Merge tag 'ceph-for-5.3-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "Lots of exciting things this time!

   - support for rbd object-map and fast-diff features (myself). This
     will speed up reads, discards and things like snap diffs on sparse
     images.

   - ceph.snap.btime vxattr to expose snapshot creation time (David
     Disseldorp). This will be used to integrate with "Restore Previous
     Versions" feature added in Windows 7 for folks who reexport ceph
     through SMB.

   - security xattrs for ceph (Zheng Yan). Only selinux is supported for
     now due to the limitations of ->dentry_init_security().

   - support for MSG_ADDR2, FS_BTIME and FS_CHANGE_ATTR features (Jeff
     Layton). This is actually a single feature bit which was missing
     because of the filesystem pieces. With this in, the kernel client
     will finally be reported as "luminous" by "ceph features" -- it is
     still being reported as "jewel" even though all required Luminous
     features were implemented in 4.13.

   - stop NULL-terminating ceph vxattrs (Jeff Layton). The convention
     with xattrs is to not terminate and this was causing
     inconsistencies with ceph-fuse.

   - change filesystem time granularity from 1 us to 1 ns, again fixing
     an inconsistency with ceph-fuse (Luis Henriques).

  On top of this there are some additional dentry name handling and cap
  flushing fixes from Zheng. Finally, Jeff is formally taking over for
  Zheng as the filesystem maintainer"

* tag 'ceph-for-5.3-rc1' of git://github.com/ceph/ceph-client: (71 commits)
  ceph: fix end offset in truncate_inode_pages_range call
  ceph: use generic_delete_inode() for ->drop_inode
  ceph: use ceph_evict_inode to cleanup inode's resource
  ceph: initialize superblock s_time_gran to 1
  MAINTAINERS: take over for Zheng as CephFS kernel client maintainer
  rbd: setallochint only if object doesn't exist
  rbd: support for object-map and fast-diff
  rbd: call rbd_dev_mapping_set() from rbd_dev_image_probe()
  libceph: export osd_req_op_data() macro
  libceph: change ceph_osdc_call() to take page vector for response
  libceph: bump CEPH_MSG_MAX_DATA_LEN (again)
  rbd: new exclusive lock wait/wake code
  rbd: quiescing lock should wait for image requests
  rbd: lock should be quiesced on reacquire
  rbd: introduce copyup state machine
  rbd: rename rbd_obj_setup_*() to rbd_obj_init_*()
  rbd: move OSD request allocation into object request state machines
  rbd: factor out __rbd_osd_setup_discard_ops()
  rbd: factor out rbd_osd_setup_copyup()
  rbd: introduce obj_req->osd_reqs list
  ...

9 files changed, 56 insertions, 12 deletions

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 65a38c4a02a1..39e6f4c57580 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -211,6 +211,7 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin
 	 CEPH_FEATURE_MON_STATEFUL_SUB |	\
 	 CEPH_FEATURE_CRUSH_TUNABLES5 |		\
 	 CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING |	\
+	 CEPH_FEATURE_MSG_ADDR2 |		\
 	 CEPH_FEATURE_CEPHX_V2)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT	0
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 3ac0feaf2b5e..cb21c5cf12c3 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -682,7 +682,7 @@ extern const char *ceph_cap_op_name(int op);
 /* flags field in client cap messages (version >= 10) */
 #define CEPH_CLIENT_CAPS_SYNC			(1<<0)
 #define CEPH_CLIENT_CAPS_NO_CAPSNAP		(1<<1)
-#define CEPH_CLIENT_CAPS_PENDING_CAPSNAP	(1<<2);
+#define CEPH_CLIENT_CAPS_PENDING_CAPSNAP	(1<<2)
 
 /*
  * caps message, used for capability callbacks, acks, requests, etc.
diff --git a/include/linux/ceph/cls_lock_client.h b/include/linux/ceph/cls_lock_client.h
index bea6c77d2093..17bc7584d1fe 100644
--- a/include/linux/ceph/cls_lock_client.h
+++ b/include/linux/ceph/cls_lock_client.h
@@ -52,4 +52,7 @@ int ceph_cls_lock_info(struct ceph_osd_client *osdc,
 		       char *lock_name, u8 *type, char **tag,
 		       struct ceph_locker **lockers, u32 *num_lockers);
 
+int ceph_cls_assert_locked(struct ceph_osd_request *req, int which,
+			   char *lock_name, u8 type, char *cookie, char *tag);
+
 #endif
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index a6c2a48d42e0..450384fe487c 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -218,18 +218,27 @@ static inline void ceph_encode_timespec64(struct ceph_timespec *tv,
 /*
  * sockaddr_storage <-> ceph_sockaddr
  */
-static inline void ceph_encode_addr(struct ceph_entity_addr *a)
+#define CEPH_ENTITY_ADDR_TYPE_NONE	0
+#define CEPH_ENTITY_ADDR_TYPE_LEGACY	__cpu_to_le32(1)
+
+static inline void ceph_encode_banner_addr(struct ceph_entity_addr *a)
 {
 	__be16 ss_family = htons(a->in_addr.ss_family);
 	a->in_addr.ss_family = *(__u16 *)&ss_family;
+
+	/* Banner addresses require TYPE_NONE */
+	a->type = CEPH_ENTITY_ADDR_TYPE_NONE;
 }
-static inline void ceph_decode_addr(struct ceph_entity_addr *a)
+static inline void ceph_decode_banner_addr(struct ceph_entity_addr *a)
 {
 	__be16 ss_family = *(__be16 *)&a->in_addr.ss_family;
 	a->in_addr.ss_family = ntohs(ss_family);
 	WARN_ON(a->in_addr.ss_family == 512);
+	a->type = CEPH_ENTITY_ADDR_TYPE_LEGACY;
 }
 
+extern int ceph_decode_entity_addr(void **p, void *end,
+				   struct ceph_entity_addr *addr);
 /*
  * encoders
  */
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 337d5049ff93..82156da3c650 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -84,11 +84,13 @@ struct ceph_options {
 #define CEPH_MSG_MAX_MIDDLE_LEN	(16*1024*1024)
 
 /*
- * Handle the largest possible rbd object in one message.
+ * The largest possible rbd data object is 32M.
+ * The largest possible rbd object map object is 64M.
+ *
  * There is no limit on the size of cephfs objects, but it has to obey
  * rsize and wsize mount options anyway.
  */
-#define CEPH_MSG_MAX_DATA_LEN	(32*1024*1024)
+#define CEPH_MSG_MAX_DATA_LEN	(64*1024*1024)
 
 #define CEPH_AUTH_NAME_DEFAULT   "guest"
 
@@ -299,10 +301,6 @@ int ceph_wait_for_latest_osdmap(struct ceph_client *client,
 
 /* pagevec.c */
 extern void ceph_release_page_vector(struct page **pages, int num_pages);
-
-extern struct page **ceph_get_direct_page_vector(const void __user *data,
-						 int num_pages,
-						 bool write_page);
 extern void ceph_put_page_vector(struct page **pages, int num_pages,
 				 bool dirty);
 extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index 3a4688af7455..b4d134d3312a 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -104,7 +104,6 @@ struct ceph_mon_client {
 #endif
 };
 
-extern struct ceph_monmap *ceph_monmap_decode(void *p, void *end);
 extern int ceph_monmap_contains(struct ceph_monmap *m,
 				struct ceph_entity_addr *addr);
 
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 2294f963dab7..ad7fe5d10dcd 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -198,9 +198,9 @@ struct ceph_osd_request {
 	bool              r_mempool;
 	struct completion r_completion;       /* private to osd_client.c */
 	ceph_osdc_callback_t r_callback;
-	struct list_head  r_unsafe_item;
 
 	struct inode *r_inode;         	      /* for use by callbacks */
+	struct list_head r_private_item;      /* ditto */
 	void *r_priv;			      /* ditto */
 
 	/* set by submitter */
@@ -389,6 +389,14 @@ extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
 void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb);
 void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err);
 
+#define osd_req_op_data(oreq, whch, typ, fld)				\
+({									\
+	struct ceph_osd_request *__oreq = (oreq);			\
+	unsigned int __whch = (whch);					\
+	BUG_ON(__whch >= __oreq->r_num_ops);				\
+	&__oreq->r_ops[__whch].typ.fld;					\
+})
+
 extern void osd_req_op_init(struct ceph_osd_request *osd_req,
 			    unsigned int which, u16 opcode, u32 flags);
 
@@ -497,7 +505,7 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
 		   const char *class, const char *method,
 		   unsigned int flags,
 		   struct page *req_page, size_t req_len,
-		   struct page *resp_page, size_t *resp_len);
+		   struct page **resp_pages, size_t *resp_len);
 
 extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,
 			       struct ceph_vino vino,
diff --git a/include/linux/ceph/striper.h b/include/linux/ceph/striper.h
index cbd0d24b7148..3486636c0e6e 100644
--- a/include/linux/ceph/striper.h
+++ b/include/linux/ceph/striper.h
@@ -66,4 +66,6 @@ int ceph_extent_to_file(struct ceph_file_layout *l,
 			struct ceph_file_extent **file_extents,
 			u32 *num_file_extents);
 
+u64 ceph_get_num_objects(struct ceph_file_layout *l, u64 size);
+
 #endif
diff --git a/include/linux/iversion.h b/include/linux/iversion.h
index be50ef7cedab..2917ef990d43 100644
--- a/include/linux/iversion.h
+++ b/include/linux/iversion.h
@@ -113,6 +113,30 @@ inode_peek_iversion_raw(const struct inode *inode)
 }
 
 /**
+ * inode_set_max_iversion_raw - update i_version new value is larger
+ * @inode: inode to set
+ * @val: new i_version to set
+ *
+ * Some self-managed filesystems (e.g Ceph) will only update the i_version
+ * value if the new value is larger than the one we already have.
+ */
+static inline void
+inode_set_max_iversion_raw(struct inode *inode, u64 val)
+{
+	u64 cur, old;
+
+	cur = inode_peek_iversion_raw(inode);
+	for (;;) {
+		if (cur > val)
+			break;
+		old = atomic64_cmpxchg(&inode->i_version, cur, val);
+		if (likely(old == cur))
+			break;
+		cur = old;
+	}
+}
+
+/**
  * inode_set_iversion - set i_version to a particular value
  * @inode: inode to set
  * @val: new i_version value to set