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

Pull Ceph changes from Sage Weil:
 "Lots of stuff this time around:

   - lots of cleanup and refactoring in the libceph messenger code, and
     many hard to hit races and bugs closed as a result.
   - lots of cleanup and refactoring in the rbd code from Alex Elder,
     mostly in preparation for the layering functionality that will be
     coming in 3.7.
   - some misc rbd cleanups from Josh Durgin that are finally going
     upstream
   - support for CRUSH tunables (used by newer clusters to improve the
     data placement)
   - some cleanup in our use of d_parent that Al brought up a while back
   - a random collection of fixes across the tree

  There is another patch coming that fixes up our ->atomic_open()
  behavior, but I'm going to hammer on it a bit more before sending it."

Fix up conflicts due to commits that were already committed earlier in
drivers/block/rbd.c, net/ceph/{messenger.c, osd_client.c}

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (132 commits)
  rbd: create rbd_refresh_helper()
  rbd: return obj version in __rbd_refresh_header()
  rbd: fixes in rbd_header_from_disk()
  rbd: always pass ops array to rbd_req_sync_op()
  rbd: pass null version pointer in add_snap()
  rbd: make rbd_create_rw_ops() return a pointer
  rbd: have __rbd_add_snap_dev() return a pointer
  libceph: recheck con state after allocating incoming message
  libceph: change ceph_con_in_msg_alloc convention to be less weird
  libceph: avoid dropping con mutex before fault
  libceph: verify state after retaking con lock after dispatch
  libceph: revoke mon_client messages on session restart
  libceph: fix handling of immediate socket connect failure
  ceph: update MAINTAINERS file
  libceph: be less chatty about stray replies
  libceph: clear all flags on con_close
  libceph: clean up con flags
  libceph: replace connection state bits with states
  libceph: drop unnecessary CLOSED check in socket state change callback
  libceph: close socket directly from ceph_con_close()
  ...

include/linux/ceph/ceph_features.h

@@ -0,0 +1,27 @@
+#ifndef __CEPH_FEATURES
+#define __CEPH_FEATURES
+
+/*
+ * feature bits
+ */
+#define CEPH_FEATURE_UID            (1<<0)
+#define CEPH_FEATURE_NOSRCADDR      (1<<1)
+#define CEPH_FEATURE_MONCLOCKCHECK  (1<<2)
+#define CEPH_FEATURE_FLOCK          (1<<3)
+#define CEPH_FEATURE_SUBSCRIBE2     (1<<4)
+#define CEPH_FEATURE_MONNAMES       (1<<5)
+#define CEPH_FEATURE_RECONNECT_SEQ  (1<<6)
+#define CEPH_FEATURE_DIRLAYOUTHASH  (1<<7)
+/* bits 8-17 defined by user-space; not supported yet here */
+#define CEPH_FEATURE_CRUSH_TUNABLES (1<<18)
+
+/*
+ * Features supported.
+ */
+#define CEPH_FEATURES_SUPPORTED_DEFAULT  \
+	(CEPH_FEATURE_NOSRCADDR |	 \
+	 CEPH_FEATURE_CRUSH_TUNABLES)
+
+#define CEPH_FEATURES_REQUIRED_DEFAULT   \
+	(CEPH_FEATURE_NOSRCADDR)
+#endif

include/linux/ceph/ceph_fs.h

@@ -35,20 +35,6 @@
 /* arbitrary limit on max # of monitors (cluster of 3 is typical) */
 #define CEPH_MAX_MON   31
 
-
-/*
- * feature bits
- */
-#define CEPH_FEATURE_UID            (1<<0)
-#define CEPH_FEATURE_NOSRCADDR      (1<<1)
-#define CEPH_FEATURE_MONCLOCKCHECK  (1<<2)
-#define CEPH_FEATURE_FLOCK          (1<<3)
-#define CEPH_FEATURE_SUBSCRIBE2     (1<<4)
-#define CEPH_FEATURE_MONNAMES       (1<<5)
-#define CEPH_FEATURE_RECONNECT_SEQ  (1<<6)
-#define CEPH_FEATURE_DIRLAYOUTHASH  (1<<7)
-
-
 /*
  * ceph_file_layout - describe data layout for a file/inode
  */

include/linux/ceph/decode.h

@@ -1,6 +1,7 @@
 #ifndef __CEPH_DECODE_H
 #define __CEPH_DECODE_H
 
+#include <linux/err.h>
 #include <linux/bug.h>
 #include <linux/time.h>
 #include <asm/unaligned.h>
@@ -84,6 +85,52 @@ static inline int ceph_has_room(void **p, void *end, size_t n)
 		ceph_decode_copy(p, pv, n);			\
 	} while (0)
 
+/*
+ * Allocate a buffer big enough to hold the wire-encoded string, and
+ * decode the string into it.  The resulting string will always be
+ * terminated with '\0'.  If successful, *p will be advanced
+ * past the decoded data.  Also, if lenp is not a null pointer, the
+ * length (not including the terminating '\0') will be recorded in
+ * *lenp.  Note that a zero-length string is a valid return value.
+ *
+ * Returns a pointer to the newly-allocated string buffer, or a
+ * pointer-coded errno if an error occurs.  Neither *p nor *lenp
+ * will have been updated if an error is returned.
+ *
+ * There are two possible failures:
+ *   - converting the string would require accessing memory at or
+ *     beyond the "end" pointer provided (-E
+ *   - memory could not be allocated for the result
+ */
+static inline char *ceph_extract_encoded_string(void **p, void *end,
+						size_t *lenp, gfp_t gfp)
+{
+	u32 len;
+	void *sp = *p;
+	char *buf;
+
+	ceph_decode_32_safe(&sp, end, len, bad);
+	if (!ceph_has_room(&sp, end, len))
+		goto bad;
+
+	buf = kmalloc(len + 1, gfp);
+	if (!buf)
+		return ERR_PTR(-ENOMEM);
+
+	if (len)
+		memcpy(buf, sp, len);
+	buf[len] = '\0';
+
+	*p = (char *) *p + sizeof (u32) + len;
+	if (lenp)
+		*lenp = (size_t) len;
+
+	return buf;
+
+bad:
+	return ERR_PTR(-ERANGE);
+}
+
 /*
  * struct ceph_timespec <-> struct timespec
  */
@@ -151,7 +198,7 @@ static inline void ceph_encode_filepath(void **p, void *end,
 					u64 ino, const char *path)
 {
 	u32 len = path ? strlen(path) : 0;
-	BUG_ON(*p + sizeof(ino) + sizeof(len) + len > end);
+	BUG_ON(*p + 1 + sizeof(ino) + sizeof(len) + len > end);
 	ceph_encode_8(p, 1);
 	ceph_encode_64(p, ino);
 	ceph_encode_32(p, len);

include/linux/ceph/libceph.h

@@ -22,12 +22,6 @@
 #include "osd_client.h"
 #include "ceph_fs.h"
 
-/*
- * Supported features
- */
-#define CEPH_FEATURE_SUPPORTED_DEFAULT CEPH_FEATURE_NOSRCADDR
-#define CEPH_FEATURE_REQUIRED_DEFAULT  CEPH_FEATURE_NOSRCADDR
-
 /*
  * mount options
  */
@@ -132,7 +126,7 @@ struct ceph_client {
 	u32 supported_features;
 	u32 required_features;
 
-	struct ceph_messenger *msgr;   /* messenger instance */
+	struct ceph_messenger msgr;   /* messenger instance */
 	struct ceph_mon_client monc;
 	struct ceph_osd_client osdc;
 
@@ -160,7 +154,7 @@ struct ceph_client {
 struct ceph_snap_context {
 	atomic_t nref;
 	u64 seq;
-	int num_snaps;
+	u32 num_snaps;
 	u64 snaps[];
 };
 

include/linux/ceph/messenger.h

@@ -31,9 +31,6 @@ struct ceph_connection_operations {
 	int (*verify_authorizer_reply) (struct ceph_connection *con, int len);
 	int (*invalidate_authorizer)(struct ceph_connection *con);
 
-	/* protocol version mismatch */
-	void (*bad_proto) (struct ceph_connection *con);
-
 	/* there was some error on the socket (disconnect, whatever) */
 	void (*fault) (struct ceph_connection *con);
 
@@ -53,6 +50,7 @@ struct ceph_messenger {
 	struct ceph_entity_inst inst;    /* my name+address */
 	struct ceph_entity_addr my_enc_addr;
 
+	atomic_t stopping;
 	bool nocrc;
 
 	/*
@@ -80,7 +78,10 @@ struct ceph_msg {
 	unsigned nr_pages;              /* size of page array */
 	unsigned page_alignment;        /* io offset in first page */
 	struct ceph_pagelist *pagelist; /* instead of pages */
+
+	struct ceph_connection *con;
 	struct list_head list_head;
+
 	struct kref kref;
 	struct bio  *bio;		/* instead of pages/pagelist */
 	struct bio  *bio_iter;		/* bio iterator */
@@ -105,23 +106,6 @@ struct ceph_msg_pos {
 #define BASE_DELAY_INTERVAL	(HZ/2)
 #define MAX_DELAY_INTERVAL	(5 * 60 * HZ)
 
-/*
- * ceph_connection state bit flags
- */
-#define LOSSYTX         0  /* we can close channel or drop messages on errors */
-#define CONNECTING	1
-#define NEGOTIATING	2
-#define KEEPALIVE_PENDING      3
-#define WRITE_PENDING	4  /* we have data ready to send */
-#define STANDBY		8  /* no outgoing messages, socket closed.  we keep
-			    * the ceph_connection around to maintain shared
-			    * state with the peer. */
-#define CLOSED		10 /* we've closed the connection */
-#define SOCK_CLOSED	11 /* socket state changed to closed */
-#define OPENING         13 /* open connection w/ (possibly new) peer */
-#define DEAD            14 /* dead, about to kfree */
-#define BACKOFF         15
-
 /*
  * A single connection with another host.
  *
@@ -131,18 +115,22 @@ struct ceph_msg_pos {
  */
 struct ceph_connection {
 	void *private;
-	atomic_t nref;
 
 	const struct ceph_connection_operations *ops;
 
 	struct ceph_messenger *msgr;
+
+	atomic_t sock_state;
 	struct socket *sock;
-	unsigned long state;	/* connection state (see flags above) */
+	struct ceph_entity_addr peer_addr; /* peer address */
+	struct ceph_entity_addr peer_addr_for_me;
+
+	unsigned long flags;
+	unsigned long state;
 	const char *error_msg;  /* error message, if any */
 
-	struct ceph_entity_addr peer_addr; /* peer address */
 	struct ceph_entity_name peer_name; /* peer name */
-	struct ceph_entity_addr peer_addr_for_me;
+
 	unsigned peer_features;
 	u32 connect_seq;      /* identify the most recent connection
 				 attempt for this connection, client */
@@ -207,24 +195,26 @@ extern int ceph_msgr_init(void);
 extern void ceph_msgr_exit(void);
 extern void ceph_msgr_flush(void);
 
-extern struct ceph_messenger *ceph_messenger_create(
-	struct ceph_entity_addr *myaddr,
-	u32 features, u32 required);
-extern void ceph_messenger_destroy(struct ceph_messenger *);
+extern void ceph_messenger_init(struct ceph_messenger *msgr,
+			struct ceph_entity_addr *myaddr,
+			u32 supported_features,
+			u32 required_features,
+			bool nocrc);
 
-extern void ceph_con_init(struct ceph_messenger *msgr,
-			  struct ceph_connection *con);
+extern void ceph_con_init(struct ceph_connection *con, void *private,
+			const struct ceph_connection_operations *ops,
+			struct ceph_messenger *msgr);
 extern void ceph_con_open(struct ceph_connection *con,
+			  __u8 entity_type, __u64 entity_num,
 			  struct ceph_entity_addr *addr);
 extern bool ceph_con_opened(struct ceph_connection *con);
 extern void ceph_con_close(struct ceph_connection *con);
 extern void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg);
-extern void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg);
-extern void ceph_con_revoke_message(struct ceph_connection *con,
-				  struct ceph_msg *msg);
+
+extern void ceph_msg_revoke(struct ceph_msg *msg);
+extern void ceph_msg_revoke_incoming(struct ceph_msg *msg);
+
 extern void ceph_con_keepalive(struct ceph_connection *con);
-extern struct ceph_connection *ceph_con_get(struct ceph_connection *con);
-extern void ceph_con_put(struct ceph_connection *con);
 
 extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
 				     bool can_fail);

include/linux/ceph/mon_client.h

@@ -70,7 +70,7 @@ struct ceph_mon_client {
 	bool hunting;
 	int cur_mon;                       /* last monitor i contacted */
 	unsigned long sub_sent, sub_renew_after;
-	struct ceph_connection *con;
+	struct ceph_connection con;
 	bool have_fsid;
 
 	/* pending generic requests */

include/linux/ceph/msgpool.h

@@ -11,10 +11,11 @@
 struct ceph_msgpool {
 	const char *name;
 	mempool_t *pool;
+	int type;               /* preallocated message type */
 	int front_len;          /* preallocated payload size */
 };
 
-extern int ceph_msgpool_init(struct ceph_msgpool *pool,
+extern int ceph_msgpool_init(struct ceph_msgpool *pool, int type,
 			     int front_len, int size, bool blocking,
 			     const char *name);
 extern void ceph_msgpool_destroy(struct ceph_msgpool *pool);

include/linux/crush/crush.h

@@ -154,6 +154,14 @@ struct crush_map {
 	__s32 max_buckets;
 	__u32 max_rules;
 	__s32 max_devices;
+
+	/* choose local retries before re-descent */
+	__u32 choose_local_tries;
+	/* choose local attempts using a fallback permutation before
+	 * re-descent */
+	__u32 choose_local_fallback_tries;
+	/* choose attempts before giving up */ 
+	__u32 choose_total_tries;
 };