto out;
+	}
 
 	/* success */
 	*pfsopt = fsopt;
@@ -926,6 +938,7 @@ static int __init init_ceph(void)
 	if (ret)
 		goto out;
 
+	ceph_xattr_init();
 	ret = register_filesystem(&ceph_fs_type);
 	if (ret)
 		goto out_icache;
@@ -935,6 +948,7 @@ static int __init init_ceph(void)
 	return 0;
 
 out_icache:
+	ceph_xattr_exit();
 	destroy_caches();
 out:
 	return ret;
@@ -944,6 +958,7 @@ static void __exit exit_ceph(void)
 {
 	dout("exit_ceph\n");
 	unregister_filesystem(&ceph_fs_type);
+	ceph_xattr_exit();
 	destroy_caches();
 }
 

fs/ceph/super.h

@@ -367,7 +367,7 @@ static inline u32 ceph_ino_to_ino32(__u64 vino)
 	u32 ino = vino & 0xffffffff;
 	ino ^= vino >> 32;
 	if (!ino)
-		ino = 1;
+		ino = 2;
 	return ino;
 }
 
@@ -733,6 +733,8 @@ extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
 extern int ceph_removexattr(struct dentry *, const char *);
 extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
 extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
+extern void __init ceph_xattr_init(void);
+extern void ceph_xattr_exit(void);
 
 /* caps.c */
 extern const char *ceph_cap_string(int c);

include/linux/ceph/libceph.h

@@ -208,7 +208,7 @@ extern struct kmem_cache *ceph_cap_cachep;
 extern struct kmem_cache *ceph_dentry_cachep;
 extern struct kmem_cache *ceph_file_cachep;
 
-extern int ceph_parse_options(struct ceph_options **popt, char *options,
+extern struct ceph_options *ceph_parse_options(char *options,
 			      const char *dev_name, const char *dev_name_end,
 			      int (*parse_extra_token)(char *c, void *private),
 			      void *private);

include/linux/ceph/messenger.h

@@ -14,8 +14,6 @@
 struct ceph_msg;
 struct ceph_connection;
 
-extern struct workqueue_struct *ceph_msgr_wq;       /* receive work queue */
-
 /*
  * Ceph defines these callbacks for handling connection events.
  */
@@ -54,7 +52,6 @@ struct ceph_connection_operations {
 struct ceph_messenger {
 	struct ceph_entity_inst inst;    /* my name+address */
 	struct ceph_entity_addr my_enc_addr;
-	struct page *zero_page;          /* used in certain error cases */
 
 	bool nocrc;
 
@@ -101,7 +98,7 @@ struct ceph_msg {
 struct ceph_msg_pos {
 	int page, page_pos;  /* which page; offset in page */
 	int data_pos;        /* offset in data payload */
-	int did_page_crc;    /* true if we've calculated crc for current page */
+	bool did_page_crc;   /* true if we've calculated crc for current page */
 };
 
 /* ceph connection fault delay defaults, for exponential backoff */

net/ceph/ceph_common.c

@@ -201,7 +201,9 @@ enum {
 	Opt_ip,
 	Opt_last_string,
 	/* string args above */
+	Opt_share,
 	Opt_noshare,
+	Opt_crc,
 	Opt_nocrc,
 };
 
@@ -217,7 +219,9 @@ static match_table_t opt_tokens = {
 	{Opt_key, "key=%s"},
 	{Opt_ip, "ip=%s"},
 	/* string args above */
+	{Opt_share, "share"},
 	{Opt_noshare, "noshare"},
+	{Opt_crc, "crc"},
 	{Opt_nocrc, "nocrc"},
 	{-1, NULL}
 };
@@ -277,10 +281,11 @@ static int get_secret(struct ceph_crypto_key *dst, const char *name) {
 	return err;
 }
 
-int ceph_parse_options(struct ceph_options **popt, char *options,
-		       const char *dev_name, const char *dev_name_end,
-		       int (*parse_extra_token)(char *c, void *private),
-		       void *private)
+struct ceph_options *
+ceph_parse_options(char *options, const char *dev_name,
+			const char *dev_name_end,
+			int (*parse_extra_token)(char *c, void *private),
+			void *private)
 {
 	struct ceph_options *opt;
 	const char *c;
@@ -289,7 +294,7 @@ int ceph_parse_options(struct ceph_options **popt, char *options,
 
 	opt = kzalloc(sizeof(*opt), GFP_KERNEL);
 	if (!opt)
-		return err;
+		return ERR_PTR(-ENOMEM);
 	opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr),
 				GFP_KERNEL);
 	if (!opt->mon_addr)
@@ -398,10 +403,16 @@ int ceph_parse_options(struct ceph_options **popt, char *options,
 			opt->mount_timeout = intval;
 			break;
 
+		case Opt_share:
+			opt->flags &= ~CEPH_OPT_NOSHARE;
+			break;
 		case Opt_noshare:
 			opt->flags |= CEPH_OPT_NOSHARE;
 			break;
 
+		case Opt_crc:
+			opt->flags &= ~CEPH_OPT_NOCRC;
+			break;
 		case Opt_nocrc:
 			opt->flags |= CEPH_OPT_NOCRC;
 			break;
@@ -412,12 +423,11 @@ int ceph_parse_options(struct ceph_options **popt, char *options,
 	}
 
 	/* success */
-	*popt = opt;
-	return 0;
+	return opt;
 
 out:
 	ceph_destroy_options(opt);
-	return err;
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(ceph_parse_options);
 

net/ceph/osdmap.c

@@ -283,7 +283,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 		ceph_decode_32_safe(p, end, yes, bad);
 #if BITS_PER_LONG == 32
 		err = -EINVAL;
-		if (yes > ULONG_MAX / sizeof(struct crush_rule_step))
+		if (yes > (ULONG_MAX - sizeof(*r))
+			  / sizeof(struct crush_rule_step))
 			goto bad;
 #endif
 		r = c->rules[i] = kmalloc(sizeof(*r) +