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

Pull Ceph updates from Sage Weil:
 "A few groups of patches here.  Alex has been hard at work improving
  the RBD code, layout groundwork for understanding the new formats and
  doing layering.  Most of the infrastructure is now in place for the
  final bits that will come with the next window.

  There are a few changes to the data layout.  Jim Schutt's patch fixes
  some non-ideal CRUSH behavior, and a set of patches from me updates
  the client to speak a newer version of the protocol and implement an
  improved hashing strategy across storage nodes (when the server side
  supports it too).

  A pair of patches from Sam Lang fix the atomicity of open+create
  operations.  Several patches from Yan, Zheng fix various mds/client
  issues that turned up during multi-mds torture tests.

  A final set of patches expose file layouts via virtual xattrs, and
  allow the policies to be set on directories via xattrs as well
  (avoiding the awkward ioctl interface and providing a consistent
  interface for both kernel mount and ceph-fuse users)."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (143 commits)
  libceph: add support for HASHPSPOOL pool flag
  libceph: update osd request/reply encoding
  libceph: calculate placement based on the internal data types
  ceph: update support for PGID64, PGPOOL3, OSDENC protocol features
  ceph: update "ceph_features.h"
  libceph: decode into cpu-native ceph_pg type
  libceph: rename ceph_pg -> ceph_pg_v1
  rbd: pass length, not op for osd completions
  rbd: move rbd_osd_trivial_callback()
  libceph: use a do..while loop in con_work()
  libceph: use a flag to indicate a fault has occurred
  libceph: separate non-locked fault handling
  libceph: encapsulate connection backoff
  libceph: eliminate sparse warnings
  ceph: eliminate sparse warnings in fs code
  rbd: eliminate sparse warnings
  libceph: define connection flag helpers
  rbd: normalize dout() calls
  rbd: barriers are hard
  rbd: ignore zero-length requests
  ...

1 files changed, 75 insertions, 83 deletions

diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 2c04afeead1..68c96a508ac 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -9,14 +9,6 @@
 #include <linux/ceph/msgr.h>
 
 /*
- * osdmap encoding versions
- */
-#define CEPH_OSDMAP_INC_VERSION     5
-#define CEPH_OSDMAP_INC_VERSION_EXT 6
-#define CEPH_OSDMAP_VERSION         5
-#define CEPH_OSDMAP_VERSION_EXT     6
-
-/*
  * fs id
  */
 struct ceph_fsid {
@@ -64,7 +56,7 @@ struct ceph_timespec {
  * placement group.
  * we encode this into one __le64.
  */
-struct ceph_pg {
+struct ceph_pg_v1 {
 	__le16 preferred; /* preferred primary osd */
 	__le16 ps;        /* placement seed */
 	__le32 pool;      /* object pool */
@@ -91,21 +83,6 @@ struct ceph_pg {
 
 #define CEPH_PG_TYPE_REP     1
 #define CEPH_PG_TYPE_RAID4   2
-#define CEPH_PG_POOL_VERSION 2
-struct ceph_pg_pool {
-	__u8 type;                /* CEPH_PG_TYPE_* */
-	__u8 size;                /* number of osds in each pg */
-	__u8 crush_ruleset;       /* crush placement rule */
-	__u8 object_hash;         /* hash mapping object name to ps */
-	__le32 pg_num, pgp_num;   /* number of pg's */
-	__le32 lpg_num, lpgp_num; /* number of localized pg's */
-	__le32 last_change;       /* most recent epoch changed */
-	__le64 snap_seq;          /* seq for per-pool snapshot */
-	__le32 snap_epoch;        /* epoch of last snap */
-	__le32 num_snaps;
-	__le32 num_removed_snap_intervals; /* if non-empty, NO per-pool snaps */
-	__le64 auid;               /* who owns the pg */
-} __attribute__ ((packed));
 
 /*
  * stable_mod func is used to control number of placement groups.
@@ -128,7 +105,7 @@ static inline int ceph_stable_mod(int x, int b, int bmask)
  * object layout - how a given object should be stored.
  */
 struct ceph_object_layout {
-	struct ceph_pg ol_pgid;   /* raw pg, with _full_ ps precision. */
+	struct ceph_pg_v1 ol_pgid;   /* raw pg, with _full_ ps precision. */
 	__le32 ol_stripe_unit;    /* for per-object parity, if any */
 } __attribute__ ((packed));
 
@@ -145,8 +122,12 @@ struct ceph_eversion {
  */
 
 /* status bits */
-#define CEPH_OSD_EXISTS 1
-#define CEPH_OSD_UP     2
+#define CEPH_OSD_EXISTS  (1<<0)
+#define CEPH_OSD_UP      (1<<1)
+#define CEPH_OSD_AUTOOUT (1<<2)  /* osd was automatically marked out */
+#define CEPH_OSD_NEW     (1<<3)  /* osd is new, never marked in */
+
+extern const char *ceph_osd_state_name(int s);
 
 /* osd weights.  fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */
 #define CEPH_OSD_IN  0x10000
@@ -161,9 +142,25 @@ struct ceph_eversion {
 #define CEPH_OSDMAP_PAUSERD  (1<<2)  /* pause all reads */
 #define CEPH_OSDMAP_PAUSEWR  (1<<3)  /* pause all writes */
 #define CEPH_OSDMAP_PAUSEREC (1<<4)  /* pause recovery */
+#define CEPH_OSDMAP_NOUP     (1<<5)  /* block osd boot */
+#define CEPH_OSDMAP_NODOWN   (1<<6)  /* block osd mark-down/failure */
+#define CEPH_OSDMAP_NOOUT    (1<<7)  /* block osd auto mark-out */
+#define CEPH_OSDMAP_NOIN     (1<<8)  /* block osd auto mark-in */
+#define CEPH_OSDMAP_NOBACKFILL (1<<9) /* block osd backfill */
+#define CEPH_OSDMAP_NORECOVER (1<<10) /* block osd recovery and backfill */
+
+/*
+ * The error code to return when an OSD can't handle a write
+ * because it is too large.
+ */
+#define OSD_WRITETOOBIG EMSGSIZE
 
 /*
  * osd ops
+ *
+ * WARNING: do not use these op codes directly.  Use the helpers
+ * defined below instead.  In certain cases, op code behavior was
+ * redefined, resulting in special-cases in the helpers.
  */
 #define CEPH_OSD_OP_MODE       0xf000
 #define CEPH_OSD_OP_MODE_RD    0x1000
@@ -177,6 +174,7 @@ struct ceph_eversion {
 #define CEPH_OSD_OP_TYPE_ATTR  0x0300
 #define CEPH_OSD_OP_TYPE_EXEC  0x0400
 #define CEPH_OSD_OP_TYPE_PG    0x0500
+#define CEPH_OSD_OP_TYPE_MULTI 0x0600 /* multiobject */
 
 enum {
 	/** data **/
@@ -217,6 +215,23 @@ enum {
 
 	CEPH_OSD_OP_WATCH   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 15,
 
+	/* omap */
+	CEPH_OSD_OP_OMAPGETKEYS   = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 17,
+	CEPH_OSD_OP_OMAPGETVALS   = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 18,
+	CEPH_OSD_OP_OMAPGETHEADER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 19,
+	CEPH_OSD_OP_OMAPGETVALSBYKEYS  =
+	  CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 20,
+	CEPH_OSD_OP_OMAPSETVALS   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 21,
+	CEPH_OSD_OP_OMAPSETHEADER = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 22,
+	CEPH_OSD_OP_OMAPCLEAR     = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 23,
+	CEPH_OSD_OP_OMAPRMKEYS    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 24,
+	CEPH_OSD_OP_OMAP_CMP      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 25,
+
+	/** multi **/
+	CEPH_OSD_OP_CLONERANGE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_MULTI | 1,
+	CEPH_OSD_OP_ASSERT_SRC_VERSION = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 2,
+	CEPH_OSD_OP_SRC_CMPXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 3,
+
 	/** attrs **/
 	/* read */
 	CEPH_OSD_OP_GETXATTR  = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1,
@@ -238,6 +253,7 @@ enum {
 	CEPH_OSD_OP_SCRUB_RESERVE   = CEPH_OSD_OP_MODE_SUB | 6,
 	CEPH_OSD_OP_SCRUB_UNRESERVE = CEPH_OSD_OP_MODE_SUB | 7,
 	CEPH_OSD_OP_SCRUB_STOP      = CEPH_OSD_OP_MODE_SUB | 8,
+	CEPH_OSD_OP_SCRUB_MAP     = CEPH_OSD_OP_MODE_SUB | 9,
 
 	/** lock **/
 	CEPH_OSD_OP_WRLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1,
@@ -248,10 +264,12 @@ enum {
 	CEPH_OSD_OP_DNLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6,
 
 	/** exec **/
+	/* note: the RD bit here is wrong; see special-case below in helper */
 	CEPH_OSD_OP_CALL    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1,
 
 	/** pg **/
 	CEPH_OSD_OP_PGLS      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1,
+	CEPH_OSD_OP_PGLS_FILTER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 2,
 };
 
 static inline int ceph_osd_op_type_lock(int op)
@@ -274,6 +292,10 @@ static inline int ceph_osd_op_type_pg(int op)
 {
 	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_PG;
 }
+static inline int ceph_osd_op_type_multi(int op)
+{
+	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_MULTI;
+}
 
 static inline int ceph_osd_op_mode_subop(int op)
 {
@@ -281,11 +303,12 @@ static inline int ceph_osd_op_mode_subop(int op)
 }
 static inline int ceph_osd_op_mode_read(int op)
 {
-	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_RD;
+	return (op & CEPH_OSD_OP_MODE_RD) &&
+		op != CEPH_OSD_OP_CALL;
 }
 static inline int ceph_osd_op_mode_modify(int op)
 {
-	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_WR;
+	return op & CEPH_OSD_OP_MODE_WR;
 }
 
 /*
@@ -294,34 +317,38 @@ static inline int ceph_osd_op_mode_modify(int op)
  */
 #define CEPH_OSD_TMAP_HDR 'h'
 #define CEPH_OSD_TMAP_SET 's'
+#define CEPH_OSD_TMAP_CREATE 'c' /* create key */
 #define CEPH_OSD_TMAP_RM  'r'
+#define CEPH_OSD_TMAP_RMSLOPPY 'R'
 
 extern const char *ceph_osd_op_name(int op);
 
-
 /*
  * osd op flags
  *
  * An op may be READ, WRITE, or READ|WRITE.
  */
 enum {
-	CEPH_OSD_FLAG_ACK = 1,          /* want (or is) "ack" ack */
-	CEPH_OSD_FLAG_ONNVRAM = 2,      /* want (or is) "onnvram" ack */
-	CEPH_OSD_FLAG_ONDISK = 4,       /* want (or is) "ondisk" ack */
-	CEPH_OSD_FLAG_RETRY = 8,        /* resend attempt */
-	CEPH_OSD_FLAG_READ = 16,        /* op may read */
-	CEPH_OSD_FLAG_WRITE = 32,       /* op may write */
-	CEPH_OSD_FLAG_ORDERSNAP = 64,   /* EOLDSNAP if snapc is out of order */
-	CEPH_OSD_FLAG_PEERSTAT = 128,   /* msg includes osd_peer_stat */
-	CEPH_OSD_FLAG_BALANCE_READS = 256,
-	CEPH_OSD_FLAG_PARALLELEXEC = 512, /* execute op in parallel */
-	CEPH_OSD_FLAG_PGOP = 1024,      /* pg op, no object */
-	CEPH_OSD_FLAG_EXEC = 2048,      /* op may exec */
-	CEPH_OSD_FLAG_EXEC_PUBLIC = 4096, /* op may exec (public) */
+	CEPH_OSD_FLAG_ACK =            0x0001,  /* want (or is) "ack" ack */
+	CEPH_OSD_FLAG_ONNVRAM =        0x0002,  /* want (or is) "onnvram" ack */
+	CEPH_OSD_FLAG_ONDISK =         0x0004,  /* want (or is) "ondisk" ack */
+	CEPH_OSD_FLAG_RETRY =          0x0008,  /* resend attempt */
+	CEPH_OSD_FLAG_READ =           0x0010,  /* op may read */
+	CEPH_OSD_FLAG_WRITE =          0x0020,  /* op may write */
+	CEPH_OSD_FLAG_ORDERSNAP =      0x0040,  /* EOLDSNAP if snapc is out of order */
+	CEPH_OSD_FLAG_PEERSTAT_OLD =   0x0080,  /* DEPRECATED msg includes osd_peer_stat */
+	CEPH_OSD_FLAG_BALANCE_READS =  0x0100,
+	CEPH_OSD_FLAG_PARALLELEXEC =   0x0200,  /* execute op in parallel */
+	CEPH_OSD_FLAG_PGOP =           0x0400,  /* pg op, no object */
+	CEPH_OSD_FLAG_EXEC =           0x0800,  /* op may exec */
+	CEPH_OSD_FLAG_EXEC_PUBLIC =    0x1000,  /* DEPRECATED op may exec (public) */
+	CEPH_OSD_FLAG_LOCALIZE_READS = 0x2000,  /* read from nearby replica, if any */
+	CEPH_OSD_FLAG_RWORDERED =      0x4000,  /* order wrt concurrent reads */
 };
 
 enum {
 	CEPH_OSD_OP_FLAG_EXCL = 1,      /* EXCL object create */
+	CEPH_OSD_OP_FLAG_FAILOK = 2,    /* continue despite failure */
 };
 
 #define EOLDSNAPC    ERESTART  /* ORDERSNAP flag set; writer has old snapc*/
@@ -381,48 +408,13 @@ struct ceph_osd_op {
 			__le64 ver;
 			__u8 flag;	/* 0 = unwatch, 1 = watch */
 		} __attribute__ ((packed)) watch;
-};
+		struct {
+			__le64 offset, length;
+			__le64 src_offset;
+		} __attribute__ ((packed)) clonerange;
+	};
 	__le32 payload_len;
 } __attribute__ ((packed));
 
-/*
- * osd request message header.  each request may include multiple
- * ceph_osd_op object operations.
- */
-struct ceph_osd_request_head {
-	__le32 client_inc;                 /* client incarnation */
-	struct ceph_object_layout layout;  /* pgid */
-	__le32 osdmap_epoch;               /* client's osdmap epoch */
-
-	__le32 flags;
-
-	struct ceph_timespec mtime;        /* for mutations only */
-	struct ceph_eversion reassert_version; /* if we are replaying op */
-
-	__le32 object_len;     /* length of object name */
-
-	__le64 snapid;         /* snapid to read */
-	__le64 snap_seq;       /* writer's snap context */
-	__le32 num_snaps;
-
-	__le16 num_ops;
-	struct ceph_osd_op ops[];  /* followed by ops[], obj, ticket, snaps */
-} __attribute__ ((packed));
-
-struct ceph_osd_reply_head {
-	__le32 client_inc;                /* client incarnation */
-	__le32 flags;
-	struct ceph_object_layout layout;
-	__le32 osdmap_epoch;
-	struct ceph_eversion reassert_version; /* for replaying uncommitted */
-
-	__le32 result;                    /* result code */
-
-	__le32 object_len;                /* length of object name */
-	__le32 num_ops;
-	struct ceph_osd_op ops[0];  /* ops[], object */
-} __attribute__ ((packed));
-
-
 
 #endif